Sequence-Aware Factorization Machines for Temporal Predictive Analytics

TL;DR

This paper introduces SeqFM, a novel sequence-aware factorization machine that models temporal dependencies in dynamic features, significantly improving predictive performance in web applications like advertising and recommendations.

Contribution

SeqFM innovatively incorporates a multi-view self-attention mechanism to separately model static, dynamic, and their mutual features, enhancing FM-based models for temporal data.

Findings

SeqFM outperforms existing models in ranking, classification, and regression tasks.

Experimental results show superior effectiveness and efficiency on large-scale datasets.

SeqFM effectively captures sequential dependencies, improving predictive accuracy.

Abstract

In various web applications like targeted advertising and recommender systems, the available categorical features (e.g., product type) are often of great importance but sparse. As a widely adopted solution, models based on Factorization Machines (FMs) are capable of modelling high-order interactions among features for effective sparse predictive analytics. As the volume of web-scale data grows exponentially over time, sparse predictive analytics inevitably involves dynamic and sequential features. However, existing FM-based models assume no temporal orders in the data, and are unable to capture the sequential dependencies or patterns within the dynamic features, impeding the performance and adaptivity of these methods. Hence, in this paper, we propose a novel Sequence-Aware Factorization Machine (SeqFM) for temporal predictive analytics, which models feature interactions by fully investigating the effect of sequential dependencies. As static features (e.g., user gender) and dynamic features (e.g., user interacted items) express different semantics, we innovatively devise a multi-view self-attention scheme that separately models the effect of static features, dynamic features and the mutual interactions between static and dynamic features in three different views. In SeqFM, we further map the learned representations of feature interactions to the desired output with a shared residual network. To showcase the versatility and generalizability of SeqFM, we test SeqFM in three popular application scenarios for FM-based models, namely ranking, classification and regression tasks. Extensive experimental results on six large-scale datasets demonstrate the superior effectiveness and efficiency of SeqFM.