New Hybrid Techniques for Business Recommender Systems

TL;DR

This paper introduces hybrid recommender system techniques tailored for B2B knowledge-based services, demonstrating significant performance improvements by combining multiple methods evaluated on business consultancy cases.

Contribution

It proposes a novel process for integrating recommender systems into B2B consultancy services and introduces a hybridization strategy that enhances recommendation accuracy.

Findings

Hybrid methods outperform individual techniques.

Hybridization improves recommendation performance.

Context-aware recommender techniques are effective in B2B scenarios.

Abstract

Besides the typical applications of recommender systems in B2C scenarios such as movie or shopping platforms, there is a rising interest in transforming the human-driven advice provided e.g. in consultancy via the use of recommender systems. We explore the special characteristics of such knowledge-based B2B services and propose a process that allows to incorporate recommender systems into them. We suggest and compare several recommender techniques that allow to incorporate the necessary contextual knowledge (e.g. company demographics). These techniques are evaluated in isolation on a test set of business intelligence consultancy cases. We then identify the respective strengths of the different techniques and propose a new hybridisation strategy to combine these strengths. Our results show that the hybridisation leads to a substantial performance improvement over the individual methods.