Modeling the number of clothing merchandise returned through online shopping using a mixture of Poisson distribution: an interdisciplinary approach

Abstract

Background: Online shopping has witnessed a significant surge in popularity owing to its accessibility and convenience. The rise of online shopping has revolutionized the retail industry, with clothing purchases garnering a dedicated following. However, a persistent challenge in internet purchasing lies in the uncertainty surrounding the fit, appearance, and quality of clothing merchandise. As a result, customers often resort to returning items that fail to meet their expectations or differ from the website's descriptions. In this study, we aim to address this issue by proposing a novel approach to model the number of items returned through online purchases. Specifically, we employ a mixture of Poisson distribution to capture the complexities of the return process and its underlying factors.

Methods: A mixture of Poisson distribution is employed to model the uncertainties in online clothing returns. The approach aims to capture the complexities of the return process and its underlying factors, providing valuable insights for e-commerce businesses to optimize operations and enhance customer satisfaction.  

Results: The findings of this study have the potential to shed light on the reasons behind increased return rates, offering e-commerce businesses valuable information to optimize their operations and enhance customer satisfaction.

Conclusions: Poisson distribution is capable of analyzing the hidden patterns in the data, and hence the results of the study are beneficial for various stakeholders, including statisticians, e-commerce firms, and app developers.