Based on Machine Learning to Predict if the Client Will Subscribe the Term Deposit

Zhenyu Ni

doi:10.54097/snsxay31

Authors

Zhenyu Ni Department of statistic, University of California, Davis, United States

DOI:

https://doi.org/10.54097/snsxay31

Keywords:

Machine learning; Logistic regression; Telemarketing.

Abstract

This paper uses several approaches of machine learning to predict if the customers will buy the term deposit by telemarketing of the bank. The data is collected from the phone calls of a Portuguese banking institution from 2008 to 2012. The paper compared five models: logistic regression, k-nearest-neighbors, support vector machine, decision tree and random forest. The analysis revealed several key insights. The predictive significance of variables like duration, p-days, and previous was confirmed by their important effect on the desired outcome. The result of this study is focused on the accuracy, precision, recall, the F1-score, and the Area Under the Receiver Operating Characteristic (ROC) Curve. The logistic regression method has the best result among all the five models, because it has the highest accuracy and the largest Area Under ROC Curve (AUC). This shows a high level of ability to distinguish if the clients will subscribe to the term deposit. This study will give a valuable reference to the bank for precision marketing to their future customers.

Downloads

Download data is not yet available.

References

[1] Yi F, Yin Y Q, Wang D J, and Dhamotharan L. A dynamic ensemble selection method for bank telemarketing sales prediction. Journal of Business Research 139: 368–82. 2022.

[2] Jiang Y B. Using Logistic Regression Model to Predict the Success of Bank Telemarketing. Journal of data science, 4, 35. 2018.

[3] Devlin J F. Customer knowledge and choice criteria in retail banking. Journal of Strategic Marketing, 10(4), 273–290. 2002. https://doi.org/10.1080/0965254022000014541

[4] Aregbeyen O. The determinants of bank selection choices by customers: Recent and extensive evidence from Nigeria. International journal of business and social science, 2(22), 276-288. 2011.

[5] Singh D K, & Goel N O O P U R. Customer relationship management: Two dataset comparison in perspective of bank loan approval using machine learning techniques. Journal of Theoretical and Applied Information Technology, 101(19). 2023.

[6] Moro S, Cortez P, & Rita P. A data-driven approach to predict the success of bank telemarketing. Decis. Support Syst., 62, 22-31. 2014.

[7] Zhang Z. Introduction to machine learning: k-nearest neighbors. Annals of translational medicine, 4(11), 218. 2016. https://doi.org/10.21037/atm.2016.03.37

[8] Suthaharan, S. Support Vector Machine. In: Machine Learning Models and Algorithms for Big Data Classification. Integrated Series in Information Systems, vol 36. Springer, Boston, MA. 2016. https://doi.org/10.1007/978-1-4899-7641-3_9

[9] Pisner D A, & Schnyer D M. Support vector machine. In Machine learning (pp. 101-121). Academic Press. 2020.

[10] Song Y Y, & Lu Y. Decision tree methods: applications for classification and prediction. Shanghai archives of psychiatry. 2015.

[11] Breiman L. Random forests. Machine learning, 45(1), 5-32. 2001.