Multi-modal Embedding Fusion-based Recommender

TL;DR

This paper introduces a multi-modal fusion recommendation system that integrates various interaction data types and metadata, demonstrating superior performance across diverse e-commerce domains and benchmark datasets.

Contribution

The paper presents a flexible, multi-modal fusion-based recommendation platform capable of handling diverse data types, outperforming existing methods on multiple datasets.

Findings

Significantly outperforms prior state-of-the-art methods on benchmark datasets.

Successfully deployed across various e-commerce domains, demonstrating versatility.

Supports multiple interaction data types and metadata modalities natively.

Abstract

Recommendation systems have lately been popularized globally, with primary use cases in online interaction systems, with significant focus on e-commerce platforms. We have developed a machine learning-based recommendation platform, which can be easily applied to almost any items and/or actions domain. Contrary to existing recommendation systems, our platform supports multiple types of interaction data with multiple modalities of metadata natively. This is achieved through multi-modal fusion of various data representations. We deployed the platform into multiple e-commerce stores of different kinds, e.g. food and beverages, shoes, fashion items, telecom operators. Here, we present our system, its flexibility and performance. We also show benchmark results on open datasets, that significantly outperform state-of-the-art prior work.