A deep hybrid learning model for customer repurchase behavior. (March 2021)

• Record Type: Journal Article
• Authors: Kim, Jina; Ji, HongGeun; Oh, Soyoung; Hwang, Syjung; Park, Eunil; del Pobil, Angel P.
• Is Part Of: Journal of retailing and consumer services. Volume 59(2021)
• Publication Date: 2021-03
• Subjects: Deep learning -- Smartphone -- Customer repurchase -- Online review; Retail trade -- Periodicals; Service industries -- Periodicals; Customer services -- Periodicals; Commerce de détail -- Périodiques; Service à la clientèle -- Périodiques; Customer services; Retail trade; Periodicals; 658.87
• DOI: 10.1016/j.jretconser.2020.102381
• Languages: English
• ISSNs: 0969-6989

Abstract

Abstract: Smartphones have become an integral part of our daily lives, which has led to the rapid growth of the smartphone market. As the global smartphone market tends to remain stable, retaining existing customers has become a challenge for smartphone manufacturers. This study investigates whether a deep hybrid learning approach with various customer-oriented types of data can be useful in exploring customer repurchase behavior of same-brand smartphones. Considering data from more than 74, 000 customers, the proposed deep learning approach showed a prediction accuracy higher than 90%. Based on the results of deep hybrid learning models, we aim to provide better understanding on customer behavior, such that it could be used as valuable assets for innovating future marketing strategies. Highlights: A deep hybrid-learning approach is employed to address customer repurchase behavior. More than 90% prediction accuracy is achieved. Both practical and academic implications of customer repurchase behavior are presented.