Intuit, Inc.

Prateek Anand

Qingbo Hu

Apurva Swarnakar

Systems and methods for assessment of user price sensitivity using a predictive model are disclosed. An example method may be performed by one or more processors of a retention system and include retrieving traversal sequences including lists of pages users accessed prior to price notifications, labeling the traversal sequences based on whether users terminated sessions upon the notifications, transforming the traversal sequences into graphs based on identifiers assigned to the pages and instances in which users successively accessed pages, defining predictive features suggesting an extent to which identified structural attributes of given graphs affect user price sensitivity, generating model training data based on the labeled traversal sequences and predictive features, determining optimal weights for the predictive features, and generating a model incorporating the optimal weights and trained to predict a likelihood that a user will terminate a session when notified of a price to continue given the user's traversal sequence.

Assessment of user price sensitivity

Certain aspects of the present disclosure provide techniques for training and using predictive models to predict the occurrence of an event within a software application. An example method generally generating a spatially sampled data set for a set of users of a software application. The spatially sampled data set includes, for each respective user of the set of users, an amount of time the user has spent, a number of discrete portions of the software application the user has visited, and an indication of whether the user has completed a defined task. A spatio-temporally sampled data set for users in the spatially sampled data set is generated, including, for each respective user in the spatially sampled data set, a plurality of candidate timestamps. A predictive model is trained based on the spatio-temporally sampled data set.

Growing community of inventors

San Diego, CA, United States of America

Prateek Anand