Multi-modal Embedding Fusion-based Recommender
This work addresses the need for flexible and high-performing recommendation systems in e-commerce and other domains, though it appears incremental as it builds on existing multi-modal fusion concepts.
The authors tackled the problem of recommendation systems by developing a multi-modal fusion platform that supports various interaction data and metadata types, achieving significant performance improvements over state-of-the-art methods on open datasets.
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.