Recommending Software Apps in a B2B Context
Cai-Nicolas Ziegler, Alexandru Oprea, Thomas Hornung, Holger Eggs, Georg Lausen · 2013 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT) · 2013
Recommenders have become integral components of B2C e-commerce over the last ten years. However, there has been little use so far in B2B, in particular in research contexts. We thus present the anatomy of our live hybrid recommender system, which operates in a domain where the users are represented by companies and the products being recommended are B2B apps. Besides operating in an entire new domain, the SAP Store recommender is based on a weighted hybrid design, making use of our confidence-based weighting scheme for combining ratings. Empirical evaluations have shown that our system performs significantly better than a top-seller recommender benchmark.