Recommendations in a Multi-Domain Setting: Adapting for Customization, Scalability and Real-Time Performance

TL;DR

This paper discusses building a real-time, multi-domain recommender system that integrates various algorithms and neural approaches, demonstrated through job marketplace and startup recommendation use-cases.

Contribution

It introduces a scalable, adaptable system architecture capable of serving diverse domains with real-time recommendations, combining multiple recommendation techniques.

Findings

Effective multi-domain recommendation architecture demonstrated

Real-world use-cases validate system applicability

Integration of traditional and neural recommendation methods

Abstract

In this industry talk at ECIR'2022, we illustrate how to build a modern recommender system that can serve recommendations in real-time for a diverse set of application domains. Specifically, we present our system architecture that utilizes popular recommendation algorithms from the literature such as Collaborative Filtering, Content-based Filtering as well as various neural embedding approaches (e.g., Doc2Vec, Autoencoders, etc.). We showcase the applicability of our system architecture using two real-world use-cases, namely providing recommendations for the domains of (i) job marketplaces, and (ii) entrepreneurial start-up founding. We strongly believe that our experiences from both research- and industry-oriented settings should be of interest for practitioners in the field of real-time multi-domain recommender systems.