Skip to content
Fast Company Executive Board

The Fast Company Executive Board is a private, fee-based network of influential leaders, experts, executives, and entrepreneurs who share their insights with our audience.

Leveraging user feedback to personalize experience for digital applications

User feedback is essential to uncovering user needs and improving products. However, user feedback without context on the user is not very helpful.

Girl on a phone

[Images: insta_photos/Adobe Stock]

Profile photo of Harish Srigiriaju

User feedback is essential to uncovering user needs and improving products. However, user feedback without context on the user is not very helpful. This context can be in the form of demographics, engagement patterns, plan type, channel, or similar. When this context is combined with user feedback, robust analytical models can be developed to understand more about the users.   

Personalization is key to driving user satisfaction and engagement for digital products. Personalization is a guiding principle to alter content, design, or features to cater to the needs and taste of each individual user. Although products are standardized to achieve scale, without personalization, users will not be interested in spending time on the application. Personalizing products is no longer just a delight to the user—it is an essential requirement in today’s world.

There are various ways to achieve personalization that include rule-based algorithms and artificial intelligence. Leveraging user feedback to segment the user and nudge users toward relevant features or content is a unique approach to personalization.

User feedback can be collected in the form of in-app ratings and reviews. These ratings are collected when users are actively using the application and are different from the ratings on the app stores. They can be at feature level or at app level.

With feature-level ratings and engagement data, one can determine which features are most relevant to the users. Features that receive high satisfaction scores, but are not used enough, can be surfaced to the user to drive engagement. 

With app-level ratings, correlations can be drawn between engagement and satisfaction. Oftentimes, it is assumed that higher engagement leads to retention of the users. But this might not always hold true; therefore, rich data from in-app ratings can validate this key assumption.

Another essential advantage for collecting in-app ratings is the ability to predict churn or deactivations in an application. If in-app ratings are collected at regular intervals, predictive models can be developed to identify which users are likely to deactivate within a particular time frame. This information can be very powerful as unsatisfied users identified from the ratings can be offered discounts or extended trial periods to retain them even before they decide to leave.

Based on the historical churn, critical periods in which users tend to deactivate can be identified. For instance, if most unsatisfied users tend to deactivate after two weeks of activation, discounts can be offered just before the two-week period to get them to stay longer. 

The ultimate objective of product managers is to increase the revenue from satisfied/loyal users and reduce churn. Both of these objectives can be achieved by first segmenting the users based on feedback, then personalizing the features, design, content, and promotions based on the segments. Collecting in-app ratings is a simple but effective approach that can be applied to any digital product.

Furthermore, feature ratings can be used to rank features and personalize the home screen where users tend to spend time. Product managers can start implementing such personalization models through simple, rule-based methods, and further automate over time. To automate personalization, artificial intelligence models can be deployed to segment the users and then features can be ranked or designs can be tweaked for each of those segments to drive user satisfaction over time. 


Harish Srigiriaju is a Distinguished Engineer at Verizon. He has expertise in advanced analytics and technical product management.