Evaluating user segments for predicting Customer Lifetime Value

• Victória C. S. Rodrigues UFV
• João M. Ramos UFV / Manna Team
• Fabrício A. Silva UFV / Manna Team
• Linnyer B. R. Aylon UEM / Manna Team

DOI: https://doi.org/10.5753/eniac.2024.245073

Abstract

The Customer Lifetime Value (CLV) is fundamental to business operations, offering a comprehensive understanding of customer value over time. This study aims to evaluate the impact of customer segmentation on CLV prediction, using machine learning models established in the literature to estimate the number of transactions and the average monetary value across three distinct datasets. A comparative analysis was conducted on the values related to the number of transactions and the average monetary value in two different scenarios: one where the model is trained exclusively with the characteristics of each segment and another where it is trained with all the data. The results reveal that customer segmentation can improve prediction accuracy, and the choice between segmenting customers and training with all data should be based on the specific characteristics and nature of the dataset.

Keywords: CLV, LTV, Machine Learning

References

Online Retail. UCI Machine Learning Repository, 2015. DOI: 10.24432/C5BW33.

AutoresOmitidosparaRevisão. Título Omitido para Revisão. In Local de Publicação Omitido para Revisão.

Daqing Chen. Online Retail II. UCI Machine Learning Repository, 2019. DOI: 10.24432/C5CG6D.

Xinqian Dai. Customer lifetime value analysis based on machine learning. In Proceedings of the 6th International Conference on Information System and Data Mining, ICISDM ’22, page 13–17, New York, NY, USA, 2022. Association for Computing Machinery. ISBN 9781450396257. DOI: 10.1145/3546157.3546160.

Peter S Fader, Bruce GS Hardie, and Ka Lok Lee. Rfm and clv: Using iso-value curves for customer base analysis. Journal of marketing research, 42(4):415–430, 2005.

Philip Hans Franses. A note on the mean absolute scaled error. International Journal of Forecasting, 32(1):20–22, 2016. ISSN 0169-2070. DOI: 10.1016/j.ijforecast.2015.03.008. URL [link].

Ankit Kumar, K. Singh, Gaurav Kumar, Tanupriya Choudhury, and K. Kotecha. Customer lifetime value prediction: Using machine learning to forecast clv and enhance customer relationship management. 2023 7th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), pages 1–7, 2023. DOI: 10.1109/ISMSIT58785.2023.10304958.

Edward Malthouse and Frank Mulhern. Understanding and using customer loyalty and customer value. Journal of Relationship Marketing, 6(3-4):59–86, 2008.

Ina Maryani and Dwiza Riana. Clustering and profiling of customers using rfm for customer relationship management recommendations. In 2017 5th International Conference on Cyber and IT Service Management (CITSM), pages 1–6. IEEE, 2017.

Roland T Rust, Valarie Zeithaml, and Katherine N Lemon. O valor do cliente: o modelo que está reformulando a estratégia corporativa. Bookman, 2001.

Adrian Sargeant. Using donor lifetime value to inform fundraising strategy. Nonprofit Management and Leadership, 12(1):25–38, 2001.

Arun Sharma. The metrics of relationships: measuring satisfaction, loyalty and profitability of relational customers. Journal of Relationship Marketing, 6(2):33–50, 2007.

Raphael Albuquerque Xavier SILVA. Estudo de caso sobre aplicações de modelos clássicos de previsão de demanda para uma empresa de delivery de alimentos. B.S. thesis, 2023.

Yuechi Sun, Haiyan Liu, and Yu Gao. Research on customer lifetime value based on machine learning algorithms and customer relationship management analysis model. Heliyon, 9(2), 2023.

B V Vishwas and Ashish Patel. Hands-on Time Series Analysis with Python: From Basics to Bleeding Edge Techniques. Apress, 2020.