Show Menu
TOPICS×

Smart Personas Overview

Smart Personas helps you classify unknown audiences into personas in real-time, using advanced data science techniques.
In a marketing context, a persona is an audience segment defined by visitors, users, or potential buyers, who share a specific set of traits, such as demographics, browsing habits, shopping history, etc.
Smart Personas models take this concept a step further, by using Audience Manager's machine learning capabilities to automatically classify unknown audiences into distinct personas. Audience Manager achieves this by calculating the propensity of your unknown audience for a set of known audiences.
When you create a Smart Personas model, the first step is choosing the baseline traits or segments that you want your target audience to be classified by. These traits or segments will define your personas.
During the evaluation phase, the model creates a new Smart Personas segment for each trait and segment that you defined as baseline. The next time Audience Manager sees a visitor from your target audience who is not classified for a persona (did not qualify for any of your baseline traits or segments), the Smart Personas model will run a prediction on which of the Smart Personas segments the visitor should belong to, and add them to that segment.
You can identify the auto-created Smart Personas segments in the Segments page. Each Smart Personas model has its own folder in the navigation tree, and you can see each model's segments by clicking the model folder.

Use Cases

To help you better understand how and when you should use Smart Personas, here are a few use cases that Audience Manager customers can solve by using this feature.

Use Case #1

As a marketer in an e-commerce company, I want to classify all my web and mobile visitors into various brand affinity categories, such as Apple products, Google products, HP products, etc., so that I can personalize their user experience.

Use Case #2

As a marketer in a media company, I want to classify all my unauthenticated web and mobile visitors by favorite genres, so that I can suggest to them personalized content across all channels.

Use Case #3

As an advertiser for financial services provider, I want to make sure I classify my audience based on their interest in mortgage loans, refinancing, student loans, etc., so that I can advertise to them in real time, within a short retargeting window.

Use Case #4

As an advertiser, I want to classify my audience in real time, so that I can react quickly to trending news.

How Smart Personas Models Work

When you create a Smart Personas model, you go through three steps:
  1. First, you select a minimum of two traits or segments that will constitute your personas.
  2. Then, you choose a trait or segment that defines the target audience that you want to classify.
  3. Finally, you choose a name for the model and select a data source that will store the Smart Personas segments.

Selection Criteria for Personas

You can choose any trait or segment to define your personas. We recommend choosing your traits or segments so that each persona has at least a few hundred real time user profiles, and each user profile has a rich set of traits for the algorithm to learn from.
Make sure you are capturing granular traits across your digital properties. For optimal results, the overlap amongst personas should be minimal.

Selection Criteria for Target Audience

Similar to persona selection, we recommend choosing your trait or segment that defines your target audience in such way that it has a rich set of traits, for classification into the right persona.

Smart Personas Model Training Phase

Before the algorithm can classify your audience into the right personas, it needs to train itself on your data.
For each persona that you define, the algorithm retrieves all the AAM UUID s active in the last 30 days, and analyzes their respective traits.

Smart Personas Model Classification Phase

When a visitor who is part of the target audience is seen in real time, the model evaluates whether the visitor is part of the defined personas. For every visitor that does not belong to any of the personas, the model assigns a persona qualification score.
While evaluating audiences and assigning scores, the model uses the default Profile Merge Rule defined in your account. Finally, the visitor gets classified into the persona for which they received the highest score.

Considerations and Limitations

When configuring your Smart Personas models, keep in mind the following considerations and limitations:
  • You can create up to 10 Smart Personas models.
  • For each model, you can choose up to 50 base traits / segments.
  • Third party data is not currently supported in Smart Personas. It will be supported in a future update, coming in 2020.
  • During the beta phase, audience classification is done only for real time audiences.
  • Smart Personas performs audience classification based on all of your first party traits, from all your data sources.
  • Segment evaluation for Smart Personas uses the default Profile Merge Rule that you defined in your account. To learn more about Profile Merge Rules see the dedicated documentation .

Role-Based Access Controls

The traits and segments that you choose for personas and audience classification are subject to Audience Manager Role-Based Access Controls .
Audience Manager users can only select traits or segments for personas and target audiences, that they have permission to view .

Data Export Controls

Smart Personas segments created by Smart Personas models inherit the Data Export Controls from the data source that you choose when building the model.
The newly created Smart Personas traits and segments will have the same privacy restrictions as the data source that you have selected.
When activating your Smart Personas segments, pay attention to all data governance restrictions for your selected destinations.