Incorporating Heterogeneous User Behaviors and Social Influences for Predictive Analysis

TL;DR

This paper introduces a novel predictive model that integrates heterogeneous user behaviors and social influences using advanced neural network components, improving behavior prediction accuracy in real-world applications.

Contribution

It proposes a new LSTM variant, a multi-faceted attention mechanism, and a social influence modeling approach for enhanced behavior prediction.

Findings

Model outperforms existing methods on real-world datasets.

Effectively captures multi-type behaviors and social influences.

Improves prediction accuracy and interpretability.

Abstract

Behavior prediction based on historical behavioral data have practical real-world significance. It has been applied in recommendation, predicting academic performance, etc. With the refinement of user data description, the development of new functions, and the fusion of multiple data sources, heterogeneous behavioral data which contain multiple types of behaviors become more and more common. In this paper, we aim to incorporate heterogeneous user behaviors and social influences for behavior predictions. To this end, this paper proposes a variant of Long-Short Term Memory (LSTM) which can consider context information while modeling a behavior sequence, a projection mechanism which can model multi-faceted relationships among different types of behaviors, and a multi-faceted attention mechanism which can dynamically find out informative periods from different facets. Many kinds of behavioral data belong to spatio-temporal data. An unsupervised way to construct a social behavior graph based on spatio-temporal data and to model social influences is proposed. Moreover, a residual learning-based decoder is designed to automatically construct multiple high-order cross features based on social behavior representation and other types of behavior representations. Qualitative and quantitative experiments on real-world datasets have demonstrated the effectiveness of this model.