Customer Churn Prediction in Neobanking System Using Predictive Analytics and Feature Selection
Article Sidebar
Main Article Content
Abstract
Context: Customer behavior, including loyalty and satisfaction, is increasingly volatile due to rapid technological and market changes. Neobank startups, in particular, face significant challenges related to customer churn, which can severely impact profitability and reputation. Objective: To develop a predictive model that identifies customers at risk of churning in the neobanking sector, enabling proactive retention strategies. Method: This study employed data mining techniques using three classification algorithms, Logistic Regression, Naïve Bayes, and Decision Tree, implemented in the WEKA platform. Feature selection methods based on accuracy, precision, and correlation were applied to identify key churn indicators. Results: The Decision Tree algorithm outperformed the others, achieving an accuracy of 80.5%. It demonstrated superior performance, particularly when all features were included in the model. Key predictive features were successfully identified through feature selection techniques. Conclusions: The findings confirm that Decision Trees are effective in predicting customer churn in neobanks. Understanding and targeting the key factors influencing churn can help neobanks retain customers and maintain a competitive edge.
Article Details
Issue
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles published in SyCom are open access and distributed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0).
How to Cite
References
[1] Y. Huang, L. Li, “Naïve Bayes Classification Algorithm Based on Small Sample Set”. In Proc. IEEE CCIS 2011 – International Conference on Cloud Computing and Intelligent Systems,, Beijing, China, Sept. 15–17, 2011
[2] M. Bogaert, L. Delaere, “Ensemble Methods in Customer Churn Prediction: A Comparative Analysis of the State-of-the-Art”. Mathematics, 11, 1137, 2023. https://doi.org/10.3390/math11051137
[3] G. Buchi, M. Cugno, A. Zerbetto, R. Castagnoli, “New Banks in the 4th Industrial Revolution: A Review and Typology“. Proceedings of 22nd Excellence in Services International Conference. Thessaloniki, Greece, Aug. 29–30, 2019, pp. 47–63. Available: https://sites.les.univr.it/eisic/wp-content/uploads/2019/11/6-Buchi-Fasolo-Cugno-Zerbetto-Castagnoli-2.pdf
[4] Chih-Fong Tsai & Yu-Hsin Lu, “Customers churn prediction by hybrid neural networks”. Expert Systems with Applications, 36, 12547–12553, 2009. http://dx.doi.org/10.1016/j.eswa.2009.05.032
[5] J. Fu and M. Mishra, “Combatting fraudulent and predatory fintech apps with machine learning,” Proceedings of the 2023 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA, Dec. 2023, pp. 1234–1242.
[6] B. Huang, M. T. Kechadi, B. Buckley, “Customer churn prediction in telecommunications”. Expert Systems with Applications, 39(1), 1414–1425, 2012.
[7] IBM Corporation, “Working with telecommunications”, Minimizing churn in the telecommunications industry, 2010, United States of America.
[8] L. Jie, Xu, Xu “A novel model for global customer retention using data mining technology, data mining and knowledge discovery in real life applications”, Julio Ponce and Adem Karahoca (eds.), 438, I-Tech, 2009, Vienna, Austria.
[9] T. Kolajo, A. B. Adeyemo, “Data mining technique for predicting telecommunications industry customer churn using both descriptive and predictive algorithms”. Computing Information Systems & Development Informatics Journal, 3(2), 27–34, 2012.
[10] I. Ullah, B. Raza, A. K. Malik, M. Imran, S. U. Islam, S. W. Kim, “A churn prediction model using random forest: analysis of machine learning techniques for churn prediction and factor identification in telecom sector”. IEEE Access, 7, 60134–60149, 2019.
[11] A.V. Komarov, V.M. Martyukova, “Neobanking As A Direction Of Development Of Modern Financial Technologies”. Vestnik Universiteta, (3):134–142, 2020. https://doi.org/10.26425/1816-4277-2020-3-134-142
[12] I. Martinčević, S. Črnjević, I. Klopotan, “Novelties and Benefits of Fintech in the Financial Industry”. International Journal of E-services and Mobile Applications, 14(1), 1–25, 2022. https://doi.org/10.4018/ijesma.2022010107
[13] E. O. Oyatoye, S. O. Adebiyi, B. B. Amole, “Modeling switching behaviour of Nigeria global system for mobile communica-tion multiple SIMs Subscribers` using Markov chain analysis”. Journal of Operations Management, 14(1), 7–31, 2020.
[14] N. B. Syam, J. D. Hess, “Acquisition versus retention: competitive customer relationship management”, Working Paper, University of Houston, Houston, Texas, 2006, USA.
[15] T. Xu, “Telecom Churn Prediction System Based on Ensemble Learning Using Feature Grouping”. Applied Sciences, 2021, 11, 4742. https://doi.org/10.3390/app11114742
[16] R. Saxena, “Introduction to k Nearest Neighbor Classification and Condensed Nearest Neighbour Data Reduction”. Data Science, Machine Learning Journal, blog post, December 23, 2016.
[17] S. B. Kotsiantis, “Feature selection for machine learning classification problems: a recent overview”. Artificial Intelligence Review, 42, 157 (2014). https://doi.org/10.1007/s10462-011-9230-1
[18] S. Portela, R. Menezes, “Detecting customer defections: an application of continuous duration models”. Journal of Global Strategic Management, 9, 22–30, 2011. http://dx.doi.org/10.20460/jgsm.2011515809
[19] Z. Lei and G. Junfeng, “Customer Classification of Discrete Data Concerning Customer Assets Based on Data Mining”. Int. Conf. Intell. Transp. Big Data Smart City, pp. 352–355, 2019.
[20] OECD, Digital Disruption in Banking and its Impact on Competition, 2020. http://www.oecd.org/daf/competition/digital-disruption-in-financial-markets.htm
[21] P. P. Singh, F. I. Anik, R. Senapati, A. Sinha, N. Sakib, E. Hossain, “Investigating customer churn in banking: A machine learning approach and visualization app for data science and management”. Data Science and Management, 7 (2024) 7–16. https://doi.org/10.1016/j.dsm.2023.09.002