Abstract: In some embodiments, a computing system extrapolates aggregated interaction data associated with users of an online platform by applying a mixed granularity model to generate extrapolated interaction data for each user in the users. The aggregated interaction data includes a total number of occurrences of a target action performed by the users with respect to the online platform. The extrapolated data includes a series of actions leading to the target action for each user. The computing system identifies an impact of each action in the series of actions for each user on leading to the target action based, at least in part, upon the extrapolating a series of actions associated with the user. User interfaces presented on the online platform can be modified based on at least the identified impacts to improve customization of the user interfaces to the users or enhance an experience of the users.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating a modified analytics prediction machine learning model using an iterative transfer learning approach. For example, the disclosed systems generate an initial version of an analytics prediction machine learning model for predicting an analytics metric according to learned parameters. In some embodiments, the disclosed systems determine expected data channel contributions for the analytics metric according to prior data. Additionally, in some cases, the disclosed systems generate a modified analytics prediction machine learning model by iteratively updating model parameters such that predicted data channel contributions are within a threshold similarity of expected data channel contributions.

Abstract: In some embodiments, a computing system generates de-biased training data for fairness-aware predictive models to facilitate online resource access. The computing system extracts latent features from training data of a first machine learning model for predicting an access flag for a user indicating the ability of the user to access an online environment. Based on the latent features, the computing system trains a second machine learning model to generate de-biased training data by applying a loss function that includes loss terms associated with an individual bias and a group bias of the training data. The de-biased training data are utilized to train the first machine learning model and to update the access flag for the user by applying the first machine learning model to attributes of the user. A user device associated with the user can be provided with access to the online environment according to the updated access flag.