Do personalized economic incentives work in promoting shared mobility? Examining customer churn using a time-varying Cox model

Published in Transportation Research Part C: Emerging Technologies, 2021

Recommended citation: Hu, Songhua, Peng Chen, and Xiaohong Chen. "Do personalized economic incentives work in promoting shared mobility? Examining customer churn using a time-varying Cox model." Transportation Research Part C: Emerging Technologies 128 (2021): 103224. https://www.sciencedirect.com/science/article/abs/pii/S0968090X21002382

Shared mobility options have grown significantly in recent years. However, a major threat to the growing usage of shared-cars is customer churn. Despite companies continually providing rewards to attract customers, factors that contribute to customer churn are not well-understood in the existing literature. This study analyzed one-year transaction data of a one-way carsharing program and applied an extended Cox proportional hazards model to examine these effects. Our results show that: (1) A customer’s retention probability decreased over time with a decelerating rate. (2) Customers were less likely to churn when their frequently-visited shared-car stations were located in neighborhoods with low access to transit or in areas with colleges, railway hubs, or airports. (3) Elderly and male customers had a lower likelihood of churning. (4) The number of coupons was negatively associated with the likelihood of customer churn. (5) The effect of coupons generally increased at first and then decreased after the 130th day. These findings contribute to coupon design and the location choice of shared-car stations. Specifically, we suggest that large-denomination coupons should be split into multiple small-denomination coupons. We encourage companies to locate stations in areas with poor transit access. Meanwhile, coupon issuing strategies can be redeveloped. Offering more coupons to new customers can help maximize the profits of service providers. However, such a strategy is debatable because it invades personal privacy and is unfair for existing loyal customers. Download paper here