diff --git a/src/_data/catalog/sources.yml b/src/_data/catalog/sources.yml index 1d43d3d959..1776761bef 100644 --- a/src/_data/catalog/sources.yml +++ b/src/_data/catalog/sources.yml @@ -1484,7 +1484,7 @@ items: isCloudEventSource: true slug: actions-qualtrics url: connections/sources/catalog/cloud-apps/actions-qualtrics - hidden: true + hidden: false regions: - us endpoints: diff --git a/src/_data/sidenav/main.yml b/src/_data/sidenav/main.yml index 0cf714ec9d..93239458ab 100644 --- a/src/_data/sidenav/main.yml +++ b/src/_data/sidenav/main.yml @@ -355,6 +355,13 @@ sections: title: Computed Traits - path: '/engage/audiences/sql-traits' title: SQL Traits + - section_title: Predictive Traits + slug: engage/audiences/predictive-traits + section: + - path: '/engage/audiences/predictive-traits/' + title: Predictive Traits + - path: '/engage/audiences/predictive-traits/using-predictive-traits' + title: Using Predictive Traits - section_title: Journeys description: "Learn how to create multi-step Journeys to tailor messages to your users." diff --git a/src/engage/audiences/predictive-traits/index.md b/src/engage/audiences/predictive-traits/index.md new file mode 100644 index 0000000000..07017eccb8 --- /dev/null +++ b/src/engage/audiences/predictive-traits/index.md @@ -0,0 +1,87 @@ +--- +title: Predictive Traits +plan: engage-foundations +--- + +> info "" +> Predictive Traits is in public beta. + +Predictive Traits, Segment's artificial intelligence and machine learning feature, lets you predict the likelihood that users will perform any event tracked in Segment. + +With Predictive Traits, you can identify users with, for example, a high propensity to purchase, refer a friend, or use a promo code. Predictive Traits also lets you predict a user's lifetime value (LTV). + +Segment saves Predictive Traits to user profiles, letting you build Audiences, trigger Journeys, and send data to downstream Destinations. + +On this page, you'll learn how to build a Predictive Trait. + +## Access and build Predictive Traits + +To create Predictive Traits, you'll first request demo access, then build a Predictive Trait. + +![The Predictive Trait builder in the Segment UI](../../images/trait_builder.png) + + +### Request Predictive Traits access + +Follow these steps to access Predictive Trait: + +1. Navigate to **Engage > Audiences > Computed Traits**. Select **Create computed trait**. +2. Select **Request Demo** to access Predictive Traits. + +### Build a Predictive Trait + +Once your Workspace is enabled for Predictive Traits, follow these steps to build a Predictive Trait: + +3. In the Trait Builder, select **Predictive Traits**, choose the Trait you want to create, then click **Next**. + - Choose **Custom Predictive Goal**, **Likelihood to Purchase**, or **Predicted Lifetime Value**. +4. (For custom Predictive Goals) Add a condition(s) and event to predict, then select **Calculate**. If you're satisfied with the available data, select **Next**. +5. (Optional) Connect a Destination, then select **Next**. +6. Add a name and description for the Trait, then select **Create Trait**. + +In the next section, you'll learn more about the three available Predictive Traits. + +## Choosing a Predictive Trait + +Segment offers three Predictive Traits: Custom Predictive Goals, Likelihood to Purchase, and Predicted LTV. + +### Custom Predictive Goals + +Custom Predictive Goals require a starting cohort, target event, and quality data. + +#### Starting cohort + +When you build a Custom Predictive Goal, you'll first need to select a cohort, or a group of users, for which you want to make a prediction. Traits with small cohorts compute faster and tend to be more accurate. If you want to predict for an entire Audience, though, skip cohort selection and move to selecting a target event. + +#### Target event + +The target event is the Segment event that you want to predict a user's likelihood to perform. Predictions work better when many customers have performed the event. + +#### Data requirements + +Segment doesn't enforce data requirements for predictions. In machine learning, however, data quality and quantity are critical. Segment recommends that you make predictions for at least 50,000 users and choose a target event that at least 5,000 users have performed in the last 30 days. + +You can create predictions outside of these suggestions, but your results may vary. + +### Likelihood to Purchase + +Likelihood to Purchase is identical to Custom Predictive Goals, but Segment prefills the **Order Completed** event, assuming it's tracked in you Segment instance. + +If you don’t track Order Completed, choose a target event that represents a customer making a purchase. + +### Predicted Lifetime Value + +Predicted Lifetime Value predicts a customer's future spend over the next 90 days. To create this prediction, select a purchase event, revenue property, and the currency (which defaults to USD). The following table contains details for each property: + +| Property | Description | +| --------------- | ---------------------------------------------------------------------------------------------------------------------------- | +| Purchase event | Choose a target event that represents a customer making a purchase. For most companies, this is usually **Order Completed**. | +| Purchase amount | Select the purchase event property that represents the total amount. For most companies, this is the **Revenue** property. | +| Currency | Segment defaults all currencies to USD. | + +#### Data requirements + +Predicted LTV has strict data requirements. Segment can only make predictions for customers that have purchased two or more times. Segment also requires a year of purchase data to perform LTV calculations. + +## Use cases + +For use cases and information on how Segment builds Predictive Traits, read [Using Predictive Traits](/docs/engage/audiences/predictive-traits/using-predictive-traits/). diff --git a/src/engage/audiences/predictive-traits/using-predictive-traits.md b/src/engage/audiences/predictive-traits/using-predictive-traits.md new file mode 100644 index 0000000000..8137968155 --- /dev/null +++ b/src/engage/audiences/predictive-traits/using-predictive-traits.md @@ -0,0 +1,104 @@ +--- +title: Using Predictive Traits +plan: engage-foundations +--- + +> info "" +> Predictive Traits is in public beta. + +## Working with Predictive Traits in Segment + +Segment creates Predictive Traits as Computed Traits, with scores saved to user profiles as a percentage cohort. For example, `0.8` on a user's profile indicates that the user is in the the cohort's 80th percentile, or the top 20%. + +Once you've selected a cohort, you can use Predictive Traits in concert with other Segment features: + +- [Audiences](/docs/engage/audiences/), which you can create with Predictive Traits as a base. +- [Journeys](/docs/engage/journeys/); use Predictive Traits in Journeys to trigger [Engage marketing campaigns](/docs/engage/campaigns/) when users enter a high-percentage cohort, or send promotional material if a customer shows interest and has a high propensity to buy. +- [Destinations](/docs/connections/destinations/); send your Predictive Traits downstream to [Warehouses](/docs/connections/storage/warehouses/), support systems, and ad platforms. + +### Prediction tab + +Once Segment has generated your prediction, you can access it in your Trait's **Prediction** tab. The Prediction tab gives you actionable insight into your Predictive Trait. + +![The Explore your prediction section of the Computed Trait Prediction tab](../../images/explore_prediction.png) + +The **Explore your prediction** section of the Prediction tab visualizes prediction data and lets you create Audiences for targeting. An interactive chart displays a percentile cohort score that indicates the likelihood of users in each group to convert on your chosen goal. You can choose the top 20%, bottom 80%, or create custom ranges for specific use cases. + +You can then create an Audience from the group you've selected, letting you send efficient, targeted marketing campaigns within Journeys. You can also send your prediction data to downstream Destinations. + +#### Model statistics + +The Predictions tab's **Understand your prediction** section provides insights into the performance of the underlying predictive model. This information helps you understand the data points that contribute to the prediction results. + +![The Understand your prediction dashboard in the Segment UI](../../images/understand_prediction.png) + +The Understand your prediction dashboard displays the following model metrics: + +- **AUC**, or Area under [the ROC curve](https://en.wikipedia.org/wiki/Receiver_operating_characteristic){:target="_blank"}; AUC lands between 0 and 1, where 1 is a perfect future prediction, and 0 represents the opposite. Higher AUC indicates better predictions. +- **Lift Quality**, which measures the effectiveness of a predictive model. Segment calculates lift quality as the ratio between the results obtained with and without the predictive model. Higher lift quality indicates better predictions. +- **Log Loss**; the more a predicted probability diverges from the actual value, the higher the log-loss value will be. Lower log loss indicates better predictions. +- **Top contributing events**; this graph visually describes the events factored into the model, as well as the associated weights used to create the prediction. + +## Predictive Traits use cases + +Predictions offer more value in some situations than others. This sections covers common scenarios where Predictive Traits have high impact, as well as others where alternative approaches may be more appropriate. + +### Marketing opportunities + +- **Improve ad targeting**; build targeted audience segments based on predictive behavior. +- **Optimize campaign performance**; reduce customer acquisition costs (CAC), and improve customer lifetime value (LTV) by building campaigns that target customers most likely to purchase or perform another desired action. +- **Power more personalization**; With Predictive Traits, you can deliver the right message at the right time. You can create targeted customer Journeys with personalized offers and recommendations that boost conversion and promote upsell and cross sell. +- **Win back unengaged customers**; Predictive Traits let you identify unengaged customers and create personalized winback campaigns to reengage them. + +### Data science use cases + +- **Model improvement**; You can extract Predictive Traits from Segment and use them to improve proprietary machine learning models. +- **Testing experiences**; data teams can validate and strengthen existing machine learning models by testing proprietary models against Segment's out-of-the-box models. +- **Save time on predictive modeling**; data science teams can use Segment's predictive models, freeing up time to building other in-house models like inventory management, fraud alerting, and so on. + +### When to use a prediction + +Predictions are most effective in the following situations: + +- **When your desired outcome is difficult to measure and not clearly defined**, like activation, retention, engagement, or long-term value Journeys. +- **When your product has more than 100,000 average monthly users**; smaller sample sizes lead to less accurate statistical conclusions. +- **When you need to save time building cohorts**; Predictive Traits lets marketers access and take action on predictive data without the help of data science teams, while also giving data teams out-of-the-box + +### When other approaches work better + +Predictions may not be as beneficial in the following situations: + +- **When you sell limited but highly-priced items**, like enterprise software, complex medical machines, and so on; this also applies if you're in the B2B sector. +- **When you don't yet have enough data**; your model could produce errors if, for example, your target is too new and lacks sufficient data. Waiting a month could allow Segment to gather more predictive data. + +## Frequently asked questions + +{% faq %} +{% faqitem What type of machine learning model is used? %} +Segment uses a binary classification model that uses decision trees. +{% endfaqitem %} + +{% faqitem What level of confidence can I have in my predictions? %} +Once Segment creates your prediction, you can check the model statistics page, where Segments shows you how the model was created. Segment also maintains automated systems that monitor model performance and will alert you if your model is not predictive. +{% endfaqitem %} + +{% faqitem How long do Predictive Traits take to create? %} +Trait creation depends on the amount of data, but Segment expects predictions to be completed in around 24 hours. For larger customers, however, this could take 48 hours. Predictive Traits shows a status of `In Progress` while computing; Segment updates this status when customers are scored. +{% endfaqitem %} + +{% faqitem How do you store trait values? %} +The created trait value represents the user's percentile cohort. This value refreshes every seven days. If you see `0.85` on a user's profile, this means the user is in the 85th percentile, or the top 15% for the Predictive Trait. +{% endfaqitem %} + +{% faqitem How frequently do you re-train the model? %} +Segment rebuilds the machine learning model every 30 days. +{% endfaqitem %} + +{% faqitem How frequently do you update trait values? %} +Every seven days. +{% endfaqitem %} + +{% faqitem How many Predictive Traits can I have? %} +You can have 10 active Predictive Traits. +{% endfaqitem %} +{% endfaq %} diff --git a/src/engage/images/explore_prediction.png b/src/engage/images/explore_prediction.png new file mode 100644 index 0000000000..a1457d6244 Binary files /dev/null and b/src/engage/images/explore_prediction.png differ diff --git a/src/engage/images/trait_builder.png b/src/engage/images/trait_builder.png new file mode 100644 index 0000000000..44c0cd329d Binary files /dev/null and b/src/engage/images/trait_builder.png differ diff --git a/src/engage/images/understand_prediction.png b/src/engage/images/understand_prediction.png new file mode 100644 index 0000000000..61923aed47 Binary files /dev/null and b/src/engage/images/understand_prediction.png differ diff --git a/src/engage/index.md b/src/engage/index.md index 4584b54674..c1053a0430 100644 --- a/src/engage/index.md +++ b/src/engage/index.md @@ -21,6 +21,7 @@ Add detail to user profiles with new traits and use them to power personalized m - [**Computed Traits:**](/docs/engage/audiences/computed-traits/) Use the Engage drag-and-drop interface to build per-user (B2C) or per-account (B2B) metrics on user profiles (for example, “lifetime value” or “lead score”). - [**SQL Traits:**](/docs/engage/audiences/sql-traits/) Run custom queries on your data warehouse using the Engage SQL editor, and import the results into Segment. With SQL Traits, you can pull rich, uncaptured user data back into Segment. +- [**Predictive Traits (Beta)**:](/docs/engage/audiences/predictive-traits/) Predict the likelihood that users will perform custom events tracked in Segment, like LTV, churn, and purchase. #### Build Audiences Create lists of users or accounts that match specific criteria. For example, after creating an `inactive accounts` audience that lists paid accounts with no logins in 60 days, you can push the audience to your analytics tools or send an SMS, email, or WhatsApp campaign with Engage Channels. Learn more about [Engage audiences](/docs/engage/audiences/).