Modelling and Analysis of Temporal Preference Drifts Using A Component-Based Factorised Latent Approach

TL;DR

This paper introduces a component-based latent factor model to effectively capture and analyze the domain-specific temporal drifts in user preferences, significantly improving recommendation accuracy and robustness.

Contribution

The paper presents a novel latent factor model that captures domain-dependent component-specific temporal patterns and allows flexible component switching, enhancing recommendation performance.

Findings

Outperforms state-of-the-art static models on three datasets.

Demonstrates greater robustness and stability of the dynamic model.

Highlights the importance of modeling temporal effects and component-based architecture.

Abstract

The changes in user preferences can originate from substantial reasons, like personality shift, or transient and circumstantial ones, like seasonal changes in item popularities. Disregarding these temporal drifts in modelling user preferences can result in unhelpful recommendations. Moreover, different temporal patterns can be associated with various preference domains, and preference components and their combinations. These components comprise preferences over features, preferences over feature values, conditional dependencies between features, socially-influenced preferences, and bias. For example, in the movies domain, the user can change his rating behaviour (bias shift), her preference for genre over language (feature preference shift), or start favouring drama over comedy (feature value preference shift). In this paper, we first propose a novel latent factor model to capture the domain-dependent component-specific temporal patterns in preferences. The component-based approach followed in modelling the aspects of preferences and their temporal effects enables us to arbitrarily switch components on and off. We evaluate the proposed method on three popular recommendation datasets and show that it significantly outperforms the most accurate state-of-the-art static models. The experiments also demonstrate the greater robustness and stability of the proposed dynamic model in comparison with the most successful models to date. We also analyse the temporal behaviour of different preference components and their combinations and show that the dynamic behaviour of preference components is highly dependent on the preference dataset and domain. Therefore, the results also highlight the importance of modelling temporal effects but also underline the advantages of a component-based architecture that is better suited to capture domain-specific balances in the contributions of the aspects.