This article describes the Tealium Predict ML product and how it is used to create, train, and deploy machine learning models to make predictions about visitor behavior.
In this article:
Tealium Predict is a built-in machine learning technology product used with the Tealium AudienceStream CDP product that takes a complicated discipline (machine learning) and distills it down to a fully-managed feature. Coupled with AudienceStream, the product allows you to build and create more intelligent audiences and activate trustworthy machine learning insights across your entire tech stack.
Using Tealium Predict, you can create, optimize, and deploy data models that make meaningful predictions about your visitor behavior. Deployed models are managed by Tealium in real-time using a predictive output attribute that is made available to you after your model is trained and deployed. In just a few clicks, you can then create a model using the new output attribute, which is immediately available and actionable in AudienceStream.
Key benefits of Tealium Predict include the following:
A target attribute is a AudienceStream attribute that defines or signals the visitor behavior that you seek to predict with any Tealium Predict model. The target attribute must be either a Boolean/Flag or a Badge type attribute and be Visit or Visitor-scoped.
When you create a model using Tealium Predict, potential target attributes from your AudienceStream dataset display. To the right of each attribute, a rating of Ready or Not Ready displays to signify whether or not the attribute selected is ready for training. This rating simplifies model creation by clarifying which of your flags and badges are ready to be used to create models. A rating of Not Ready does not mean that the attribute is problematic in other contexts. It simply means that this attribute is currently deemed insufficient for successful training of a Tealium Predict model.
Machine learning technology in general requires a relatively high volume of data to succeed and machine learning models provide better results when trained on a large amount of data.
The following two factors to define target attributes that are Ready or Not Ready:
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 that uses a target attribute that is labeled Not Ready typically fails during the training process due to insufficient data for the model to learn on.
If the target attribute you want to use is labeled as Not Ready, try one of the following common solutions:
To learn more about machine learning technology, see Machine Learning Concepts and Technology.