Data Analytics in the Banking Sector with Emerging Technology: Machine Learning Approaches for Customer Loss Prediction

Öz

With the advancement of technology, the banking sector has experienced significant development and has become highly reliant on data. It has become crucial for banks to assess and utilize the increasing volume of data with the aid of advancing technology. In this article, a dataset belonging to bank customers was evaluated using machine learning methods. The objective was to predict whether the bank would lose a customer based on the given dataset. The methods employed in this study were Random Forest, Decision Tree, Gaussian Naive Bayes, K-Nearest Neighbors, Adaboost and Logistic Regression algorithms respectively. Prior to comparing the models, hyperparameter optimization was applied to ensure obtaining the best possible results and enable a fari comparison among the models. Among the algorithms compared in this study, the Random Forest algorithm yielded superior results. The success rates of the other compared algorithms were determined as follows: K-Nearest Neighhbors, Decision Tree, Adaboost, Gaussian Naiva Bayes and Logistic Regression.

Anahtar Kelimeler

• Bank
• Customer
• Artificial Intelligence
• Tree Algorithms

Gelişen Teknoloji ile Bankacılık Sektöründe Veri Analitiği: Müşteri Kaybı Tahmini İçin Makine Öğrenmesi Yaklaşımları

Öz

Günümüz gelişen teknoloji ile birlikte banka sektörü daha da gelişmiş ve verilerden çokça faydalanır duruma gelmişlerdir. Artan verileri gelişen teknoloji ile birlikte değerlendirmeleri ve kendi faydalarına kullanmaları elzemdir. Bu makalede makine öğrenmesi yöntemleri ile banka müşterilerine ait olan bir veri seti değerlendirilmiştir. Veri seti üzerinde bankanın müşteriyi kayıp edip etmeyeceği tahmin edilmiştir. Bu çalışma kapsamında kullanılan yöntemler sırasıyla Rastgele Orman, Karar Ağacı, Gauss, K-En Yakın Komşu, Adaboost ve Lojistik Regresyon algoritmalarıdır. Modeller karşılaştırılmadan önce en iyi sonuçları alabilmek ve eşit bir karşılaştırma sağlayabilmek için modeller üzerinde hiperparametre optimizasyonu uygulanmıştır. Bu çalışmada Rastgele Orman algoritması karşılaştırılan diğer algoritmalardan daha iyi sonuçlar elde etmiştir. Karşılaştırılan diğer algoritmaların başarı sonuçları ise sırasıyla K-En Yakın Komşu, Karar Ağacı, Adaboost, Gauss ve Lojistik Regresyon şeklinde belirlenmiştir.

Anahtar Kelimeler

• Banka
• Müşteri
• Yapay zeka
• Ağaç Algoritmaları

Kaynakça

1. AL-Najjar, D., Al-Rousan, N., AL-Najjar, H. 2022. Machine Learning to Develop Credit Card Customer Churn Prediction. Journal of Theoretical and Applied Electronic Commerce Research, 17(4): 1529–1542.
2. Amuda, K.A., Adeyemo, A.B. 2020. Customers Churn Prediction in Financial Institution Using Artificial Neural Network. https://arxiv.org/abs/1912.11346
3. Biau, G., Scornet, E. 2016. A random forest guided tour. Test, 25(2): 197–227.
4. Canete-Sifuentes, L., Monroy, R., Medina-Perez, M.A. 2021. A Review and Experimental Comparison of Multivariate Decision Trees. IEEE Access, 9: 110451–110479.
5. Connelly, L. (n.d.). Logistic Regression (Vol. 29, Issue 5).
6. De Caigny, A., Coussement, K., De Bock, K.W. 2018. A new hybrid classification algorithm for customer churn prediction based on logistic regression and decision trees. European Journal of Operational Research, 269(2): 760–772.
7. Deng, Y., Li, D., Yang, L., Tang, J., Zhao, J. 2021. Analysis and prediction of bank user churn based on ensemble learning algorithm. Proceedings of 2021 IEEE International Conference on Power Electronics, Computer Applications, ICPECA 2021, 288–291.
8. Domingos, E., Ojeme, B., Daramola, O. 2021. Experimental analysis of hyperparameters for deep learning‐based churn prediction in the banking sector. Computation, 9(3).

9. Guliyev, H., Yerdelen Tatoğlu, F. 2021. Customer churn analysis in banking sector: Evidence from explainable machine learning models. Journal of Applied Microeconometrics, 1(2), 85–99.
10. Haddadi, S.J., Mohammadi, M.O., Bahrami, M., Khoeini, E., Beygi, M., Khoshkar, M. H. 2022. Customer Churn Prediction in the Iranian Banking Sector. 2022 International Conference on Applied Artificial Intelligence, ICAPAI 2022.
11. Karvana, K.G.M., Yazid, S., Syalim, A., Mursanto, P. 2019. Customer churn analysis and prediction using data mining models in banking industry. In 2019 international workshop on big data and information security (IWBIS) pp. 33-38. IEEE.
12. Kaur, I., Kaur, J. 2020. Customer churn analysis and prediction in banking industry using machine learning. PDGC 2020 - 2020 6th International Conference on Parallel, Distributed and Grid Computing, 434–437.
13. Keramati, A., Ghaneei, H., Mirmohammadi, S.M. 2016. Developing a prediction model for customer churn from electronic banking services using data mining. Financial Innovation, 2(1).
14. Kim, S., Shin, K.S., Park, K. 2005. An Application of Support Vector Machines for Customer Churn Analysis: Credit Card Case. In LNCS (Vol. 3611).
15. Rahman, M., Kumar, V. 2020. Machine Learning Based Customer Churn Prediction in Banking. Proceedings of the 4th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2020, 1196–1201.
16. Schulz, E., Speekenbrink, M., Krause, A. 2018. A tutorial on Gaussian process regression: Modelling, exploring, and exploiting functions. Journal of Mathematical Psychology, 85, 1–16.
17. Zaky, A., Ouf, S., Roushdy, M. 2022. Predicting Banking Customer Churn based on Artificial Neural Network. 5th International Conference on Computing and Informatics, ICCI 2022, 132–139.
18. Zhang, S., Cheng, D., Deng, Z., Zong, M., Deng, X. 2018. A novel kNN algorithm with data-driven k parameter computation. Pattern Recognition Letters, 109, 44–54.