Look-alike Modeling

Extend your reach beyond your core customers and discover new, unique, high-value audiences from third-party data using our proprietary TraitWeight algorithm, powered by Adobe Sensei.


You can’t duplicate your best customers, but you can find more like them.

You need to keep finding new customers. But it’s hard to know where to focus your time and resources. And time really matters. You need to uncover these audiences before your competitors do. And you need to do it fast. The key lies in using your current customer data to locate others with similar attributes.

Look-alike modeling extends your reach by finding new high-value audience segments similar to your current customer base. Select a trait or segment, a time interval, and first- or third-party data sources. Our machine learning algorithm, TraitWeight, is powered by Adobe Sensei and looks for people or businesses in the data sources with the same traits. Next, we weigh and display the results based on which traits are closest to your base audience. You then can build accurate traits to expand your audience.


See what makes it work.

Start engaging new audiences quickly. You’ll find our new models are actionable much faster than our competitors.

Current and relevant results
The modeling process automatically runs at regular intervals to extract new value from your data so you always have the latest information at your fingertips.

Don’t spend time guessing at traits or segments, or managing a large set of static rules — the algorithm will find audiences for you.

Server-side discovery
Modeling works with server-side discovery and qualification processes that evaluate your data and the third-party data you have access to. This means you don’t have to see visitors on your site to qualify them for a trait.

Learn more about look-alike modeling in Adobe Audience Manager.

Pull back the curtain.

Read more about how look-alike modeling works in our Adobe blog.

Read more

Find your next best customer.

Learn how to create your first lookalike model in our Help page.

Read more