Abstract: Systems and methods are provided for dynamic segmentation of users during an experiment based on changes to application data collected during the experiment. Data regarding application interactions and associated application metadata may be collected from users during application experiments that involve testing different variants of a feature or otherwise different user experiences. The data regarding application interactions and associated application metadata may be evaluated to discover segments of users and/or usage patterns (e.g., “cohorts”). During the experiment, the users may be dynamically re-segmented into new/different cohorts based on new application data being collected.

Abstract: Systems and methods are provided for evaluation of application interactions and associated metadata to manage application feature experiments, use of synthetic traffic (“canaries”), and the like. Data regarding application interactions and associated application metadata may be evaluated to identify usage patterns and conditions associated with desired actions, and usage patterns and conditions associated with undesired actions. Identifying such usage patterns and conditions can facilitate prediction of future actions given some set of observed application interactions and application metadata. Such predictions can be leveraged to perform experiments that optimize the occurrence of desired actions, and implement canaries to determine the effect of various user journeys and application data on desired actions.