Context-Aware Sequential Model for Multi-Behaviour Recommendation

TL;DR

CASM is a novel context-aware sequential model that effectively captures multiple user behaviors in recommendation systems, outperforming existing methods by leveraging multi-head self-attention and weighted loss functions.

Contribution

Introduces CASM, a multi-behavior recommendation model using context-aware self-attention and weighted loss to improve sequential behavior modeling.

Findings

CASM outperforms state-of-the-art models on four datasets.

Effectively models multiple user behaviors simultaneously.

Uses weighted binary cross-entropy for behavior contribution control.

Abstract

Sequential recommendation models are crucial for next-item recommendations in online platforms, capturing complex patterns in user interactions. However, many focus on a single behavior, overlooking valuable implicit interactions like clicks and favorites. Existing multi-behavioral models often fail to simultaneously capture sequential patterns. We propose CASM, a Context-Aware Sequential Model, leveraging sequential models to seamlessly handle multiple behaviors. CASM employs context-aware multi-head self-attention for heterogeneous historical interactions and a weighted binary cross-entropy loss for precise control over behavior contributions. Experimental results on four datasets demonstrate CASM's superiority over state-of-the-art approaches.