Designing Multi-Modal Embedding Fusion-Based Recommender

Electronics

Sylwia Sysko-Romańczuk¹  Andrzej Michałowski²  Michał Daniluk²  Anna Wróblewska²  Jacek Dąbrowski²  Barbara Rychalska²  Mikołaj Wieczorek²  Michał Pastuszak² 

[1] Faculty of Management, Warsaw University of Technology, Narbutta 85, 02-524 Warsaw, Poland;Synerise S.A., Giełdowa 1, 01-211 Warsaw, Poland;

关键词: recommendations;    machine learning;    deep learning;    multi-modal representation;    data representation;    embeddings;   

DOI  :  10.3390/electronics11091391

来源: DOAJ

【 摘 要 】

Recommendation systems have lately been popularised globally. However, often they need to be adapted to particular data and the use case. We have developed a machine learning-based recommendation system, which can be easily applied to almost any items and/or actions domain. Contrary to existing recommendation systems, our system supports multiple types of interaction data with various modalities of metadata through a multi-modal fusion of different data representations. We deployed the system into numerous e-commerce stores, e.g., food and beverages, shoes, fashion items, and telecom operators. We present our system and its main algorithms for data representations and multi-modal fusion. We show benchmark results on open datasets that outperform the state-of-the-art prior work. We also demonstrate use cases for different e-commerce sites.

【 授权许可】

Unknown