DisenReason: Behavior Disentanglement and Latent Reasoning for Shared-Account Sequential Recommendation

TL;DR

DisenReason is a novel two-stage method for shared-account sequential recommendation that disentangles behaviors and infers the number of latent users, significantly improving recommendation accuracy over existing methods.

Contribution

It introduces a behavior disentanglement and latent reasoning framework specifically designed for shared-account recommendation, addressing limitations of fixed user assumptions.

Findings

Outperforms state-of-the-art baselines on four datasets

Achieves up to 12.56% improvement in MRR@5

Achieves up to 6.06% improvement in Recall@20

Abstract

Shared-account usage is common on streaming and e-commerce platforms, where multiple users share one account. Existing shared-account sequential recommendation (SSR) methods often assume a fixed number of latent users per account, limiting their ability to adapt to diverse sharing patterns and reducing recommendation accuracy. Recent latent reasoning technique applied in sequential recommendation (SR) generate intermediate embeddings from the user embedding (e.g, last item embedding) to uncover users' potential interests, which inspires us to treat the problem of inferring the number of latent users as generating a series of intermediate embeddings, shifting from inferring preferences behind user to inferring the users behind account. However, the last item cannot be directly used for reasoning in SSR, as it can only represent the behavior of the most recent latent user, rather than the collective behavior of the entire account. To address this, we propose DisenReason, a two-stage reasoning method tailored to SSR. DisenReason combines behavior disentanglement stage from frequency-domain perspective to create a collective and unified account behavior representation, which serves as a pivot for latent user reasoning stage to infer the number of users behind the account. Experiments on four benchmark datasets show that DisenReason consistently outperforms all state-of-the-art baselines across four benchmark datasets, achieving relative improvements of up to 12.56\% in MRR@5 and 6.06\% in Recall@20.