# Lookalike Models ### About this export | Field | Value | | --- | --- | | **content_type** | lesson | | **platform** | contentstack-academy | | **source_url** | https://www.contentstack.com/academy/courses/beyond-the-basics/lookalike-models | | **course_slug** | beyond-the-basics | | **lesson_slug** | lookalike-models | | **markdown_file_url** | /academy/md/courses/beyond-the-basics/lookalike-models.md | | **generated_at** | 2026-04-28T06:55:35.343Z | > Part of **[Beyond the Basics](https://www.contentstack.com/academy/courses/beyond-the-basics)** on Contentstack Academy. **Academy MD v3** — structured for retrieval; no quiz or assessment keys. #### Video details #### At a glance - **Title:** Lookalike Models - **Duration:** 1m 50s - **Media link:** https://cdn.jwplayer.com/previews/oXPDbF1w - **Publish date (unix):** 1751897371 #### Streaming renditions - application/vnd.apple.mpegurl - audio/mp4 · AAC Audio · 113573 kbps - video/mp4 · 180p · 200p · 152187 kbps - video/mp4 · 270p · 300p · 168241 kbps - video/mp4 · 360p · 400p · 185580 kbps - video/mp4 · 406p · 450p · 201175 kbps - video/mp4 · 540p · 600p · 244015 kbps #### Timed text tracks (delivery) - **thumbnails:** `https://cdn.jwplayer.com/strips/oXPDbF1w-120.vtt` #### Transcript Welcome to the laboratory, your hub for getting hands-on with all things data science inside of Linux. Here we will focus on bringing you unprecedented access to industry-leading machine learning and AI tools, all of which are self-serviceable. It really is like having a team of data scientists at your disposal. What if you knew which users were going to buy a product or unsubscribe before an action even took place? Now with lookalike models you can do just that by comparing those who have reached a particular goal, the target audience, to those who have not, your source. We can then build a predictive audience of those who are very likely to reach that goal in the future. The UI comes packed with a variety of existing and new features as well as improvements upon existing ones. Auto-tuning for example acts as an easy button ensuring even those with little experience can successfully build great models to power predictive audiences. We've improved both visuals and navigation to ensure you fully understand how models are being used and what makes each one unique. Clear and actionable debugging information ensures there's no mystery and always a next step. Finally, accuracy and reach help you find the perfect balance to support your desired use case. Lookalike models apply to many marketing use cases at any stage of the funnel. Locate customers who are likely to churn, find those most likely to make a purchase, and nurture those that show clear signs of becoming high-value users. And so much more. Get started today by creating your first model. #### Subtitles (WebVTT) ```webvtt WEBVTT 1 00:00:00.000 --> 00:00:04.960 Welcome to the laboratory, your hub for getting hands-on with all things data 2 00:00:04.960 --> 00:00:09.820 science inside of Linux. Here we will focus on bringing you unprecedented 3 00:00:09.820 --> 00:00:14.400 access to industry-leading machine learning and AI tools, all of which are 4 00:00:14.400 --> 00:00:18.880 self-serviceable. It really is like having a team of data scientists at your 5 00:00:18.880 --> 00:00:24.760 disposal. What if you knew which users were going to buy a product or unsubscribe 6 00:00:24.760 --> 00:00:29.720 before an action even took place? Now with lookalike models you can do just 7 00:00:29.720 --> 00:00:35.200 that by comparing those who have reached a particular goal, the target audience, to 8 00:00:35.200 --> 00:00:40.040 those who have not, your source. We can then build a predictive audience of 9 00:00:40.040 --> 00:00:46.560 those who are very likely to reach that goal in the future. The UI comes packed 10 00:00:46.560 --> 00:00:50.840 with a variety of existing and new features as well as improvements upon 11 00:00:50.840 --> 00:00:56.960 existing ones. Auto-tuning for example acts as an easy button ensuring even 12 00:00:56.960 --> 00:01:01.280 those with little experience can successfully build great models to power 13 00:01:01.280 --> 00:01:07.840 predictive audiences. We've improved both visuals and navigation to ensure you 14 00:01:07.840 --> 00:01:12.680 fully understand how models are being used and what makes each one unique. 15 00:01:12.680 --> 00:01:17.440 Clear and actionable debugging information ensures there's no mystery 16 00:01:17.440 --> 00:01:24.400 and always a next step. Finally, accuracy and reach help you find the perfect 17 00:01:24.400 --> 00:01:31.040 balance to support your desired use case. Lookalike models apply to many 18 00:01:31.040 --> 00:01:36.200 marketing use cases at any stage of the funnel. Locate customers who are likely 19 00:01:36.200 --> 00:01:42.080 to churn, find those most likely to make a purchase, and nurture those that show 20 00:01:42.080 --> 00:01:48.120 clear signs of becoming high-value users. And so much more. Get started today by 21 00:01:48.120 --> 00:01:51.400 creating your first model. ``` ```transcript [00:00] Welcome to the laboratory, your hub for getting hands-on with all things data [00:04] science inside of Linux. Here we will focus on bringing you unprecedented [00:09] access to industry-leading machine learning and AI tools, all of which are [00:14] self-serviceable. It really is like having a team of data scientists at your [00:18] disposal. What if you knew which users were going to buy a product or unsubscribe [00:24] before an action even took place? Now with lookalike models you can do just [00:29] that by comparing those who have reached a particular goal, the target audience, to [00:35] those who have not, your source. We can then build a predictive audience of [00:40] those who are very likely to reach that goal in the future. The UI comes packed [00:46] with a variety of existing and new features as well as improvements upon [00:50] existing ones. Auto-tuning for example acts as an easy button ensuring even [00:56] those with little experience can successfully build great models to power [01:01] predictive audiences. We've improved both visuals and navigation to ensure you [01:07] fully understand how models are being used and what makes each one unique. [01:12] Clear and actionable debugging information ensures there's no mystery [01:17] and always a next step. Finally, accuracy and reach help you find the perfect [01:24] balance to support your desired use case. Lookalike models apply to many [01:31] marketing use cases at any stage of the funnel. Locate customers who are likely [01:36] to churn, find those most likely to make a purchase, and nurture those that show [01:42] clear signs of becoming high-value users. And so much more. Get started today by [01:48] creating your first model. ``` #### Lesson text Gain an in-depth understanding of Lytics Lookalike Models and how to build Predictive Audiences that drive engagement and conversions. ## Introducing Lookalike Models ### Overview Note: On January 10, 2023, we upgraded our UI with a new, refreshed interface. All of the underlying functionality is the same, but you will notice that things look a little different from this Academy guide. The most notable change is that the navigation menu has moved from the top of the app to the left side. We appreciate your patience as we work on updating our Academy. Lytics makes it easy to build Lookalike Models and Predictive Audiences that drive engagement and conversions. ### What will I learn? * What are Lytics Lookalike Models? How can I use them? * Where do Lookalike Models live in Lytics? * How to start making models * How to understand your model performance and what to do next * How to create Predictive Audiences ### How are Lytics Lookalike Models different from other tools? You may be familiar with "Lookalike Audiences" on Facebook or "Similar Audiences" on Google. Lytics Lookalike Models are different in a few key ways: * Based on your own first-party, cross-channel data (no walled garden) * You can build and validate your own custom models (no black box) * Quick and easy interface for marketers to make models (no data science team required) * Provide real-time predictions - updating user scores for dynamic and effective targeting ### Lytics Laboratory Lytics provides a **data science workbench for your marketing teams** in the **Laboratory** section of the Lytics UI. This is where you'll go to build **Lookalike Models**. ![Click Laboratory > UI Models.png](https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/bltb24a9f4465cfcc2c/686bd5514e325563d15687ae/Click_Laboratory_UI_Models.png) Check out the short video "Lookalike Models" (1.5 min). #### What are common use cases for Lookalike Models? * Optimize early stage funnel. Identify users least likely to progress to **cast an intelligently wide net**. * Unknown users to known users * Optimize late stage funnel. Identify users most likely to convert to **optimize higher touch experiences**. * Known Users to Purchasers * One time Purchasers to Repeat Purchasers * Nurture users who are likely to become high lifetime value (LTV) customers * Reduce churn by identifying known users who are likely to churn Learn more: [Lytics Laboratory documentation](https://learn.lytics.com/documentation/product/features/laboratory/introduction) **Which of the following are benefits of Lytics Lookalike Models? (select all that apply)** A. Models continuously update allowing real-time predictions B. You can import existing models from other tools into Lytics C. Custom models can be built from scratch D. Models are built using your own first-party data Answer: A, C, D ### Core Concepts Before learning how to build Lookalike Models in Lytics, it's important to understand the key terms that will be used throughout:  * **Model**: the output of customer data and a ML algorithm that can provide predictions on the data. * **Source Audience**: the group of users you want to reach with your marketing messages to get them to convert on a particular marketing goal.  * For example: “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 (have converted in the past). * For example: “users with email addresses”. * **Predictive Audience**: the output audience(s) that are built using the predictive score from a Lookalike Model. For more definitions, see our [Glossary](https://learn.lytics.com/content/lytics-glossary). #### Segmentation Strategies: Manual vs. Machine Check out the [Lookalike Models Overview](https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/overview#segmentation-strategies:-manual-vs.-machine) for an example of how Lookalike Models work compared to a manual segmentation strategy. **Match the Lytics term to its definition.** Model Output of data and an algorithm that provides predictions Target Audience Users that have yet to convert on your marketing goal Source Audience Users that have converted in the past Predictive Audience Users available to target, using the predictive score output from a Lookalike Model ## Building Lookalike Models ### Lookalike Model Builder The Lookalike Model Builder provides an interface for marketers to quickly build custom models in Lytics. Navigate to the Lookalike Models dashboard and find the **Create New Model** button at the top right to get started. ![click-create-new-model.png](https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt49a93af1fddafc74/686be0df47548f406f569af6/click-create-new-model.png) ### Configuration Options You can use a number of basic and advanced configuration options to build your model: * Basic options provide an intelligent starting point, making it quick and easy to get started.  * Advanced options give granular control to those who have more experience with model building. For most use cases, building a model with the basic configuration parameters is sufficient. The **only required parameters** are: * Source audience * Target audience  Selecting the right audiences is **very important for building a usable model**. We'll touch on this more in a later section. For descriptions and examples of all configuration options, see [Model Builder documentation](https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/model-builder).  **Which of the following basic configuration parameters are required?** A. Custom Model Name B. Source Audience C. Auto Tune D. Target Audience Answer: B, D **Models built with Auto Tune can also include advanced configuration parameters.** A. True B. False Answer: True ### Model Dashboard The Lookalike Model dashboard provides visibility of the health, status, and usage of your Lookalike Models. It lists all models in your account allowing you to search, sort, and view the summary, configuration, and diagnostic information for each model created. ![lytics-lookalike-model-summary.png](https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt9aae40f62f0e263e/686be6318f61ad7bdddc66d6/lytics-lookalike-model-summary.png) Here's a quick rundown of the main sections: #### Model health chart Shows the total number of models for an account, and how many are considered **healthy** or unhealthy. A model is considered healthy if it can make accurate predictions. #### Model status  Displays how many of your models have been **activated**. An activated model is a model currently generating a score that is being written to user profiles, meaning the model's predictions can be used for audience segmentation and targeting. #### Model usage  Shows the percentage of all your audiences that are using activated models. #### Model table Allows you to search for any model in your account. Click any model to open its [summary](https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/model-summary) for more detailed information about that model. See the [documentation](https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/model-dashboard) for more details.  **Note: Lookalike Models Activation Limit** - You can only have 5 Lookalike Models active at a time, per the default account setting. If you're interested in a higher limit, please contact your Account Manager for more information. **To use your model's predictions in audience segmentation and targeting, the model must be \_\_\_\_\_\_\_?** A. Recently created B. Activated C. Top performing Answer: B ### Model Summary The Lookalike Model Summary surfaces valuable information and metrics about the performance and usage of your model. #### Understanding Accuracy and Reach At the top of each Model Summary page, you'll see two bars indicating the model's accuracy and reach scores. ![accuracy-reach.png](https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt62f4dd47b1e7fbb7/686bec9c77a15576584c156d/accuracy-reach.png) * **Accuracy**: the precision of a model’s predictions * **Reach**: the relative size of a Lookalike Model’s addressable audience As a general principle, you cannot optimize for both accuracy and reach in a Lookalike Model. There are inherent tradeoffs between the two. * Optimize for **reach** for targeting users in earlier stages of your funnel * Reach more users, while being less precise * Optimize for **accuracy** for targeting users in later stages of your funnel * Be more precise, but reach less users ![accuracy-reach-graph.png](https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt71c82eed35bbc7b9/686bec9d167482a55e1b16f9/accuracy-reach-graph.png) When balancing the trade off between accuracy and reach, consider the sum of accuracy and reach to determine a model’s fitness to be used: good models have an accuracy and reach sum around 10, excellent models will sum to more than 10, fair/poor models will sum to less than 10. Refer to the [Accuracy vs. Reach](https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/accuracy-vs-reach) documentation **Interpreting your model's results** In the rest of the Model Summary, you can see how the source and target audiences overlap, the important features that contribute to the model's predictions, what audiences are using the model, and any diagnostic and troubleshooting messages. ![model-summary.png](https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt33a305dda3cad71c/686bec9d588d4685e5838125/model-summary.png) **Model predictions** Displays the size of your source and target audiences and charts the predictions for those audiences. The shape of the graph is most important, which indicates the amount of overlap between your source and target audiences. **Model features importance** Indicates which information the model is using to make predictions. More specifically, the chart lists the relative importance of features among users likely to convert from the source to the target audience. **Model usage** Displays a list of audiences that are utilizing this model for targeting and a button to create a new Predictive Audience with this model. **Diagnostics & troubleshooting** Provides messages pertaining to the performance and status of your Lookalike Model. These messages are categorized as warnings, errors, or information, and may include suggestions on how to improve your models. Refer the [Model Summary](https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/model-summary) documentation **Check your understanding of the tradeoffs between accuracy and reach.** High reach Better for earlier stages of your funnel Low accuracy and low reach Better for later stages of your funnel High accuracy Not a good model, shouldn't be used for predictions[](https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/accuracy-vs-reach) ## Targeting Predictive Audiences ### Creating Predictive Audiences Marketing campaigns run with **Predictive Audiences** from a healthy **Lookalike Model** are very likely to result in higher conversion rates. Even better, Lytics makes it super easy to create Predictive Audiences with the click of a button. Really, it's that easy! **Ok, show me how to create a Predictive Audience!** Once a Lookalike Model is built and users are scored, follow these steps to make a Predictive Audience. 1. Find the model of interest and go to its **Summary** page. 2. Scroll to the **Model Usage** section. 3. Click **Create Predictive Audience**. 4. Now in the Audience Builder, you'll see the model predictions pre-populated as a user field named \`segment\_prediction\`. 5. You can adjust the prediction decision threshold or add rules to further refine the audience. ![model\_usage.png](https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt41dfebed02ce28ed/686bf67219cab28ee2cecd4b/model_usage.png) Refer to the [Create Predictive Audiences](https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/model-builder#create-predictive-audiences) documentation. ### Selecting the right Source and Target Building effective Lookalike Models that power your Predictive Audiences is an iterative process.  Some experimentation is to be expected before you find the right audiences and configuration options for your use case, which ties into the idea behind the "Lytics Laboratory."  #### Selecting the Right Source and Target Audience One of the most important factors for Lookalike Model performance is your selection of the source and target audience.  ![Lytics\_Lookalike\_Models\_audience\_selection\_diagram.png](https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt69987467fd5b4f68/686c0d29f1c7c242864ecc5f/Lytics_Lookalike_Models_audience_selection_diagram.png) Check out the documentation linked below for examples of how to select the right audiences for your use case. Refer to the [Selecting the right audiences](https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/interpreting-model-messages#selecting-the-right-source-and-target-audience) documentation. **Match the audience type to the example use case.** Adjacent Audience unknown audience → audience with email Divergent Audience unknown audience → audience with newsletter signup and single purchase Overlapping Audience unknown audience → audience with no purchases ### Iterating your Predictive Audiences Most Predictive Audiences are built by identifying users in the source audience who have a high model score, indicating they are likely to convert to the target audience.  This "high score" is called the Decision Threshold. #### Adjusting the Decision Threshold The decision threshold is a score from 0-1 * 0= very unlikely to convert * 1= very likely convert  * In most cases, the decision threshold is set to 0.5 To adjust the **reach** of the audience you are building, you might consider using a different decision threshold. * Lower decision threshold - **reach more users** in the source audience. * Higher decision threshold - **be more accurate but reach less users** in the source audience. Refer to the [Decision Threshold](https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/interpreting-model-messages#adjusting-the-decision-threshold) documentation **How do I pick the right threshold?** You may see diagnostic messages suggesting you create audiences using a different decision threshold. But keep in mind any relevant domain knowledge (which the model doesn't have) when choosing the decision threshold. **If you want to expand the reach of your Predictive Audience, how should you adjust the decision threshold?** A. Raise the decision threshold B. Keep it the same but pick a larger source audience C. Lower the decision threshold Answer: C #### My model is unhealthy. What can I do? See the [Improving Unhealthy Models](https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/interpreting-model-messages#improving-unhealthy-models) section for examples of why your model might not be performing well and suggested next steps. **What is the most common reason a model is considered unhealthy?** A. Auto Tune wasn't selected B. Source and target audiences were divergent or overlapping C. Decision threshold was too high D. Not enough signal in the underlying data Answer: B **If you are trying to predict which users are likely to make a purchase, which of the following data sources are required to build an accurate Lookalike Model?** A. Email data B. Demographic data C. Subscription data D. Purchase data Answer: D ## Next Steps ### More Resources To continue learning, we recommend you check out the following resources: * [Lookalike Models documentation](https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/overview) * [Leveraging Lookalike Models & Predictive Audiences](https://learn.lytics.com/use-cases/leverage-lookalike-models-and-predictive-audiences) * Learn about 6 different Use Cases across the customer lifecycle Just as you iterate Lookalike Models, the Lytics Team wants to keep iterating our training guides. #### Key takeaways - Connect **Lookalike Models** back to your stack configuration before moving to the next module. - Capture one concrete artifact (screenshot, Postman call, or code snippet) that proves the step works in your environment. - Re-read the delivery versus management boundary for anything you changed in the entry model. ## Supplement for indexing ### Content summary Lookalike Models. Gain an in-depth understanding of Lytics Lookalike Models and how to build Predictive Audiences that drive engagement and conversions. Introducing Lookalike Models Overview Note: On January 10, 2023, we upgraded our UI with a new, refreshed interface. All of the underlying functionality is the same, but you will notice that things look a little different from this Academy guide. The most notable change is that the navigation menu has moved from the top of the app to the left side. We appreciate your patience as we work on updating our Academy. Lytics makes it easy to build Lookalike Models and Predictive Audiences that drive engagement and conversions. What will I learn? What are Lytics Look ### Retrieval tags - Lookalike - Models - beyond-the-basics - lesson 04 - Lookalike Models - beyond-the-basics lesson ### Indexing notes Index this lesson as a primary chunk tagged with lesson_id "04" and topics: [Lookalike, Models]. Parent course slug: beyond-the-basics. Use asset_references URLs as thumbnail hints in search results when present. Never surface LMS quiz content or assessment answers from this file. ### Asset references | Label | URL | | --- | --- | | Video thumbnail: Lookalike Models | `https://cdn.jwplayer.com/v2/media/oXPDbF1w/poster.jpg?width=720` | | Click Laboratory > UI Models.png | `https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/bltb24a9f4465cfcc2c/686bd5514e325563d15687ae/Click_Laboratory_UI_Models.png` | | click-create-new-model.png | `https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt49a93af1fddafc74/686be0df47548f406f569af6/click-create-new-model.png` | | lytics-lookalike-model-summary.png | `https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt9aae40f62f0e263e/686be6318f61ad7bdddc66d6/lytics-lookalike-model-summary.png` | | accuracy-reach.png | `https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt62f4dd47b1e7fbb7/686bec9c77a15576584c156d/accuracy-reach.png` | | accuracy-reach-graph.png | `https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt71c82eed35bbc7b9/686bec9d167482a55e1b16f9/accuracy-reach-graph.png` | | model-summary.png | `https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt33a305dda3cad71c/686bec9d588d4685e5838125/model-summary.png` | | model\_usage.png | `https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt41dfebed02ce28ed/686bf67219cab28ee2cecd4b/model_usage.png` | | Lytics\_Lookalike\_Models\_audience\_selection\_diagram.png | `https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt69987467fd5b4f68/686c0d29f1c7c242864ecc5f/Lytics_Lookalike_Models_audience_selection_diagram.png` | ### External links | Label | URL | | --- | --- | | Contentstack Academy home | `https://www.contentstack.com/academy/` | | Training instance setup | `https://www.contentstack.com/academy/training-instance` | | Academy playground (GitHub) | `https://github.com/contentstack/contentstack-academy-playground` | | Contentstack documentation | `https://www.contentstack.com/docs/` | | Click Laboratory > UI Models.png | `https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/bltb24a9f4465cfcc2c/686bd5514e325563d15687ae/Click_Laboratory_UI_Models.png` | | Lytics Laboratory documentation | `https://learn.lytics.com/documentation/product/features/laboratory/introduction` | | Glossary | `https://learn.lytics.com/content/lytics-glossary` | | Lookalike Models Overview | `https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/overview#segmentation-strategies:-manual-vs.-machine` | | click-create-new-model.png | `https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt49a93af1fddafc74/686be0df47548f406f569af6/click-create-new-model.png` | | Model Builder documentation | `https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/model-builder` | | lytics-lookalike-model-summary.png | `https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt9aae40f62f0e263e/686be6318f61ad7bdddc66d6/lytics-lookalike-model-summary.png` | | summary | `https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/model-summary` | | documentation | `https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/model-dashboard` | | accuracy-reach.png | `https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt62f4dd47b1e7fbb7/686bec9c77a15576584c156d/accuracy-reach.png` | | accuracy-reach-graph.png | `https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt71c82eed35bbc7b9/686bec9d167482a55e1b16f9/accuracy-reach-graph.png` | | Accuracy vs. Reach | `https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/accuracy-vs-reach` | | model-summary.png | `https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt33a305dda3cad71c/686bec9d588d4685e5838125/model-summary.png` | | model\_usage.png | `https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt41dfebed02ce28ed/686bf67219cab28ee2cecd4b/model_usage.png` | | Create Predictive Audiences | `https://learn.lytics.com/documentation/product/features/laboratory/lookalike-models/model-builder#create-predictive-audiences` | | Lytics\_Lookalike\_Models\_audience\_selection\_diagram.png | `https://images.contentstack.io/v3/assets/bltebc53cfaf0dd6403/blt69987467fd5b4f68/686c0d29f1c7c242864ecc5f/Lytics_Lookalike_Models_audience_selection_diagram.png` |