Abstract: An A/B testing system is adapted to include a user correlation engine and an A/B test exposure module. The A/B testing system includes an A/B test server that provides at least one A/B test to users of a product and collects and analyzes results of the A/B test(s) to determine an outcome. The user correlation engine clusters the users into behavioral clusters based on an activity level of the users with the product. The behavioral clusters include at least high engagement users and lower engagement users. The results of the A/B test(s) for the high and lower engagement users are correlated to identify correlations between at least one high engagement user and at least one lower engagement user. The A/B test exposure module allocates the A/B test exposures to at least the high engagement users based on the identified correlations to optimize the A/B test exposures across the A/B test(s).

Abstract: A system analyzes user activity data generated by computing devices associated with a plurality of users in a messaging system to extract a random user from the plurality of users. Based on determining that user activity data associated with the random user comprises a consistent pattern, a cluster associated with the consistent pattern is generated and the random user is added to the cluster. Then user activity data for the other users in the plurality of users is analyzed to determine whether user activity data for each of the other users comprises a similar pattern as the generated cluster. Each user that is determined to be associated with user activity data comprising a similar pattern as the consistent pattern of the generated cluster is added to the generated cluster and user activity data associated with each user added to the generated cluster is removed from the user activity data.

Abstract: A system analyzes user activity data generated by computing devices associated with a plurality of users in a messaging system to extract a random user from the plurality of users. Based on determining that user activity data associated with the random user comprises a consistent pattern, a cluster associated with the consistent pattern is generated and the random user is added to the cluster. Then user activity data for the other users in the plurality of users is analyzed to determine whether user activity data for each of the other users comprises a similar pattern as the generated cluster. Each user that is determined to be associated with user activity data comprising a similar pattern as the consistent pattern of the generated cluster is added to the generated cluster and user activity data associated with each user added to the generated cluster is removed from the user activity data.