Estimate who is likely to take a future action, compare which of a defined set of offers is most relevant to each customer, or find customers who resemble a reference audience. Choose the approach that fits the outcome you want to drive.

No, mParticle’s predictive capabilities are designed for marketers. You define the conversion goal and the time frame, and mParticle handles the modeling. There is no pipeline to build and no model to maintain, which is what lets a marketing team run predictions without a data science queue in front of them.

Predictive attributes are machine-learning scores that live on the customer profile alongside behavior and demographics. You define the outcome, and mParticle analyzes thousands of behavioral signals to score which customers are statistically most likely to get there. Once generated, they behave like any other user attribute.

A new prediction can take up to 24 hours to calculate, and shows as calculating until values exist for every relevant customer. After that, predictions refresh automatically on a weekly schedule, so scores keep pace with behavior instead of aging out.

As a score and a percentile. The score is the likelihood of the action, from 0 to 100 percent. The percentile ranks each customer against everyone else scored. Both sit on the profile, and percentile is generally the better choice for audience building because it stays stable as the underlying population shifts.

Use predictive attributes in audience criteria or retrieve them through the Profile API to inform personalized experiences. Activate resulting audiences through supported destinations in your existing mParticle workflow.

Predictive Attributes are prediction results stored on customer profiles, such as a likelihood score, a relative ranking, or a recommended action. Predictive Audiences uses predictive signals to determine who qualifies. Combine them with other audience criteria to focus your campaigns.

Describe your goal. mParticle Agent identifies relevant customer data, recommends a prediction suited to that goal, and builds it for you. You can review and refine the work in conversation. Audience activation and destination configuration remain in your existing workflow.

Predictions refresh according to their configured schedule. Review refresh settings to understand when your prediction results are updated.

Predictions learn from customer data relevant to the outcome, including historical behavior and profile attributes. The data needed depends on the prediction type and goal. Enough meaningful examples of the outcome help the model learn useful patterns.