Tealium Learning Center

This article describes how to set up the Braze connector in your Customer Data Hub account. In this article: Table of Contents Placeholder Connector Actions Action Name AudienceStream EventStream Track User ✓ ✓ Delete User ✓ ✓ Consent Categories Analytics Mobile Personalization Configure Settings Go to the Connector Marketplace and add a new connector. Read the Connector Overview article for general instructions on how to add a connector. After adding the connector, configure the following settings: API Endpoint Required. Select API endpoint for the instance your account is provisioned to. For more information, see API Endpoints. API Key Required. Provide API key with "users.track" and "users.delete" permissions enabled. For more information, see App Group REST API Keys. Action Settings - Parameters and Options Click Next or go to the Actions tab. This is where you configure connector actions. This section describes how to set up parameters and options for each action. Action - Track User Parameters Parameter Description External ID External ID of the user to delete. When multiple IDs are specified, the first non-blank values is selected based on the following priority order: External ID Braze ID Alias Name Alias Label When importing Push Tokens, External ID and Braze ID should not be specified. For more information, see User Track. Braze ID Braze ID of the user to delete. When multiple IDs are specified, the first non-blank values is selected based on the following priority order: External ID Braze ID Alias Name Alias Label When importing Push Tokens, External ID and Braze ID should not be specified. For more information, see User Track. User Alias Name The alias name of the user to be tracked. When specifying a user alias, Alias Name and Alias Label should both be set. For more information, see User Track. User Alias Label The alias label of the user to be tracked. When specifying a user alias, Alias Name and Alias Label should both be set. For more information, see User Track. Country The country of the user to be tracked. Current Location - Latitude The current latitude for the user to be tracked. Current Location - Longitude The current longitude for the user to be tracked. Date of First Session The date of the first session of the user to be tracked. Date of Last Session The date of the last session of the user to be tracked. Date of Birth The date of birth for the user to be tracked. Email Address The email address for the user to be tracked. Email Subscription Status The email subscription status for the user to be tracked. Facebook The Facebook account for the user to be tracked. First Name The first name of the user to be tracked. Gender The gender of the user to be tracked. Values are Male (m) or Female (f). Home City The home city for the user to be tracked. Image URL Optional The URL for the user's image. Language The language preference of the user to be tracked. Last Name The last name of the user to be tracked. Marked Email As Spam At User marked email as spam. Phone Number The telephone number of the user to be tracked. Push Subscription Status The Push Subscription status of the user to be tracked. Push Tokens ID Array Array. The Push Token ID for the user to be tracked. Push Tokens Array Push tokens array. Push Tokens Device ID Array The Push Token Device ID for the user's device. Time Zone The time zone for the user to be tracked. Twitter The Twitter account for the user to be tracked. Update Existing Only (Users) Optional Values are true or false. If no user value exists, one will be created by default. If set to true, only existing users are updated and no new users are created. Modify User Attributes Integer attributes may be incremented by positive or negative integers. Array attributes may be modified by adding or removing values from existing arrays. App ID The User App ID to be tracked. Name The application name to be tracked. Time Time Update Existing Only (Events) Optional Values are true or false. If no event value exists, one will be created by default. If set to true, only existing events are updated and no new events are created. App ID The Event Application ID to be tracked. Product ID Required for every mapped purchase. Currency Required for every mapped purchase. Price Required for every mapped purchase. Quantity Map Array type attributes to add multiple purchase items. Array type attributes must be of equal length. Purchase Time Time of purchase. Automatically set to "now" unless explicitly mapped. Update Existing Only (Purchases) Optional Values are true or false. If no purchase value exists, one will be created by default. If set to true, only existing purchases are updated and no new purchases are created. Action - Delete User Parameters Parameter Description External ID External ID of the user to delete. When multiple IDs are specified, the first non-blank values is selected based on the following priority order: External ID Braze ID Alias Name Alias Label For more information, see User Delete Endpoint. Braze ID Braze ID of the user to delete. When multiple IDs are specified, the first non-blank values is selected based on the following priority order: External ID Braze ID Alias Name Alias Label Must include either External ID or Braze ID. User Alias Name The alias name of the user to be deleted. When specifying a user alias, Alias Name and Alias Label should both be set. For more information, see User Delete Endpoint. User Alias Label The alias label of the user to be deleted. When specifying a user alias, Alias Name and Alias Label should both be set. ... View more

This article describes how to manage server-side users and permission roles for the Tealium Customer Data Hub. This article covers the following topics: Table of Contents Placeholder How It Works Server-side user permissions provide control over the degree of access users have for each profile by creating a separation of access between the Tealium client-side interface and the server-side interface. This allows account administrators to grant access to users only for the areas that they intend to work on. New users for accounts are still added in Tealium iQ Tag Management. Once added, the new users appear in the server-side user permissions list where server-side access is granted by profile. Additional features include the ability to add and edit users in bulk (up to 25 users at a time) and the ability to search user profiles and filter users by permission type. Admin Users Admins of the server-side interface are the only users that have the ability to change the permissions of server-side users. None of the server-side permission roles grant this ability. To be an admin on the server-side, you must have the Manage Account permission in the client-side interface. Only the Manage Users permission on the client side grants the ability to add users to the account. To learn more about managing user permission in Tealium iQ Tag Management, see Managing User Permissions in iQ Tag Management. Server-Side Permission Roles Server-side access is controlled using predefined permission roles. For each profile in the account, users are assigned a permission role to determine their access level. The following table describes the four (4) available server-side permission roles: PERMISSION ROLE DESCRIPTION No Access (default) The No Access permission role does not grant any access to the server-side profile. If the user attempts to access the server-side, their profile is blocked and an "Access Denied" message displays. Reader The Reader permission grants read-only access to the server-side profile. A user in this role can browse the profile configuration, but the Save/Publish button is disabled. Users with this role cannot save any changes. Editor The Editor permission grants edit and save access to the server-side profile. With this role, you can save but not publish. Users with this role can also access and edit settings from the Profile Admin > Settings menu. Publisher The Publisher permission grants the same access as the Editor role, with the addition of the ability to save and publish the profile. Profile access between the server-side and client-side product is mutually exclusive. For example, you can grant Save and Publish permissions for client-side products without impacting server-side product permissions for a given profile. In addition, if you remove or change user access to a profile on the client-side, it is not removed or changed on the server-side. Add a Server-Side Only User To give a user access to server-side, you must first add them in the client-side interface. In the client-side interface you must have the Manage Users permission to add users to your account and the Manage Account permission to manage permissions in the server-side interface. To add a user with only permission to a server-side profile, follow these steps: In the client-side interface, add the user, but do not select any client-side permissions. The user must verify their email address before you can continue, at which point the user will have read-only access to the client-side interface and will appear in the Manage Users list in the server-side interface. In the server-side interface, go to Manage Users and assign permission roles to grant the user access to a server-side profile. Click Next. Save your changes. Return to the client-side interface. Go to Manage Users and remove the user. (Learn more) The user will no longer have access to the client-side profile, but will retain access to the server-side profile. Edit Server-Side User Permissions To edit server-side user permissions, you must have the Manage Account permission, which is assigned from the client-side interface. Use the following steps to view and edit server-side permissions for a user: Log into the server-side area of the Customer Data Hub. Click the drop-down menu in the upper right of screen and select Manage Users. A list of all server-side users displays, including the user's name, email address, and a timestamp for the last login. Click a user to display the permission details. The details for that user display. To grant access to a profile, select a permission role from the drop-down list. Repeat Step 3 through Step 5 for each user you want to edit. If no changes are needed, click X to close the user details and return to the user list. You will be prompted to confirm your intention to disregard changes if you have made adjustments. Click Stay to keep your changes or Discard to discard the changes. Your changes are saved without the need to publish. Edit User Permission Roles in Bulk Use the following steps to edit the permission role for multiple users: Click the drop-down menu in the upper right of screen and select Manage Users. Check the box to the left of each user for which you want to change the permission role. Click Bulk Actions and use the drop-down list to change the permissions for the selected users. Click Apply. Click Save in the upper right corner. You do not need to publish for your changes to persist. Frequently Asked Questions (FAQ) If a user is removed from the client-side profile, is the user also removed from the server-side profile? No. Once a user exists in both client-side and server-side, removing the user from one does not impact the other. Can I grant a user access to a server-side profile without allowing access to a client-side profile? Yes. If a user already exists in the account and has been granted permission to a profile on the server-side, go to iQ Tag Management > Manage Users and remove that user from the client-side interface. See the Adding Users section for more information. How does the "All current and future profiles" option impact server-side permissions? There is no impact to server-side users. All server-side users will have the default permission role of No Access to all new server-side profiles. What happens if a user has access to only one profile on the server-side and no profile access on the client-side? If the user selects server-side at the login screen, they will automatically be loaded into the account/profile accordingly. If the user attempts to log in to the client-side, a modal displays with a denied access message. Can a server-side admin change their own permissions for server-side profiles? Yes. A server-side admin user (granted by the Manage Account permission) can change permissions for all server-side users, including their own. Can a server-side admin update manage permissions for all server-side profiles? Yes. A server-side admin user's access is granted by the Manage Account permission, which is an account-level permission. Users with this permission level have access to the Manage Users screen in the server-side interface where they can manage user permissions for all profiles. How do the new server-side permissions affect the Omnichannel File Status API? Access control to the Omichannel File Status API will change upon final release of the server-side permissions feature. In addition to the standard requirement of needing an API key to authenticate with the API, users must have read access to the relevant Customer Data Hub account. Users utilizing the v1 API only need read access to the Customer Data Hub account. Can a server-side admin add new users to an account? No. The Manage Account permission does not grant access to add new users or delete users from an account. While they can remove access to profiles, only users who have the Manage Users permission assigned in the iQ Tag Management workflow can invite a new user to an account or completely delete a user from an account. Does this feature change the way user management access is granted or controlled within TiQ? No. The Manage Users checkbox in iQ Tag Management remains the permission that grants a user access to add or remove users from a business account. Users with only the Manage User permission will not have access to manage permissions on the server-side. Additional Resources Managing User Permissions in iQ Tag Management ... View more

This article describes how to set up the Xandr (Formerly AppNexus) Real Time Segments (Tealium-Provided Credentials) connector. To request access to this connector, you must first contact your Tealium account manager. The underlying integration for this connector uses Xandr functionality that is also in the Alpha-Beta phase with Xandr and is therefore subject to change. (Learn more) In this article: Table of Contents Placeholder How it Works The Instant Audience Service is a server-side method that uses streaming architecture to add individual or small groups of users to segments using the Xandr API. Rather than aggregating and periodically sending large batches of data using the Batch Segment Service, the Instant Audience Service associates users to segments in near real-time. Prerequisites Xandr Member ID shared with Tealium's Xandr member. To request access, you must first contact your Tealium account manager. Getting Started Obtain Authorization To begin using the Instant Audience Service and enable this integration, you will need to open a ticket with Xandr to have your member shared with Tealium's Member (9537). Provide the following information in a support request to Xandr: Are you using external user IDs? For example, do you use mapUID to store the mapping with Xandr? If you use another member's external user IDs, include their member_id as well. Do you need to populate segments belonging to other members? If so, provide the associated member_ids . Tealium's Member ID is 9537. When you would like your segments to expire by default? For example, never expire, expire 60 days from now, etc.? If you include EXPIRATION in your seg block, your default expiration will not be used. The following questions are for internal capacity planning: What is the number of unique user IDs per post? What is the number of expected posts per day? What is the number of unique segments per post? Xandr typically responds to these requests within 1-3 business days. Action Endpoint https://streaming-data.appnexus.com/rt-segment Connector Actions Action Name AudienceStream EventStream Add User to Segment ✓ ✓ Remove User From Segment ✓ ✓ Configure Settings Go to the Connector Marketplace and add the connector. Read the Connector Overview article for general instructions on how to add a connector. Action Settings - Parameters and Options Click Next or go to the Actions tab. This is where you configure connector actions. This section describes how to set up parameters and options for each action. Action - Add User to Segment Parameters Parameter Description AAID Android Advertising Identifier. The mobile device ID for Android devices. Example: AEBE52E7-03EE-455A-B3C4-E57283966239 Xandr/AppNexus User ID The User ID returned by the cookie match endpoint. Example: 12345678900987654321 In addition to configuring the connector, Tealium recommends pairing with the Cookie Match tag. This tag performs a cookie sync to exchange device IDs, which facilitates the server-to-server actions described below. (Learn more IDFA Identifier for Advertisers. The mobile device ID for iOS devices. Example: 6D92078A-8246-4BA4-AE5B-76104861E7DC MD5 UDID The MD5 hashed value of the User ID. Example: 4a8a2b374f463b7aedbb44a066363b81 Open UDID Deprecated, do not use. SH1 UDID The SHA1 hashed value of the User ID. Example: F12877BFFD9C07E7224C9A6EFB7A709F4E29FDEA SHA1 MAC Deprecated, do not use. Tealium Visitor ID Deprecated, do not use. Expiration The lifetime of the user-segment association in minutes, starting from when we read it. A value of zero (0) means that the segment never expires. A value of negative one (-1) means that the user is to be removed from this segment. Example: 1440 Member ID The ID of the member that owns this segment or has been shared the segment by data provider Tealium. Example: 9537 Segment Code A user-defined name for the segment. Example: mysegment-003 Segment ID The segment ID. Example: 12693755 Value A numeric value that you assign to a segment. Example: 0 Action - Remove User From Segment Parameters Parameter Description AAID Android Advertising Identifier. The mobile device ID for Android devices. Example: AEBE52E7-03EE-455A-B3C4-E57283966239 Xandr/AppNexus User ID The User ID returned by the cookie match endpoint. Example: 12345678900987654321 IDFA Identifier for Advertisers. The mobile device ID for iOS devices. Example: 6D92078A-8246-4BA4-AE5B-76104861E7DC MD5 UDID The MD5 hashed value of the User ID. Example: 4a8a2b374f463b7aedbb44a066363b81 Open UDID Deprecated, do not use. SH1 UDID The SHA1 hashed value of the User ID. Example: F12877BFFD9C07E7224C9A6EFB7A709F4E29FDEA SHA1 MAC Deprecated, do not use. Tealium Visitor ID Deprecated, do not use. Segment ID The segment ID. Example: 12693755 Segment Code A user-defined name for the segment. Example: mysegment-003 Member ID The ID of the member that owns this segment or has been shared the segment by data provider Tealium. Example: 9537 Testing and Validation Batching and Rate Limits This connector leverages batch actions so that Tealium can manage high-volume data transfers to the vendor. Data queues in batched actions to be sent when the first one of the following three (3) thresholds is met: 500 records 10 minutes Greater than (>) 1MB The batching behavior described in the previous section is defined at the Action level. This means that for a given account and profile, each individual action is batched. If a profile contains multiple actions, Tealium individually batches each unique action when evaluating batch behavior. Frequently Asked Questions What are some example use cases that this integration supports? Search or time-sensitive retargeting in RTB As a buyer or DMP, this service is useful if you would like to mimic search retargeting capabilities. As a user enters search keywords, you receive a server-side signal that triggers a server-side association to the segments. The user can then see ads that are relevant to their search, which enables you to capitalize on the immediate relevancy of the content for the user. Page performance sensitive targeting Use this service if you want to avoid page load strain, but still want to be able to conduct retargeting without increasing the pixels present on the page. Alternative real-time audience targeting The Instant Audience Service can also be used for transactional retargeting, in which user scores are computed based on offline data or modeling. This only requires an additional trigger to have the user added to a segment that you wish to buy against in real-time. A concrete example is, based on Clickstream data, a buyer computes a score for a user that has browsed three (3) products in the kitchen category of its site and pushes a segment value to based on this user score to immediately show them an ad for additional kitchen items. De-targeting users who have converted To use your budget as efficiently as possible. This enables you to quickly de-target users that have already converted. How often do User IDs expire? Expires UIDs on a rolling basis such that the user IDs that have not been seen for the longest period of time are removed from our database to make room for new user IDs. If you upload UIDs that are very old, you may have a high percentage of invalid user IDs in your status report. Tealium keeps your cookie mapping fresh by requesting new UIDs at the start of each session. How quickly are updates to segments activated by Xandr? Xandr sets its target Service Level Agreement (SLA) for adding users to segments with the Instant Audience Service to two (2) minutes. In order to adhere to a maximum of two (2) minutes activation time, the Instant Audience Service currently has some limits, which Tealium has incorporated into the batching functionality. For additional details, see the Batching and Rate Limits section above. Vendor Documentation Xandr Streaming Server-Side Segmentation Xandr Instant Audience Service API Help Xandr Add/Remove Users From Segment ... View more

This article describes how to set up the Clicktale tag in your iQ Tag Management (TiQ) account. In this guide: Table of Contents Placeholder How it Works Clicktale empowers brands to act on unique behavioral insights to turn user experiences into measurable advantages. For more information about Clicktale, a Contentsquare company, visit contentsquare.com. What to Expect from this Integration A working integration of iQ Tag Management with the Clicktale tag from the Tealium tag marketplace enables customers to seamlessly execute session replays associated with clickstream data in order to detect and minimize end customer friction associated with tagged web pages. Prerequisites Tealium iQ Tag Management AudienceStream EventStream (optional) Clicktale Clicktale real-time signals are available to all customers with access to the Data Export Signals Clicktale signals enable joint Tealium and Clicktale customers to identify real-time behaviors, trigger events, and activate on those signals through AudienceStream. Once a potential friction or fraud behavior is detected, these signals are automatically sent to both Clicktale and AudienceStream. From there, customers can build powerful behavior-based segments that can be used across their marketing and advertising ecosystem. The Clicktale Signals settings provide the following capture points associated with web page activity and can easily be enabled by toggling them to True: Friction Repeated Scrolling Identifies when a visitor scans the page quickly and scrolls repeatedly from top to bottom. Identifies a potentially poor user experience or a frustrated visitor. Constant Hovering Identifies when a visitor consistently hovers over the same element without clicking. This signal indicates a visitor’s intent or interest without clicking the element. Consecutive Clicking (Clickable Element) Identifies when a visitor repeatedly clicks the same (clickable) element without a response from the page. The customer does not click any other element between clicks. This signal indicates a potential issue with the element. Consecutive Clicking (Un-clickable Element) Identifies when a visitor repeatedly clicks the same (un-clickable) element without a response from the page. The customer does not click any other element between clicks. This signal indicates a potential design flaw. Rage Clicking Identifies when a customer repeatedly clicks the same element without a response from the page. This event triggers regardless of whether customers click other elements in between clicks. JavaScript Click Error Identifies each time a click triggers a JavaScript error. Fraud Excessive Pasting Triggers when thresholds are met that identify abnormal and potentially fraudulent pasting behavior within the same visitor session. There are three (3) levels of Fraud likelihood: low, medium, and high. Excessive Reload Triggers when thresholds are met that identify abnormal and potentially fraudulent reload behavior within the same visitor session. There are three (3) levels of Fraud likelihood: low, medium, and high Ad Blocking Ad Blocker Signal Identifies when or if certain files are blocked, which identifies that an ad-blocker is present. You can optionally use signals from your EventStream event specifications and your AudienceStream visitor attributes. Tag Configuration First, go to Tealium's tag marketplace and add the Clicktale Carmel tag (Learn more about how to add a tag). After adding the tag, configure the following settings in the Data Mappings section. Tag Tips Conversion fires when Order ID is set. In order to send your Clicktale Replay Link to UDH, you must: Contact your Clicktale representative to enable the generation of the replay link. Set the Send Replay Link configuration to True. The Contentsquare tag automatically detects the Tealium account and profile loading on the page and sends the replay link there. To send the replay link to a different account or profile, override the default values by mapping the desired account and profile to the tealium_account and tealium_profile destinations, respectively To pass Tealium Audiences and Badges to Clicktale: Contact your Clicktale representative to enable the receiving of this data. To send a Badge to Clicktale, navigate to the Badges tab in the mapping toolbox and enter the name by which the Badge will be identified in the Clicktale system. To send all Audiences to Clicktale, toggle the Send UDH Audiences toggle to True. Applying Load Rules Load Rules determine when and where to load an instance of this tag. The 'Load on All Pages' rule is the default load rule. To load this tag on a specific page, create a new load rule with the relevant conditions. Load this Tag on the page where you want to track the visitor's mouse movements. Data Mappings Mapping is the process of sending data from a data layer variable to the corresponding destination variable of the vendor tag. For instructions on how to map a variable to a tag destination, see Data Mappings. The available categories are: Standard Variable Description title Required. Identifies the tag instance. Clicktale Carmel is the default name. When using multiple tags by the same vendor, assign a unique name. partition Partition. The partition where data is sent. Map to this variable to dynamically configure the server partition value. project_guid Project GUID. Map to this variable to set the project guide field. send_replay_link Send Clicktale Replay Link Values are true or false. send_udh_audiences Send UDH Audiences. Values are true or false. tealium_account Tealium Account. tealium_profile Tealium Profile. E-Commerce Variable Description order_id Order ID. Overrides _corder . Required for transactions. order_total Order total. Overrides _ctotal . Required for transactions. order_shipping Shipping amount. Overrides _cship . order_tax Tax amount. Overrides _ctax . product_id Array List of Product IDs. Overrides _cprod . product_name Array List of Names. Overrides _cprodname . Required for transactions. product_sku Array List of SKUs. Overrides _csku . Required for transactions. product_category Array List of Categories. Overrides _ccat . product_quantity Array List of Quantities. Overrides _cquan . Required for transactions. product_unit_price Array List of Prices. Overrides _cprice . Required for transactions. Badges Variable Description title Badge Identifier. To send the mapped badge to Clicktale, enter the name by which the badge will be identified in Clicktale. Tealium automatically includes the badge title as a child property of a new object send_udh_data Your badge name will appear as mapped to send_udh_data . ... View more

This article describes how to get the most out of Tealium and Contentsquare by setting up the Contentsquare UX Analytics tag in your Tealium iQ Tag Management account and enabling the transmission of Tealium audiences and Visitor badges to Contentsquare. In this guide: Table of Contents Placeholder How it Works Contentsquare empowers brands to act on unique behavioral insights to turn user experiences into measurable advantages. Contentsquare daily transforms trillions of digital behaviors into intelligent visualizations and recommendations that can be used to grow revenue, increase loyalty, and fuel innovation. Users can access benchmarks and predictive scoring based on leading global data sets of digital behavior across geographies and industries. For more information, visit contentsquare.com. What to Expect From This Integration A working integration of iQ Tag Management with the Contentsquare tag from the Tealium tag marketplace enables customers to execute session replays associated with clickstream data in order to detect and minimize end customer friction associated with tagged web pages. Prerequisites Tealium iQ Tag Management AudienceStream EventStream (optional) Contentsquare Contentsquare Business Edition or higher Signals Contentsquare signals enable joint Tealium and Contentsquare customers to identify real-time behaviors, trigger events, and activate on those signals through AudienceStream. Once a potential friction or fraud behavior is detected, these signals are automatically sent to both Contentsquare and AudienceStream. From there, customers can build powerful behavior-based segments that can be used across their marketing and advertising ecosystem. The Contentsquare Signals settings provide the following capture points associated with web page activity and can easily be enabled by toggling them to True: Friction Repeated Scrolling Identifies when a visitor scans the page quickly and scrolls repeatedly from top to bottom. Identifies a potentially poor user experience or a frustrated visitor. Constant Hovering Identifies when a visitor consistently hovers over the same element without clicking. This signal indicates a visitor’s intent or interest without clicking the element. Consecutive Clicking (Clickable Element) Identifies when a visitor repeatedly clicks the same (clickable) element without a response from the page. The customer does not click any other element between clicks. This signal indicates a potential issue with the element. Consecutive Clicking (Un-clickable Element) Identifies when a visitor repeatedly clicks the same (un-clickable) element without a response from the page. The customer does not click any other element between clicks. This signal indicates a potential design flaw. Rage Clicking Identifies when a customer repeatedly clicks the same element without a response from the page. This event triggers regardless of whether customers click other elements in between clicks. JavaScript Click Error Identifies each time a click triggers a JavaScript error. Fraud Excessive Pasting Triggers when thresholds are met that identify abnormal and potentially fraudulent pasting behavior within the same visitor session. There are three (3) levels of Fraud likelihood: low, medium, and high. Excessive Reload Triggers when thresholds are met that identify abnormal and potentially fraudulent reload behavior within the same visitor session. There are three (3) levels of Fraud likelihood: low, medium, and high Ad Blocking Ad Blocker Signal Identifies when or if certain files are blocked, which identifies that an ad-blocker is present. You can optionally use signals from your EventStream event specifications and your AudienceStream visitor attributes. Tag Configuration First, go to the Tealium tag marketplace and add the Contentsquare tag (Learn more about how to add a tag). After adding the tag, go to the Data Mappings section to configure any additional mappings. Tag Tips Conversion fires when Order ID is set. In order to send your Contentsquare Replay Link to UDH, you must: Contact your Contentsquare representative to enable the generation of the replay link. Set the Send Replay Link configuration to True. The Contentsquare tag automatically detects the Tealium account and profile loading on the page and sends the replay link there. To send the replay link to a different account or profile, override the default values by mapping the desired account and profile to the tealium_account and tealium_profile destinations, respectively. To pass Tealium Audiences and Badges to Contentsquare: Contact your Contentsquare representative to enable the receiving of this data. To send a Badge to Contentsquare, navigate to the Badges tab in the mapping toolbox and enter the name by which the Badge will be identified in the Contentsquare system. To send all Audiences to Contentsquare, toggle the Send UDH Audiences toggle to True. Applying Load Rules Load Rules determine when and where to load an instance of this tag. The 'Load on All Pages' rule is the default load rule. To load this tag on a specific page, create a new load rule with the relevant conditions and load the Contentsquare tag on the page where you want to track the visitor's mouse movements. Data Mappings Mapping is the process of sending data from a data layer variable to the corresponding destination variable of the vendor tag. For instructions on how to map a variable to a tag destination, see Data Mappings. The available categories are: Standard Variable Description title Required. Identifies the tag instance. Contentsquare UX Analytics is the default name. When using multiple tags by the same vendor, assign a unique name. id_project The Project Tag ID specific to your project. Map to this variable to set the project guide field. base_url Base URL send_replay_link Send Contentsquare Replay Link Values are true or false. Also known as contensquare_replay_link . This variable and session replay capability is currently in development for Contentsquare tag and is expected to be released in H1 2020 send_udh_audiences Send Customer Data Hub (CDH) audiences. Values are true or false. tealium_account Tealium account. tealium_profile Tealium profile. E-Commerce Variable Description order_id Order ID. Overrides _corder . Required for transactions. order_total Order total. Overrides _ctotal . Required for transactions. order_shipping Shipping amount. Overrides _cship . order_tax Tax amount. Overrides _ctax . product_id Array List of Product IDs. Overrides _cprod . product_name Array List of Names. Overrides _cprodname . Required for transactions. product_sku Array List of SKUs. Overrides _csku . Required for transactions. product_category Array List of Categories. Overrides _ccat . product_quantity Array List of Quantities. Overrides _cquan . Required for transactions. product_unit_price Array List of Prices. Overrides _cprice . Required for transactions. Badges Variable Description title Badge Identifier. To send the mapped badge to Contentsquare, enter the name by which the badge will be identified in Contentsquare. Tealium automatically includes the badge title as a child property of a new object send_udh_data Your badge name will appear as mapped to send_udh_data . ... View more

This article describes how to use the HTTP API - Flattened data source to create an HTTP endpoint to collect real-time event data with support for flattening complex objects. In this article: Table of Contents Placeholder How It Works A Webhook API sends outgoing requests to an endpoint that you specify. These requests inform Tealium EventStream and AudienceStream about customer activity from your external systems. When you add a webhook data source, a unique endpoint is generated. This endpoint is used to configure a webhook in your external system. Once configured, you can create subscriptions based on topics and receive related push notifications to automate use cases, stay informed, and increase productivity. The HTTP API - Flattened data source is a generic data source that can conditionally parse incoming request bodies. This data source offers an HTTP endpoint to collect real-time event data with support for flattening complex objects. The endpoint is flexible and can be implemented as a tracking pixel in a web page or as a JSON API in your custom application. This data source is similar to the HTTP API data source, but with additional support for complex objects. Events sent using HTTP POST with a complex JSON object will be flattened as follows: Event keys are created by lowercasing and connecting key paths to a prefix. For example, a value of true located at alpha.beta  displays as "alpha_beta":true . Numbers, booleans, and strings inside of an array are preserved. Objects and arrays inside of an array are stringified. Use this data source type when you need to send data in real time and do not have the ability to modify the request to meet format requirements for the standard Tealium Collect endpoint. Requirements Tealium EventStream or Tealium AudienceStream Supported Parameters The following default parameters are supported in each request: Parameter Description tealium_event Optional The name of the event. tealium_trace_id Optional For use with Trace. tealium_visitor_id Optional For use with AudienceStream Setup The following sections provide guidance on how to add the HTTP API - Flattened data source and create a webhook. Add the Data Source The HTTP API - Flattened data source supports both the GET and POST methods using the following endpoint: https://collect.tealiumiq.com/integration/event/ACCOUNT/PROFILE/DATA_SOURCE_KEY Add the HTTP API - Flattened data source before proceeding, then copy the generated endpoint for use in an external system. Related: How to Add a Data Source Examples The following sections provide examples of input code and the resulting (flattened) output for complex objects. Complex Object Before Flattening { "boolean": true, "number": 12.34, "string": "value", "array_of_strings": ["first", "second"], "array_of_arrays": [ [1, 2], [3, 4] ], "array_of_objects": [{ "ordinal": "first" }, { "ordinal": "second" }], "object": { "child_boolean": true, "child_number": 12.34, "child_string": "value", "child_array_of_strings": ["first", "second"], "child_array_of_arrays": [ [1, 2], [3, 4] ], "child_object": { "gchild_boolean": true, "gchild_number": 12.34, "gchild_string": "value", "gchild_array_of_strings": ["first", "second"], "gchild_array_of_arrays": [ [1, 2], [3, 4] ] } } } After Flattening { "boolean": true, "number": 12.34, "string": "value", "array_of_strings": ["first", "second"], "array_of_arrays": ["[1,2]", "[3,4]"], "array_of_objects": ["{\"ordinal\":\"first\"}", "{\"ordinal\":\"second\"}"], "object_child_boolean": true, "object_child_number": 12.34, "object_child_string": "value", "object_child_array_of_strings": ["first", "second"], "object_child_array_of_arrays": ["[1,2]", "[3,4]"], "object_child_object_gchild_boolean": true, "object_child_object_gchild_number": 12.34, "object_child_object_gchild_string": "value", "object_child_object_gchild_array_of_strings": ["first", "second"], "object_child_object_gchild_array_of_arrays": ["[1,2]", "[3,4]"] } JSON Object Before Flattening A JSON object is treated as a single event by default. { "events": [ { "id": "1", "name": "Event A" }, { "id": "2", "name": "Event B" }, { "id": "3", "name": "Event C" } ] } After Flattening Unless the parser is overwritten by custom logic used to parse out batched events, the JSON object is transformed into a single event with stringified JSON array values. { "events": [ "{\"id\":\"1\",\"name\":\"Event A\"}", "{\"id\":\"2\",\"name\":\"Event B\"}", "{\"id\":\"3\",\"name\":\"Event C\"}" ] }   ... View more

To improve application security, the ability to use the target environments feature of Web Companion is now controlled by a setting in the publish settings, which now defaults to off for all accounts. Learn more about what was updated, how it works, and how to use it. Use of this tool allows the system to set a cookie with any arbitrary value which could expose your system to code injections. This feature is offered as a convenience for those who cannot use the Google Chrome browser. If you can use Chrome, Tealium recommends using the Tealium Tools Environment Switcher  as a best practice. About Target Environments If you're not familiar, "target environments" refers to the feature of Web Companion that allows you to load a different version of your iQ configuration on a page. This feature is a convenience for users that don't have access to change the underlying code of the page and want to test a different configuration. To use, you simply click the environment that you want to load and Web Companion reloads the page with that version of the Universal Tag (utag.js). What's New To improve application security, the ability to use this feature is now controlled in the publish settings of your account. By default, this setting is set to off for all accounts upon release of this change. When you use Web Companion with this setting turned off, it looks like this: Enable Web Companion Target Environments To use target environments in Web Companion, you must enable the feature in the publish settings and publish the changes. This change only impacts Web Companion and has no effect on Tealium Tools. To enable target environments for Web Companion: Log in to iQ Tag Management. Click Save/Publish in the upper right corner. The Save/Publish dialog displays. Click Configure Publish Settings in the upper right corner. The Publish Configuration dialog displays. From the General Publishing tab, scroll down to the Implementation section. Next to Web Companion, click On. Click Save and continue to publish. Additional Information Publish Configuration Settings Web Companion Methods to Switch Publish Environment ... View more

This article describes how to get the most out of Tealium and Leanplum. In this article: Table of Contents Placeholder How it Works Leanplum helps forward-looking brands meet the real-time needs of their customers by transforming data into an understanding of user needs and wants. By optimizing engagement campaigns and using multiple communication channels, the Leanplum platform delivers a timely, tested, and relevant unified experience to build customer loyalty and fuel business growth. See the Tealium + Leanplum Technology Partnership Overview for more information. Server-Side Integration The following table lists descriptions and prerequisites for the server-side Leanplum Integration types and provides links to detailed setup documentation. Integration Type What to Expect from this Integration Product Requirements Setup Guides Leanplum Connector Leverage the Leanplum Connector to pass user attribute data from Tealium to Leanplum and trigger real-time messages. Tealium EventStream and/or AudienceStream Leanplum Leanplum account Leanplum Connector Setup Guide Specifying Endpoint and API Versions When configuring the Leanplum connector, you must specify which endpoint and API version is used for each action. API Version Leanplum API version is 1.0.6 for all actions. Available Endpoints Track User Attributes (setUserAttributes API) Track Events (track API) Send Message (sendMessage API) Additional Resources Leanplum Tealium and Leanplum Partner Brief ... View more

The following product features, enhancements, and fixes were released in June, July, and August of 2020. Tags New/Cool Stuff Updated Adobe Visitor Service to Version 5.0. Updated the Adobe Experience Cloud ID Service to support Adobe library, version 5.0.1 Updated the AT Internet SmartTag to support AV insights and version 5.20.0 of the AT Internet library. Fixes Corrected collection domain issues impacting the AT Internet SmartTag. Connectors New/Cool Stuff New marketplace connector: Swrve App Events (Learn more) New Beta Experiments connector: Google Ads Conversions (Learn more) New data source: Tealium Collect for Google Tag Manager. (Learn more) Updated the Google Adwords Customer Match connector to support email address, phone number, and address information. Updated the Klaviyo connector API to support version 2.0. Updated the Google DCM Floodlight connector to validate custom variable name and to remove invalid names from the outgoing requests. (Learn more) Updated the Facebook Conversions, Facebook Offline Conversions, and Facebook App Events connectors to support Facebook's Limited Data Use feature for CCPA compliance. (Learn more) Updated the Beta Experiments version of the Flashtalking User Segments connector to add pagination and increase timeout to 10,000 milliseconds (ms). (Learn more) Updated the Beta Experiments version of the Apsis connector to add the ability to send real-time API requests from AudienceStream using the Apsis bulk API. (Learn more) Fixes Corrected issue with batch actions for the Facebook Audiences beta connectors. Corrected an issue with the Braze connector that caused the User Delete action to fail. (Learn more) iQ Tag Management New/Cool Stuff The ability to use the target environments feature of Web Companion is now controlled by a setting in the publish settings, which defaults to off for all accounts. (Learn more) When using the extension search function, you can now filter extensions by type. When searching for a tag, you can now filter tags by scope or category. With the Load Order experiment feature enabled, you can now edit tag-scoped extensions in the Extensions view. With the Load Order experiment feature enabled, you can now sort extensions by load order, title, or UID. In the accordion view for tags, extensions, and load rules, the headers are now fixed and always visible when you scroll up or down. Fixes Corrected issue causing the help documents link on the Display Rule tab in the CCPA banner with pop-up modal to not load properly. Corrected issue where adding and removing tags from tag-scoped extensions in the Load Order view did not prompt user to apply changes. The interface is now updated so that the "Scroll to Top" button displays on all tabs in the accordion view. Corrected issue with the Web Companion tool that prevented users from adding variables to the data layer, load rules, and extensions. Corrected issue causing a user with appropriate permissions to not be able to generate Data Bridge keys for the View-Through extension. Customer Data Hub New/Cool Stuff Introduced the Tealium Predict Machine Learning product. (Learn more) Updated server-side permissions to allow admins to filter users by permission, perform a keyword search on user profiles, and update profile level user permissions in bulk from the Manage Users screen. (Learn more) The server-side account/profile switcher now displays accounts and profiles in alphabetical order in the drop-down list. New data source: HTTP API - Flattened (Learn more) Fixes Corrected an array of strings mapping issue that occurred when an enrichment was applied to remove all entries. Corrected an issue with the Scheduled Jobs launcher to ensure that it continues to be triggered even if the last expected schedule date did not occur. Corrected an issue where previewing the product_view specification caused the Live Events interface to freeze. Corrected File Import column label fields to not allow tabs or spaces in the field name. Corrected an issue that caused the Add Attribute dialog not to close as expected when adding a custom attribute as an enrichment. Updated the connectors screen to display additional meta-data: Action ID and Consent Categories. Installations New/Cool Stuff AppsFlyer 1.0.0 Updated remote commands. Firebase (iOS) 1.1.0 Added support for e-commerce items array. Firebase (Android) 1.1.0 Added support for e-commerce items array. Swift 2.0.0 and Tealium Kotlin 0.1.0 (Beta) Apps with Tealium for Mobile can now take advantage of the Consent Manager module to stay compliant with the California Consumer Protection Act (CCPA). Apps with Tealium for Mobile can now leverage client-side enrichment of event data using JSON stored on the Tealium Hosted Data Layer in their mobile apps. QR Code Debugging for mobile implementations. Enabled single track event for mobile apps (vs. trackView and trackEvent methods) to improve developer experience and make it easier to use Tealium SDKs. In the latest mobile SDKs, expiry options for your data layer variables makes Tealium SDKs more configurable for complex use cases. Native session counting logic in the native SDKs removes the reliance on the webview to count. To use, the user must first update their mobile.html template. In both Kotlin and Swift, a single track call is now 2.5X faster than previous versions of their respective library. Fixes Android 5.7.2 Added Tealium.Config API setOverrideCollectDispatchProfile to override profile for Collect module. ... View more

This document describes optional review steps and how to initiate the first training for your model: In this document: Table of Contents Placeholder Review your Model Before Publish (Optional) Use the following sections as a guide to review your model and start training. Revising your model using these steps is optional. If no changes are needed, skip to Save and Publish to Start Training. Add Labels (Optional) Add a label: To add a label to improve search results, click on a model to expand the details. Click the Add Label drop-down list and use the checkboxes to select one or more labels. Click Apply. Edit the Model Name (Optional) View and edit the your model name: Click on a model to expand the details. Click Edit. The Edit Model dialog displays. Edit the model name and descriptive notes. Click Save. View or Edit your Target Attribute (Optional) To view or edit your target attribute: Click on a model to expand the details. Click the drop-down menu to the right of the Edit button and select View Target Attribute. The details for your target attribute display. Click the pencil icon to modify the attribute. The Edit Attribute dialog displays. Make the desired changes and then click Save. View or Edit your Output Attribute (Optional) To view or edit the output attribute for your model: Click on a model to expand the details. Click the drop-down menu to the right of the Edit button and select View Output Attribute. The details for your output attribute display. Click the pencil icon to modify the attribute. The Edit Attribute dialog displays. Make the desired changes and then click Save. Save and Publish to Start Training Your model is currently in the Requires Publish stage. Use the following steps to start training: Save and Publish your model. Tealium recommends using the Save As option and selecting a meaningful title and description. Before saving and publishing, your model has been saved, but not published. If no errors are encountered, training begins automatically upon publish. Click OK. If no errors are encountered, your model is now in training. Your model is now Version 1 with a status of In Training. Training is a one-time event and each retraining results in a new version number. For example, when you retrain Version 1, the resulting version is Version 2. Your model is now in training. Check to ensure the model status now displays In Training. Once the training date range has lapsed, the model status is updated to Requires Publish to Deploy. Next Steps For next steps, go to Evaluating the Trained Version. ... View more

This document describes how to use optional advanced configuration options to select a training date range and select attributes to exclude, if desired. In this document: Table of Contents Placeholder Configure Advanced Options Use the following sections as a guide to configure advanced options for your model. Select the Training Date Range Select the training date range you want to use: Under Choose Training Date Range, select Use all available data or Custom. Use all available data is the default option and is recommended. If you select Custom, use the calendar drop-down menu s to select a date range. Selecting a prediction timeframe determines the date range for the data you want to train on. The default value for the second date range is today's date. The date you select must be in the past and cannot be greater than today's date. You can select dates as far back as you want from the point when your profile began collecting data. Choose Attributes to Exclude (Optional) Predict evaluates all attributes and selects the most predictive attributes by default. To improve how well your model performs on data after it is retrained, you can optionally choose to exclude one or more attributes from your model. Use the following steps to choose additional attributes to exclude: Under Choose Attributes to exclude, select Use all available attributes or Select attributes to exclude. Use all available attributes is the default option and is recommended. If you selected Select attributes to exclude, use the drop-down list to select one or more attributes to exclude from your model results. To exclude more attributes, click the plus sign (+) as many times as you need and select another attribute from the drop-down list for each exclusion. To remove an attribute you previously selected, click the minus (-) sign to the right of that attribute. Click Finish. The first time you add a model, you are prompted to accept the terms of use in order to proceed. Read the agreement and, if you accept, click I accept the terms of use. Your new model now displays as Version 1 with a status of Requires Publish. Model versions are automatically numbered consecutively, in the order they are created. Next Steps To continue, go to Review and Start Training. ... View more

This document describes how to add a model, select your target attributes and prediction timeframe, and then name your model and attribute for future use. In this document: Table of Contents Placeholder Get Started by Adding a Model Use the following sections as a guide to add a model and get started. Add a Model and Select your Target Attribute Add a model and select your target attribute: In the left sidebar, click Predict. The Predict Overview displays. Click + Add Model. The Add Model dialog displays. In the What would you like to predict? field, select a target attribute from the drop-down list. This is the AudienceStream attribute you will use to define your model and represent the user action being predicted. You can use the plain language indicators and health status that displays to the right of each attribute to help you decide. Select a Prediction Timeframe Select a prediction timeframe: In the What is your prediction timeframe? field, enter a number for the number of days, weeks, or months you want to predict. Select days, weeks, or months from the drop-down list. Name your Model and Output Attribute Name your model and output attribute: In the Name your Model field, enter a descriptive name for this model. Use a meaningful name, for example: Likelihood to Purchase in Next 1 Days. In the Output Attribute Name field, accept the default name based on your model name or enter your own descriptive name for this output attribute. In the optional Notes field, enter any descriptive notes that will help users understand what this model is intended to predict. Click Next to proceed to the next screen, where you will choose the data to act on. Next Steps To continue, go to Advanced Configuration Options. ... View more

This document describes how to delete a model. You cannot delete a version of a model, only an entire model. Use the following steps to delete a model: Go to the Model Explorer screen. Click the model you want to delete to expand the view. Click the menu to the right of the Edit button and select Delete. Click Yes to verify that you want to delete the model. The model is deleted and no longer available for configuration or training. ... View more

This document describes how to deploy or undeploy one or more versions of a trained model. In this article: Table of Contents Placeholder Final Steps to Deployment You are now ready to deploy your trained model. Use the steps in the following sections as a guideline to deploy one or more versions of a trained model and you are on your way. Select a Trained Model and Deploy Select and Deploy a Trained model: Click on the trained model and version you want to deploy to expand the details. From the Status column in the summary, click the Trained status. Click Deploy. Click Deploy again to confirm you want to deploy this version of this model. Your model is now Version 2 with a status of Requires Publish to Deploy. Save and Publish. Your model is now Version 2 with a status of Currently Deployed. Undeploy a Deployed Model To undeploy a deployed model: Click on the deployed model and version you want to undeploy to expand the details. From the Status column in the summary, click the Currently Deployedstatus. The training details for the version display. Click Undeploy. Your model is now Version 2 with a status of Requires Publish to Undeploy. Save and Publish your changes. After you save and publish, this status of this version of your model returns to Trained. Next Steps Repeat any steps in this documentation to add and deploy new models. ... View more

This document describes how to retrain a model after evaluating the model and determining changes are required to improve predictions. In this document: Table of Contents Placeholder Determine Needed Changes and Prepare for Retraining Use the following sections as a guide to prepare your model for retraining. Edit a Trained Model To review and edit a trained model: Click on a trained model to expand the details. Click the drop-down menu to the right of the Edit button and select View Target Attribute or View Output Attribute. See Review and Start Training for detailed steps. Review the attributes and click the pencil icon to adjust as needed. Click Save. Save and Publish your changes Retrain the Model To retrain your model: Click on the trained model to expand the details. From the Status column in the summary, click the Trained status. Training details for Version 1 display. Click Retrain Model. Adjust Advanced Options if needed, such as: Training Date Range Attributes to Include Attributes to Exclude Click Finish. Click Retrain Model again to verify that you want to proceed with retraining. Your model is now Version 2 with a status of Requires Publish. Save and Publish your changes. Your model is now Version 2 with a status of In Training. View Retrained Results for Deployment Readiness Once your new version is trained, see Evaluating the Trained Version to view the results of retraining. Continue to adjust if needed. When satisfied, proceed to deploy your model. Next Steps Once you are satisfied with your results and ready to deploy, go to Deploying a Model. ... View more

This document provides detailed descriptions of model strength quality scores. In this document: Table of Contents Placeholder Understanding the Quality of Your Model The quality of any machine learning model created using Tealium Predict or any other Machine Learning tool will vary depending on several factors, including (but not limited to) the following: The attributes which comprise the dataset and how complete of a picture the combined attributes provide/ The daily volume of visitors and visits in the dataset. Higher volume typically means there is more data available for the model to learn on. The Training Data Range selected for the model. Training a model for a longer time period generally equates to more data available for the model to learn on. In order to understand whether a given model is of high enough quality for use in the real world, machine learning experts typically use a combination of interrelated metrics. The specific combination varies depending on the type of model being evaluated. Tealium Predict enables non-experts to create models, evaluate the quality of the model, and take real-world actions in the most streamlined manner possible, while retaining with enough transparency for an expert to see the typical metrics they expect. The following sections provides explanations of the metrics and ratings available with Tealium Predict to help you understand the quality of your models. For a more comprehensive explanation of other scoring reports, such as the F1 Score, Confusion Matrix,  the ROC/AUC Curve, and Probability Distribution, see Evaluating Success. Accuracy In the context of Tealium Predict, accuracy is simply the ratio of correct predictions to the total number of predictions. Accuracy alone can give you a false sense of security and therefore cannot adequately judge the quality of a machine learning model. As an example, assume that you have red and green apples and 99% of the apples are green. In this case, our model could easily train to obtain a 99% accuracy score by simply predicting that every single apple is green, since that would be correct 99% of the time. This model, with 99% accuracy, would not be a good predictor of which apples are red. Model Strength Ratings The model strength ratings used in Tealium Predict provide an easy-to-understand rating of the quality (strength) of each version of each trained model. The rating system is comprised of four categorical labels. These labels are based on F1 Score, which is the typical metric used to evaluate the quality of a propensity model. F1 Score values are categorized using the following scale: Poor - F1 score is less than or equal to 0.50 Fair - F1 score is at greater than 0.50 but less than 0.60 Good - F1 score is greater than 0.60 but less than 0.80 Excellent - F1 score is greater than 0.80 The quality of any model is a relative judgment, not an absolute fact. Different teams have different needs and goals for their models, as well as different levels of sophistication in their modeling and testing abilities and varying quality in their input datasets. For these reasons, model strength ratings are not regarded as absolute. The intention is to use the ratings as a general guideline for quality. There are two types of strength ratings in Predict: static ratings for each trained version, and ongoing dynamic ratings for each deployed model. Strength Ratings for Trained Versions The strength rating for each trained version of each model is intended to provide an easy-to-understand rating of the quality (strength) of the training and the model which resulted from it. Models not yet deployed are not yet assigned a Strength Score. Training is a one-time event. Each retraining is a new, separate event, which makes this type of strength rating static and specific to each version. The rating for a version does not change over time. The strength rating is visible next to each version on the Model Explorer page, in the Training Details panel, and in the Tiles view on the Overview page (for the latest trained version). Strength Ratings for Deployed Models All machine learning models naturally degrade in quality over time, just as the real world continually changes. Models eventually stagnate and degrade in their ability to make accurate predictions about the changing environment. Models must therefore be retrained periodically to ensure that the model is based on the freshest information available. Live Model Performance Scores For deployed models, Tealium Predict recalculates the ongoing F1 score daily using the most recent time window available. This window is defined in the Prediction Timeframe, which is the number of days specified in the model as "in the next x days". In order for this nightly recalculation to begin, the model must be deployed for the initial Prediction Timeframe (30 days in this example) so that actual true/false results are known and can be used in the calculation. The calculation window then moves forward one day, every day. The deployed live performance score allows you to understand the ongoing quality of your model and know when it has degraded, which will inevitably happen over time. ... View more

Visitor data is not purged by default. For information about purging specific visitor data, contact your account representative. Visitor Data Usage Model training is not a one-time task. For that reason, visitor data is not purged. There will always be a need for new versions of visitor data to be trained and the data must therefore be available to retain. After a successful model is deployed, the model degrades over time and needs to be refreshed with current visitor data. Data Storage and Access Controls All data related to Tealium Predict remains within the Tealium system and infrastructure, and is subject to the same Tealium security and privacy protocols. For more information, see Data Storage and Access Controls. ... View more

This document describes General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA) compliance as it relates to the Tealium Predict Machine Learning product. AudienceStream Compliance Predict is part of AudienceStream. With AudienceStream, your data is fully protected and is both GDPR and CCPA compliant, including advanced considerations such as opting in or out of automatic profiling. For detailed information about Tealium Consent Management compliance and Consent Management tools, see Consent Management. ... View more

This document describes how Predict data is collected and used. The Data Collection Stage Predict Models run at the end of each visit for every visitor at the normal time, which is during the end of the session aggregation stage. This is the stage at which data used by Predict is collected. At this time, the models produce a score -- categorized as per Visit vs. per Visitor -- that assigns a prediction percentage value between zero (0) and one (1). For additional information, see Data Storage and Access Controls. ... View more

This document describes where your data is stored during the data collection period and beyond, and the access controls used to protect that data. In this document: Table of Contents Placeholder Data Storage Predict data is stored using S3 Server-Side Encryption (SSE) and strict Identity and Access Management (IAM) policies to ensure that only necessary internal services can access the data. In the Machine Learning industry in general, the data produced by a model typically resides in a newly-created silo. The data remains siloed, even after the model is successfully integrated into an your systems and applications. For this reason, there is no guarantee that the data output by the model is fully integrated. Siloed data makes activation and the ability to achieve real business value difficult. The Tealium Predict product is implemented on each of the Tealium regional infrastructures to ensure that none of your data changes region when using the product. For example, if your general Tealium account uses an Australia-based infrastructure, then your usage of Predict occurs on that same infrastructure to ensure security. Data Usage and Sharing Data usage is consistent with your contracted terms for AudienceStream. Your data is only used for Tealium features. Data is not shared or sold, does not cross regions, and is protected by Tealium's general security and privacy protocols. GDPR and CCPA Compliance AudienceStream and your data is fully protected and compliant with the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA). Length of Time Data is Stored Using Predict, you can set the retention and storage period for related data when signing up for Predict. Contact your account manager if you have concerns about data retention periods. Data Access General usage of the Tealium Predict product does not require a third party or entity accessing or viewing your data. When your Predict packaging and services include assistance with data readiness, the Tealium internal data science team does have access to your models and training datasets to help ensure the quality of your machine learning models. Additional Information CCPA and GDPR Compliance Data Collected and Used by Predict ... View more

Visitor Stitching does not impact the Predict modeling results. Visitors vs. Visits Predict Machine Learning models train on visitor profiles, not visits. The actual and predicted values that display in the Model Training Details Confusion Matrix refer to the number of of visitors. Visitor Data Filtered When preparing for training, data is filtered by visitor_id . The model only trains on this (newest) stitched visitor_id and ignores the older (pre-stitched) ID and thus is not a problem for accounts and profiles with visitor stitching enabled. ... View more

This document describes machine learning technology concepts, goals, audiences, and technological advances. In this document: Table of Contents Placeholder Machine Learning Technology Machine learning is a subfield of artificial intelligence that focuses on enabling machines to learn without human guidance by recognizing patterns. Machine learning uses a set of predetermined rules to remember the patterns, analyze output, and create a model to explain the patterns and guide future behavior. In cases where you know what data you want, machine learning accelerates the path to acquiring the desired data. In cases where you do not know exactly what you want or need to identify a pattern, machine learning can find a pattern and reveal results that you can use to move forward with acquiring the data you need. For information about what machine learning is and what it is not, see Machine Learning vs. Artificial Intelligence. Goals Machine learning technology enables you to learn more about your users and, as a result, provide them more personalized, higher quality experiences while improving the efficiency of your marketing and advertising efforts. Audiences that Consume Machine Learning Technology Data scientists and developers who have a high level of knowledge about machine learning and actually work on machine learning projects are the primary consumers of machine learning tools and technologies. Everyone else, including marketers and business users, have a general understanding of the potential benefits of machine learning but lack the knowledge of how to start and implement a machine learning  project. Predict can be implemented and managed by members of this "everyone else" group. One does not have to be a Data Scientist or have a background in Data Science to get started and add immediate value to a business. Business Examples Machine learning models are commonly used by leading businesses to make predictions about the future behavior of their customers, such as estimating future purchase amounts. The most common business example used today is a recommendation engine, such as those built and used by Amazon, Netflix, AirBnb, and other large businesses. Advances Machine learning technology as a field has advanced to the point that it is being used successfully by some of the largest and most sophisticated technology companies. The public is generally aware of the fact that machine learning has large potential benefits for businesses and that it is here to stay. ... View more

This document provides a generic overview of the differences between Machine Learning and Artificial Intelligence. In this document: Table of Contents Placeholder Artificial Intelligence and Machine Learning Differences Artificial Intelligence (AI) and Machine Learning (ML) are correlated elements of computer science. Each of the two technologies are some of the highest trending in the industry today and used for creating intelligent software. Artificial Intelligence is the larger concept that is used create intelligent machines that can simulate human thinking capability and behavior. Machine Learning is an application or subset of AI that allows machines to learn from available data without being explicitly programmed to do so. About Artificial Intelligence Artificial intelligence is a field of computer science that enables a computer system to mimic or simulate human intelligence. The two words "Artificial" and "Intelligence" translate to "a human-made thinking power." An AI system does not require programming in advance. It uses algorithms that work with the AI intelligence already present in the system. This involves machine learning algorithms, such as "reinforcement learning" and "deep learning" neural networks. Some examples of AI implementations in used today include: Siri, Google AlphaGo, and various chess playing implementations. About Machine Learning Machine learning is a subfield of AI that enables machines to learn from historical data or experiences within a specific domain without being explicitly programmed. ML is reliant on extracting knowledge from the data. ML models are composed of complex algorithms. Through trial and error, the algorithms are refined to best explain patterns and best predict future outcomes and user behaviors. ML focuses on enabling machines or software to learn without human guidance, similar to how humans learn by recognizing patterns in the world and remembering the patterns through learned rules. Machines analyze information provided and create a model that explains the patterns. The information gathered can then guide future behavior. The primary benefit of ML is automation of effort. For example, in cases where you already know what you want to know, ML accelerates how quickly your goal is can be achieved. In cases where you do not know what you want to know or cannot identify a useful pattern in a dataset, ML can find a useful pattern and bring it the forefront for investigation. Some examples of ML implementations in use today include online recommendation systems, such as Google search algorithms, email spam filters, and Facebook automatic friend tagging suggestions. Additional Information Machine Learning Concepts and Technology ... View more

This document provides detailed information about model scoring techniques and formulas used to assign scores and rating to deployed models in the Tealium Predict product. In this document: Table of Contents Placeholder Target Attribute Health Ratings A target attribute is an AudienceStream attribute that defines or signals the visitor behavior that you seek to predict with any Predict model. The target attribute must be either a Boolean/Flag or a Badge type attribute and be Visit or Visitor-scoped. Healthy vs. Unhealthy Attributes When you create a model in Predict, potential target attributes from your AudienceStream dataset display. To the right of each attribute, a health rating of "Healthy" or "Unhealthy" displays. This health rating simplifies model creation by clarifying which of your flags and badges are ready or "healthy" and can be used to create models. A rating of "Unhealthy" does not necessarily mean that the attribute is problematic in other contexts. It simply means that this attribute is currently deemed insufficient for successful training of a Predict model. Machine learning technology in general requires a relatively high volume of data in order to succeed and Machine Learning models provide better results when trained on a large amount of data. Predict uses the following two factors to define Healthy vs. Unhealthy target attributes: The volume of data for the attribute The distribution of that volume between true and false values. Both the true and false groups must be above a minimum threshold. For example, for the dates that span the Training Date Range, the median daily counts of True and False visitors must be greater than or equal to 200. This threshold is intentionally set as low as possible to provide the most options possible for target attributes. A model with an Unhealthy target attribute will likely fail in training due to insufficient data for the model to learn on. If the target attribute you want to use is unhealthy, try one of the following common solutions: Wait for more data to accumulate. The problem often solves itself over a longer time period. Identify ways to drive additional traffic to the AudienceStream data source. Add additional data sources to your AudienceStream profile so that the volume of daily data increases for this target. Strength Scores (F1 Scores) An F1 Score is the typical metric used by experts to evaluate the quality of the type of Machine Learning models used by Predict. The F1 Score strikes a balance between two metrics: Precision and Recall. To calculate the F1 Score, Precision and Recall values are input into the following formula: F1 Score = 2 * ( (Precision * Recall) / (Precision + Recall) ) High Precision Model As an example, assume you have two colors of apples, red and green and your model seeks to predict which apples are red. If your model has high Precision, this means that the model is usually correct when it predicts an apple is red. If the model is creating a list of apples which are supposedly red, high Precision means that this list is mostly accurate and that the apples on the list are actually red. High Recall Model Using the same example, if your model has high Recall (Sensitivity), the model will be able to identify most of the red apples. A model with high recall does a good job of creating a thorough list of the red apples. Precision vs. Recall Analogy Using the same example of red and green apples, the following list describes expected results based on high or low Precision or Recall. High Precision, low Recall = a short list of red apples that is fairly accurate. High Precision, high recall = a longer list of red apples that is fairly accurate Low Precision, low Recall = a short list of red apples that is fairly inaccurate. This list contains more green apples. Low Precision, high Recall = a long list of red apples that is fairly inaccurate. This list contains green apples. The ideal model clearly should have both high precision and high recall. The concept of potential trade-offs (between the volume of apples predicted to be red, and the accuracy of those predictions) is a recurring theme that impacts how machine learning models are used in the real world. The Confusion Matrix A Confusion Matrix is a key tool used to evaluate a trained model. During the training and testing process that runs automatically when you create or retrain a model, Predict attempts to "classify" the visitors during the Training Date Range into two groups: true and false. These two groups reflect whether a user actually did the behavior signalled by the Target Attribute of your model, such as made a purchase or signed up for your email list. The Confusion Matrix allows you to easily view the accuracy of these predictions by comparing the true or false prediction value with the true or false actual value. There are four possible scenarios, as described quadrants description below. This comparison is made possible by the fact that the model is training on historical data (the Training Date Range). Once your model is deployed, the scenario changes. If your deployed model makes a prediction for a particular visitor today and the prediction timeframe is "in the next 10 days", you will not know for up to 10 days whether the actual value ends up being true or false. Quadrants of the Confusion Matrix The four quadrants of the Confusion Matrix are: True Positive Correctly predicted true (predicted true and was actually true) True Negative Correctly predicted false (predicted false and was actually false) False Positive Incorrectly predicted true (predicted true but was actually false) False Negative Incorrectly predicted false (predicted false but was actually true) You can use the values of the quadrants to calculate the two constituent parts of F1 Score (Recall and Precision). Accuracy = (TP + TN) / (TP + FP + FN + TN) The accuracy is the number of correct predictions divided by the total number of predictions made. Precision Shows the proportion of all positive predictions that were positive. Recall Shows the proportion of positive predictions that were correct. The Confusion Matrix uses a threshold value of 0.5 to differentiate between predicted positive and predicted negative values. Formula Definition Reference The following list provides a descriptive reference of elements used in Predict modeling formulas referred to in the Confusion Matrix section and other portions of this document Visitor's Visit (Vn) The act of a Visitor visiting a website or the triggering of one or more data layer enriched events. Prediction Time Window (Wn) The Prediction Time Window starts at the end of each Visitor's visit, is measured in days, and is used to determine the Prediction Outcome. Prediction (Pn) The score generated by a Deployed Model. This score represents the likelihood that the Target Attribute Value will be set to True during the Visitor's next Visit (assuming the next visit occurs within the Prediction Time Window). This value is stored in the corresponding Prediction Attribute for the model. Prediction Attribute The numeric Visit scoped data-layer attribute that stores the Prediction value generated by a corresponding Deployed Model. The Prediction Attribute is created by default when a new model is created. Prediction Threshold (PT) The numeric threshold value selected to measure a Prediction value against the Target Attribute Value. For example, if the Prediction Threshold chosen is 0.5 and a Prediction value is set to 0.51, it is assumed that the Target Attribute Value will be set to True. Target Attribute The Flag or Badge attribute selected to represent the action to be predicted by the model. Target Attribute Value (AVn) The True or False value of the Target Attribute at the end of a visitor's visit. Prediction Outcome (O) The accuracy of the Prediction as determined by the Target Attribute Value, Prediction Threshold, and Prediction Time Window. If a Visitor returns within the Prediction Time Window, the Prediction Outcome is measured by the Target Attribute Value. If a visitor does not return within the chosen Prediction Time Window, the Target Attribute Value is ignored. Prediction Classification (PC) The value, True or False as a result of applying the Prediction Threshold to the Prediction. The ROC/AUC Curve In Tealium Predict, the ROC/AUC (under the curve) is a performance measurement reported for a trained model in the Model Explorer. In industry terms, the ROC is a true positive rate calculated as the number of true positives divided by the sum of the number of true positives and the number of false negatives. The ROC describes how well a model predicts the positive class when the actual outcome is positive. The true positive rate is also referred to as Sensitivity. The Receiver Operating Characteristics (ROC) curve and the area under this curve (referred to as AUC, for area under curve) are common tools in the machine learning community for evaluating the performance of a classification model. The ROC curve shows the trade-offs between different thresholds and consists of a plot of True Positive Rate (y-axis) against the False Positive Rate (x-axis). True Positive Rate = Sensitivity False Positive Rate = (1 - Specificity) Ideally, your will be able to distinguish between True and False classes. The model always predicts the correct answer. ROC Examples The Probability Distribution and ROC curve for a perfect model would look like the following: For the above ROC curve, AUC = 1. The entire graph area displays underneath and to the right of the red curve (boundary). For an extreme contrast, below is the Probability Distribution and ROC curve in scenarios where your model always predicts the wrong answer. Always labels True as False, and vice versa. For this ROC curve, AUC = 0. A poor scenario is defined as a model that is incapable of distinguishing between True and False classes. In this scenario, the Probability Distribution displays two large curves directly on top of each other. The ROC curve is a diagonal line; and AUC = 0.5. A realistic ROC curve, where 0.5 < AUC < 1.0 displays smaller values on the x-axis of the plot to indicate lower false positives and higher true negatives. Larger values display on the y-axis of the plot to indicate higher true positives and lower false negatives. When predicting a binary outcome, it is either a correct prediction (true positive) or not (false positive). Probability Distribution You can go to the Training Details panel for any version of any trained model to view a probability distribution of the predictions made by the model during training. The two colored curves of this chart represent the distributions of true and false predictions that the model made during training. Since the model training process uses historical data and you know whether each visitor actually performed the target behavior, it is possible to test the model by comparing the predictions for historical visitors versus the actual outcomes. The purpose of this comparison is to set aside a portion of the training dataset as the test subset. The probability distribution compares predictions against actual values for the visitors in the test subset. Visitors who were part of the True class (did perform the behavior) are displayed as part of the teal-colored curve and visitors who were part of the False class are part of the orange-colored curve. Ideal Probability Distribution The following list describes characteristics of an ideal probability distribution: There is clear separation between the True and False classes, as depicted by the teal and orange curves. This shows the model can easily and accurately classify visitors. Each class (curve) only covers one portion of the predicted value range. The False class us ideally focused in the lower range on the left and the True class is focused in the upper range on the right. Additional Information Data Readiness Deployed Model Health Scores ... View more

This document serves as a guideline of items to consider when creating audiences using your results from Tealium Predict. In this article: Table of Contents Placeholder Choosing Thresholds Once a model is deployed and making predictions, a common next step is to use your predictions to create one or more audiences. The prediction values in an AudienceStream output attribute for any model are decimal numbers in a defined range (0 - 1). The typical approach is to choose one or more thresholds or cutoff points to define which portion of that prediction range you want included in your audience. For example, if your model is predicting a likelihood to purchase in the next 3 days, you may want an audience of only the visitors who are most likely to purchase. To achieve this, you can create an audience using a rule that defines the threshold as 0.8 as an example. In this scenario, the audience will include only visitors with values greater than or equal to 0.8. There is no one objectively correct threshold value for all audiences, as different audiences serve different business goals and since there are usually substantial variations between models for different target behaviors or among different datasets. Sensitivity and Specificity To choose the best threshold, consider the potential trade-offs of choosing a threshold that is relatively high or low. This can be described as a trade-off between ending up with a larger audience that is less strict or a smaller audience that is laser-focused. In statistics terms, this is known as a trade-off between Sensitivity and Specificity. Sensitivity Sensitivity represents the True Positive Rate or how well the model correctly identifies all visitors who actually will purchase (using purchase as a the behavior your model is predicting). Specificity Specificity determines how well a model identifies false values. Specificity is the metric that evaluates a the ability of the model to predict true negatives of each available category. The True Negative Rate shows how well the model correctly identifies all visitors who actually will definitely not purchase (using purchase as a the behavior your model is predicting). ... View more