A hybrid approach to three-way conversational recommendation

Conversational recommendation is ubiquitous in e-commerce, while three-way provides friendly choices for service providers and users. However, their combination has not been studied yet. In this paper, we introduce the conversational problem design hybrid (HTCR) algorithm to address it. First, a new defined by considering man–machine interaction as well misclassification promotion costs. The optimization objective of minimize total cost. Second, popularity-based technique designed user cold-start recommendation, where maturity responsible deciding when HTCR turns second technique. Third, an incremental matrix factorization regular recommendation. It efficient since only few rounds training are needed newly acquired feedback. Experiments were carried out on four well-known datasets, including Jester, MovieLens 100K, 1M Yelp. Results demonstrated that our outperformed state-of-the-art ones terms average