In-session recommender

Sid Chaudhary

Sid Chaudhary

Founder & CEO

Share:

Decide which product features to highlight for each user as they browse, based on their adoption patterns and preferences.

About the Growth Play

To ensure efficient product adoption, you must react in real-time to suggest optimal features so that the end users can reach their next product adoption milestone faster.

Using Lifecycle agent combined with personalizations, you can build an ultimate product adoption engine by highlighting the most relevant features to each user in real time.

Benefits

  • Increases user engagement by highlighting relevant features based on user behavior.
  • Reduces churn by keeping users engaged and satisfied with personalized experiences.
  • Enhances feature adoption through targeted recommendations.
  • Boosts ROI: by leveraging machine learning without the need for extensive resources.

How it works

Let's take an example of a SaaS app, "Otto," which offers features like Task Management, Time Tracking, and Team Collaboration. We aim to predict which feature to highlight to each user based on their behavior and adoption patterns.

Step 1: Create the Lifecycle Agent

Data preparation:

Ensure you have at least 21 days of data collection and a minimum of 10,000 average daily events.

Collect events related to feature usage, such as:

Tasks created

Time entries logged

Messages sent in team collaboration

Ensure your goal event, such as "Feature Adoption," has a minimum daily average of 200 true and 200 false users over 30 days.

Goal event requirements

Agent creation:

Choose the target goal representing the behavior you want to predict, such as "Becomes a Product Qualified Lead."

Choose target goal

Select the actions (events) you want to choose between, such as "Task Created," "Time Entry Logged," and "Message Sent."

Select actions

Filter out training data for better results by filtering users that would skew the results (e.g. users that did not login for the last 30 days)

Filter training data

Training the agent:

After the model is created, it starts the training and generating predictions. Intempt will create an output attribute to store prediction values.

Review the agent's prediction quality by checking the "Results" tab.

Wait to collect more data if necessary to improve prediction quality.

Step 2: Create segments

Create segments based on the agent output. Each user will have a predicted next best action, such as:

"task_created" for users likely to adopt Task Management

"time_entry_logged" for users likely to adopt Time Tracking

"message_sent" for users likely to adopt Team Collaboration

Create segments based on agent output

Segment creation details:

For Task Management, create a segment where the NBA attribute value is "task_created."

Task Management segment

For Time Tracking, create a segment where the NBA attribute value is "time_entry_logged."

Time Tracking segment

For Team Collaboration, create a segment where the NBA attribute value is "message_sent."

Team Collaboration segment

Step 3: Set up personalizations

Create experiences:

Navigate to the Experiences section and select "Create Experience"

For users with the next best action of "task_created":

Design a visual experience showcasing the advanced task management features. Use an engaging banner at the top of the dashboard highlighting "Did you know? You can now create recurring tasks and set task dependencies for better project management!" Include a call-to-action (CTA) button "Learn More" that directs users to a detailed guide or tutorial.

Task created experience

For users with a next best action of "time_entry_logged":

Create an experience with a pop-up modal that appears when the user logs time. The modal should have a message like "Maximize your productivity! Integrate your calendar and track your time seamlessly." Include a CTA button "Get Started" leading to the integration setup page.

Time entry logged experience

For users with a next best action of "message_sent":

Develop a sidebar notification that highlights new collaboration tools. Use text such as "Enhance your team's communication with our new real-time document editing and video conferencing features." Add a CTA button "Try Now" that takes users to the feature setup page.

Message sent experience

Configure targeting:

Use the segments created from the NBA model as the targeting criteria.

Assign the relevant experiences to each segment:

Segment: NBA attribute value "task_created" → Experience: Advanced Task Management Features

Assign task_created experience

Segment: NBA attribute value "time_entry_logged" → Experience: Time-Saving Tips and Integrations

Assign time_entry_logged experience

Segment: NBA attribute value "message_sent" → Experience: New Collaboration Tools

Assign message_sent experience

Start personalization:

Review the configured experiences and their targeting settings.

Start the personalization campaign.

Step 4: Monitor and optimize

Analyze results:

Regularly check the performance metrics in the Personalizations analytics section.

Key personalization metrics to monitor:

Unique Views: Number of users who viewed the personalized experience.

Conversions: Number of users who triggered the desired action.

Conversion Percentage: Percentage of users who triggered the desired action.

Lift: Improvement in conversion rate compared to the control group.

Adjust and refine:

Based on the analysis, tweak the segments and experiences to optimize recommendations.

Implement A/B tests to compare different approaches. For example, test different messaging for promoting Task Management features.

Continuously refine the NBA model and personalizations based on user feedback and performance data.

Frequently asked questions. Answered.

It predicts which product feature to highlight for each user as they browse, based on their adoption patterns and preferences. Instead of showing everyone the same generic prompts, each user sees recommendations for the feature they're most likely to adopt next. It's real-time personalization that helps users reach their next product milestone faster.

You'll need at least 21 days of data collection with a minimum of 10,000 average daily events. Your goal event (like "Feature Adoption") should have at least 200 true and 200 false users daily over 30 days. This gives the model enough signal to make accurate predictions about what each user should do next.

Track events related to feature usage. For example, if your product has Task Management, Time Tracking, and Team Collaboration features, you'd track things like "Tasks Created," "Time Entries Logged," and "Messages Sent." These are the actions the model uses to understand adoption patterns and predict next best actions.

Yes. You can filter out users that would skew the results, like people who haven't logged in for the last 30 days. This keeps the model focused on active users whose behavior actually reflects meaningful adoption patterns.

Once the model is running, you create segments based on the NBA attribute value. For example, one segment for users where NBA equals "task_created," another where NBA equals "time_entry_logged," and so on. Each segment groups users by the feature they're most likely to adopt next.

You can get creative here. For users predicted to adopt Task Management, show a banner highlighting advanced task features with a "Learn More" button. For Time Tracking users, display a pop-up modal about calendar integrations. For Team Collaboration users, add a sidebar notification about real-time document editing.

Yes. You can run A/B tests to compare different messaging, designs, or targeting strategies. For example, test two different ways of promoting Task Management features and see which one drives more adoption. Use the results to continuously refine your experiences and get better over time.

Thanks for reading till the end. Here are 3 ways we can help you grow your business:

1

Boost growth with proven growth plays

Explore our Growth Play Library, filled with actionable growth tactics and step-by-step guides to unlock your app's potential.

Check out Growth Play Library
2

Create a free GrowthOS account

Create a free GrowthOS account and get started on the journey to grow your app.

Get started free on GrowthOS
3

Get advice from a Growth expert

Schedule a personalized discovery call with our founder to explore how GrowthOS can help you grow your business.

Subscribe to The Full Stack Marketer Growth Plays

Zero theory or mindset discussions here; just actionable marketing tactics that will grow revenue today.