A hybrid approach for predicting customers' individual purchase behavior

Peker S., KOÇYİĞİT A., EREN P. E.

KYBERNETES, vol.46, no.10, pp.1614-1631, 2017 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 46 Issue: 10
  • Publication Date: 2017
  • Doi Number: 10.1108/k-05-2017-0164
  • Journal Name: KYBERNETES
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.1614-1631
  • Keywords: Customer behavior models, Personalization, Machine learning, Customer segmentation, Hybrid approach, Predictive modeling, RECOMMENDER SYSTEMS, CONTEXT
  • Middle East Technical University Affiliated: Yes

Abstract

Purpose - Predicting customers' purchase behaviors is a challenging task. The literature has introduced the individual-level and the segment-based predictive modeling approaches for this purpose. Each method has its own advantages and drawbacks, and performs in certain cases. The purpose of this paper is to propose a hybrid approach which predicts customers' individual purchase behaviors and reduces the limitations of these two methods by combining the advantages of them.