Reusable Self-Attention-based Recommender System for Fashion

TL;DR

This paper introduces AFRA, a reusable self-attention-based recommender system for fashion that incorporates diverse features and temporal context, demonstrating improved customer engagement in real-world scenarios.

Contribution

The paper presents a novel, reusable attention-based algorithm for fashion recommendation that integrates heterogeneous features and temporal data for multiple use cases.

Findings

Significant improvements in customer retention and engagement.

Effective in multiple fashion recommendation scenarios.

Validated through offline and online experiments.

Abstract

A large number of empirical studies on applying self-attention models in the domain of recommender systems are based on offline evaluation and metrics computed on standardized datasets, without insights on how these models perform in real life scenarios. Moreover, many of them do not consider information such as item and customer metadata, although deep-learning recommenders live up to their full potential only when numerous features of heterogeneous types are included. Also, typically recommendation models are designed to serve well only a single use case, which increases modeling complexity and maintenance costs, and may lead to inconsistent customer experience. In this work, we present a reusable Attention-based Fashion Recommendation Algorithm (AFRA), that utilizes various interaction types with different fashion entities such as items (e.g., shirt), outfits and influencers, and their heterogeneous features. Moreover, we leverage temporal and contextual information to address both short and long-term customer preferences. We show its effectiveness on outfit recommendation use cases, in particular: 1) personalized ranked feed; 2) outfit recommendations by style; 3) similar item recommendation and 4) in-session recommendations inspired by most recent customer actions. We present both offline and online experimental results demonstrating substantial improvements in customer retention and engagement.