# Towards Neural Mixture Recommender for Long Range Dependent User Sequences

## TL;DR

This paper introduces a neural mixture model that adaptively combines short-term and long-term dependency models for improved sequential recommendation accuracy across diverse user behaviors.

## Contribution

The paper proposes the Multi-temporal-range Mixture Model (M3), which dynamically integrates models for different temporal ranges using a learned gating mechanism, enhancing recommendation performance.

## Key findings

- M3 outperforms existing methods on public and YouTube datasets.
- Long-range dependence coexists with short-term patterns in user sequences.
- Adaptive mixture modeling improves recommendation accuracy.

## Abstract

Understanding temporal dynamics has proved to be highly valuable for accurate recommendation. Sequential recommenders have been successful in modeling the dynamics of users and items over time. However, while different model architectures excel at capturing various temporal ranges or dynamics, distinct application contexts require adapting to diverse behaviors. In this paper we examine how to build a model that can make use of different temporal ranges and dynamics depending on the request context. We begin with the analysis of an anonymized Youtube dataset comprising millions of user sequences. We quantify the degree of long-range dependence in these sequences and demonstrate that both short-term and long-term dependent behavioral patterns co-exist. We then propose a neural Multi-temporal-range Mixture Model (M3) as a tailored solution to deal with both short-term and long-term dependencies. Our approach employs a mixture of models, each with a different temporal range. These models are combined by a learned gating mechanism capable of exerting different model combinations given different contextual information. In empirical evaluations on a public dataset and our own anonymized YouTube dataset, M3 consistently outperforms state-of-the-art sequential recommendation methods.