Lookalike Models Overview

Lytics Lookalike Models enable you to discover users who are similar to your best customers and create Predictive Audiences based on your model scores, driving conversions and increasing engagement across your channels. Lookalike Models are a significant upgrade of the features formerly known as "SegmentML" and "Discovery Reports", providing a custom machine learning (ML) solution in Lytics, built for marketers.

Lookalike Models have the capacity to leverage all the features available in your Lytics user profiles to build complex models with potentially hundreds of features rather than the handful used for conventional marketing. Lytics models identify the important qualities that best distinguish your target audience from other audiences.

Ready to make your own models? See the Model Builder to get started.

To demonstrate how Lookalike Models can bring your marketing team's segmentation strategy to the next level, we've outlined how you could segment users by hand compared to how a Lookalike Model would accomplish this task. For our example use case, the goal is to identify users who are likely to buy a travel package for the summer.

How a marketer may create segmentation rules by hand:

1. People buy travel packages months in advance, so identify users who are visiting in winter and spring.
2. People who already get promotions are much more likely to buy expensive items.
3. People who have already bought a package are likely to buy again.

Targeting users that match these three rules will certainly improve the efficacy of a campaign, but why stop at three rules? Are there more factors that can be used to refine this group of users?

How Lytics Lookalike Models would do it instead:

1. What do people who have bought travel packages in the past "look like" (i.e., what features do they have in common)?
2. Analyze all the information known for these people who have bought travel packages.
3. Determine which features are significant and which values of these features are significant (e.g., visiting the website is important, specifically three to five times).
4. Analyze all the information known about people who have not bought travel packages.
5. Determine which users share common features with past summer travel package purchasers.
6. Take the most similar users to use in targeting.

The key difference here is that a marketer may use a handful of criteria using logical heuristics to define a segment of users while Lookalike Models will look at hundreds of factors including potential non-obvious, impactful criteria to define an audience of users for the same purpose.

Before learning how to build Lookalike Models in Lytics, it's important to understand the following terminology.

• Model: the output of customer data and a ML algorithm that can provide predictions on the data.
• Source Audience: the group of users to reach with your marketing messages (e.g., “unknown users”). Lytics calculates a score from 0 to 1 representing the user's likelihood to convert to the target audience.
• Target Audience: the group of users that represents the desired outcome for users in the source audience (e.g., “users with email addresses”).
• Predictive Audience: the output audience(s) that are built using the predictive score from a Lookalike Model.
• Insights: observations about the output of the model with actionable suggestions to increase marketing performance.