Yang-Ruei Jheng

Yang-Ruei Jheng

Auto-generated profile, based on publicly available information

Yang-Ruei Jheng

National Central University, Taoyuan City, Taiwan

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2026 in Sage Open
Verified
Journal Article
Open access
NXNi Xu
Ni Xu
YJYang-Ruei Jheng
Yang-Ruei Jheng
PHPing-Yu Hsu
Ping-Yu Hsu
YKYen-Huei Ko
Yen-Huei Ko
YHYi-Hsin Hsieh
Yi-Hsin Hsieh
The Dietary Supplements industry has experienced massive growth worldwide—a trend that is expected to continue. Numerous dietary supplements are sold through telemarketing. To increase the effectiveness of telemarketing operations, agents are encouraged to contact customers who are likely to (re)purchase them. Trust and loyalty are key determinants of customers’ repurchasing intentions in the e-commerce literature. In theory, agents should contact customers who are both loyal and trust the agents. However, collecting statistical surveys to measure customers’ cognition requires considerable effort, if not entirely impractical. Given its importance, measuring loyalty based on transaction data has been proposed as R(ecency), F(requency), and M(onetary) value in prior works. Trust, although a critical driver of various customer behaviors, lacks consistent measurement tools based on data-driven approaches. To fill this gap, this study strives to define formulas based on four key dimensions of trust: benevolence, integrity, competence, and predictability. To demonstrate their applicability, transaction and call logs from one of Taiwan’s leading nutrition supplement companies were used to calculate related trust scores. These scores, along with RFM, were encoded as customer features and input into a Long Short-Term Memory (LSTM) model to estimate repurchase likelihood in the following 6 months. The model achieves an accuracy of 85%. The importance of the proposed features is evaluated with Random Forest. The results indicate that Monetary value, Integrity, Recency, and Competency are the four most influential features predicting customer behavior.