TribeFlow: Mining & Predicting User Trajectories

TL;DR

TribeFlow is a versatile, fast, and accurate method for predicting user trajectories across various domains, effectively handling non-stationary and transient user behavior without domain-specific adjustments.

Contribution

It introduces TribeFlow, a novel general approach for modeling and predicting dynamic user trajectories that outperforms existing methods in accuracy and speed.

Findings

More accurate than top competitors

Up to 413x faster in predictions

Effective across multiple domains

Abstract

Which song will Smith listen to next? Which restaurant will Alice go to tomorrow? Which product will John click next? These applications have in common the prediction of user trajectories that are in a constant state of flux over a hidden network (e.g. website links, geographic location). What users are doing now may be unrelated to what they will be doing in an hour from now. Mindful of these challenges we propose TribeFlow, a method designed to cope with the complex challenges of learning personalized predictive models of non-stationary, transient, and time-heterogeneous user trajectories. TribeFlow is a general method that can perform next product recommendation, next song recommendation, next location prediction, and general arbitrary-length user trajectory prediction without domain-specific knowledge. TribeFlow is more accurate and up to 413x faster than top competitors.