Reusable Self-Attention Recommender Systems in Fashion Industry Applications

TL;DR

This paper presents a reusable self-attention recommender system tailored for the fashion industry, demonstrating real-world improvements in user retention and addressing limitations of previous offline-only studies.

Contribution

It introduces a configurable, multi-use recommender system incorporating heterogeneous side information, validated through live experiments in fashion applications.

Findings

User retention improved by up to 30%

System effectively handles multiple fashion recommendation tasks

Addresses gap between offline studies and real-world applications

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. Moreover, many of them do not consider side information such as item and customer metadata although deep-learning recommenders live up to their full potential only when numerous features of heterogeneous type are included. Also, normally the model is used only for a single use case. Due to these shortcomings, even if relevant, previous works are not always representative of their actual effectiveness in real-world industry applications. In this talk, we contribute to bridging this gap by presenting live experimental results demonstrating improvements in user retention of up to 30\%. Moreover, we share our learnings and challenges from building a re-usable and configurable recommender system for various applications from the fashion industry. In particular, we focus on fashion inspiration use-cases, such as outfit ranking, outfit recommendation and real-time personalized outfit generation.