A Study on the Transportation Industry Customer Churn using Machine Learning: A Systematic Literature Review

Abstract

Machine Learning (ML) has become a crucial technology for addressing customer churn by enabling businesses to predict customer attrition, identify at-risk customers, and develop proactive retention strategies. Although the application of ML in customer churn management has gained momentum, existing research remains scattered across different disciplines and publication outlets. This study conducts a systematic literature review to consolidate and synthesize the fragmented knowledge in the transportation sector on the use of ML in customer churn prediction and prevention. The review examines peer-reviewed publications from the ranked journals between 2019 and 2024. The search strategy identified 67 studies, of which 34 were selected as primary papers relevant to this research. The findings contribute to the literature by (i) assessing the current state of ML applications in customer churn, (ii) identifying key ML techniques employed across different stages of customer churn management (prediction, prevention, and intervention), and (iii) summarizing the reported benefits of ML in reducing customer attrition and improving retention outcomes. This study offers valuable insights for both researchers and practitioners aiming to leverage ML technologies to mitigate customer churn and enhance customer loyalty.