Makine Öğrenmesi Teknikleri Kullanılarak Bankalardaki Potansiyel Müşterilerin Sınıflandırılması

Öz

Bu çalışmada, bankalar için telefon görüşmeleri baz alınarak potansiyel müşterilerin sınıflandırılması hedeflenmiştir. Öncelikle problem dikkatli bir şekilde ele alınmış ve bu alandaki literatür taranmıştır. Daha sonrasında daha iyi ve daha hızlı bir çözüm ortaya konması istenmiştir. Bu yüzden bir dizi iyi bilinen sınıflandırma algoritmaları kullanılacak veri setine uygulanmış ve karşılattırmalı bir çalışma gerçekleştirilmiştir. Sonuçlar ışığında en iyi sonucu veren iki model %95,1 ile XGBoost modeli ve %94,6 ile Random Forest modeli olmuştur. Daha sonrasında ise daha iyi sonuçlar alınabilmesi için farklı hiperparametre optimizasyonu yapan metotlar denenmiştir. Ancak Random Forest modelinde çok düşük bir artış gözlemlense de hiperparametre optimizasyonu işlemden sonra çok büyük bir artışı kayıt edilmemiştir.

Anahtar Kelimeler

• Makine öğrenmesi
• banka mevduat hesabı
• sınıflandırma
• hiper parametre optimizasyonu

Classification of Potential Customers in Banks Using Machine Learning Techniques

Öz

In this study, it is aimed to classify potential customers based on phone calls for banks. First of all, the problem was handled carefully and the literature in this field has been investigated. Afterward, it is observed that it is required to come up with a better and faster solution. Therefore, a number of well-known classification algorithms have been applied to the data set and a comparison study has been conducted. In the light of the results, the two models that gave the best results were the XGBoost model with 95.1% and the Random Forest model with 94.6%. Afterwards, different hyperparameter optimization methods were tried to obtain better results. However, although a very low increase was observed in the Random Forest model, a very large increase was not recorded after the hyperparameter optimization process.

Anahtar Kelimeler

• Makine öğrenmesi
• banka mevduat hesabı
• sınıflandırma
• hiper parametre optimizasyonu

Kaynakça

1. Abu-Srhan, A., of, R. A.-S.-I. J., & undefined 2019. (2019). Visualization and Analysis in Bank Direct Marketing Prediction. Pdfs.Semanticscholar.Org, 10(7). https://pdfs.semanticscholar.org/8274/71809c42b759b6433bc2b7875f8e36ec74b8.pdf
2. Alexandra, J., on, K. P. S.-2021 3rd I. C., & undefined 2021. (n.d.). Machine learning approaches for marketing campaign in portuguese banks. Ieeexplore.Ieee.Org. https://ieeexplore.ieee.org/abstract/document/9649623/?casa_token=nLvFZRk4bW8AAAAA:I_Q1mAB_GL9Y-R2huGPaT_D5Vg1u5K1xJIwxHjVWBhwMSwP3C0awAhvejWlouvoszjXoaKaB_eR-_Q
3. Asare-Frempong, J., on …, M. J.-I. C., & undefined 2017. (2017). Predicting customer response to bank direct telemarketing campaign. Ieeexplore.Ieee.Org. https://doi.org/10.1109/ICE2T.2017.8215961
4. Bakır, H., & Bakır, R. (2023). DroidEncoder: Malware detection using auto-encoder based feature extractor and machine learning algorithms. Computers and Electrical Engineering, 110, 108804. Bakır, H., Çayır, A. N., & Navruz, T. S. (2023). A comprehensive experimental study for analyzing the effects of data augmentation techniques on voice classification. Multimedia Tools and Applications, 1–28.
5. Bakır, H., & Elmabruk, K. (2023). Deep learning-based approach for detection of turbulence-induced distortions in free-space optical communication links. Physica Scripta, 98(6), 065521.
6. Bakır, H., Oktay, S., & Tabaru, E. (2023). Detectıon Of Pneumonıa From X-Ray Images Usıng Deep Learnıng Technıques. Journal of Scientific Reports-A, 052, 419–440.
7. Bank Marketing Campaign | Kaggle. (n.d.). https://www.kaggle.com/datasets/edith2021/bank-marketing-campaign?resource=download
8. Bayırbağ, V., & Bakır, H. (2023). Çalışan Yıpranması Tahmin Etmek için Hiper Parametresi Ayarlanmış Makine Öğrenme Algoritmaların Kullanılması. International Conference on Scientific and Academic Research, 1, 466–471.

9. Borugadda, P., Nandru, P., Madhavaiah, C., & Theresa, S. (n.d.). Predicting the success of bank telemarketing for selling long-term deposits: An application of machine learning algorithms. Journal.Stic.Ac.Th, 7(1). https://journal.stic.ac.th/index.php/sjhs/article/view/296
10. Charbuty, B., of Applied Science, A. A.-J., Technology, & undefined 2021. (2021). Classification based on decision tree algorithm for machine learning. Jastt.Org, 02(01), 20–28. https://doi.org/10.38094/jastt20165
11. Chen, Y., Zheng, W., Li, W., Letters, Y. H.-P. R., & undefined 2021. (n.d.). Large group activity security risk assessment and risk early warning based on random forest algorithm. Elsevier. https://www.sciencedirect.com/science/article/pii/S0167865521000192?casa_token=T6mSmj0Hrk8AAAAA:FG-isbvmLJD7WG42vXbqSXkIFz9Cshc13u37qQq6cux5X5_cKk3tU8bsboGGwiDI40J2Nrb1w9U
12. Cherif, I. L., (WD), A. K.-2019 W. D., & undefined 2019. (n.d.). On using extreme gradient boosting (XGBoost) machine learning algorithm for home network traffic classification. Ieeexplore.Ieee.Org. https://ieeexplore.ieee.org/abstract/document/8734193/?casa_token=BfU2LT1NO0sAAAAA:cbZ6gZQs5N63xxLXyEsnR4AHBpBgO4vb_mx_FOoTrakN_7Ej4i2MwvfQDeN3rRo9JWPpVmiR_DkTgg
13. Das, T. K. (2015). A customer classification prediction model based on machine learning techniques. 2015 International Conference on Applied and Theoretical Computing and Communication Technology (ICATccT), 321–326.
14. Demircioğlu, U., & Bakır, H. (2023). Deep learning-based prediction of delamination growth in composite structures: Bayesian optimization and hyperparameter refinement. Physica Scripta.
15. Demircioğlu, U., Sayil, A., & Bakır, H. (2023). Detecting Cutout Shape and Predicting Its Location in Sandwich Structures Using Free Vibration Analysis and Tuned Machine-Learning Algorithms. Arabian Journal for Science and Engineering, 1–14.
16. Doğan, E., & BAKIR, H. (2023). Hiperparemetreleri Ayarlanmış Makine Öğrenmesi Yöntemleri Kullanılarak Ağdaki Saldırıların Tespiti. International Conference on Pioneer and Innovative Studies, 1, 274–286.
17. DURAN, A., BAKIR, H., & GUZEY, H. M. (2023). Bilinen CNN mimarilerinin görsel Captcha sınıflandırması açısından değerlendirilmesi. International Conference on Pioneer and Innovative Studies, 1, 379–385.
18. Elsalamony, H. A. (2014). Bank direct marketing analysis of data mining techniques. International Journal of Computer Applications, 85(7), 12–22.
19. Fetah, K., Tebon, P., Ilham, A., Khikmah, L., & Iswara, I. B. A. I. (n.d.). Long-term deposits prediction: a comparative framework of classification model for predict the success of bank telemarketing. Iopscience.Iop.Org. https://doi.org/10.1088/1742-6596/1175/1/012035
20. Ghatasheh, N., Faris, H., AlTaharwa, I., Harb, Y., Sciences, A. H.-A., & undefined 2020. (n.d.). Business analytics in telemarketing: cost-sensitive analysis of bank campaigns using artificial neural networks. Mdpi.Com. https://doi.org/10.3390/app10072581
21. Ghosh, S., Hazra, A., Choudhury, B., on Machine …, P. B.-… C., & undefined 2018. (2018). A comparative study to the bank market prediction. Springer. https://link.springer.com/chapter/10.1007/978-3-319-96136-1_21
22. González, S., García, S., Del Ser, J., Rokach, L., & Herrera, F. (2020). A practical tutorial on bagging and boosting based ensembles for machine learning: Algorithms, software tools, performance study, practical perspectives and opportunities. Information Fusion, 64, 205–237.
23. Gupta, A., of Artificial Intelligence Techniques in, G. G.-A., & undefined 2019. (n.d.). Comparative study of random forest and neural network for prediction in direct marketing. Springer. https://link.springer.com/chapter/10.1007/978-981-13-1822-1_37
24. Gupta, A., Raghav, A., on …, S. S.-I. C., & undefined 2021. (n.d.). Comparative study of machine learning algorithms for Portuguese bank data. Ieeexplore.Ieee.Org. https://ieeexplore.ieee.org/abstract/document/9397083/?casa_token=EZlp423zAcgAAAAA:E-OgdyrA5eiAtSMUp55MtvpvYBHPnhtPAielgcyclaGZiDVB5tPEYnxiWqHI1XqEs_D8pwq1kwzSNw
25. Hou, S., Cai, Z., Wu, J., Du, H., of Business, P. X.-I. J., & undefined 2022. (n.d.). Applying Machine Learning to the Development of Prediction Models for Bank Deposit Subscription. Igi-Global.Com, 9(1). https://doi.org/10.4018/IJBAN.288514
26. Hung, P. D., Hanh, T. D., & Tung, T. D. (2019). Term deposit subscription prediction using spark MLlib and ML packages. ACM International Conference Proceeding Series, 88–93. https://doi.org/10.1145/3317614.3317618
27. Jackins, V., Vimal, S., Kaliappan, M., & Lee, M. Y. (2021). AI-based smart prediction of clinical disease using random forest classifier and Naive Bayes. Journal of Supercomputing, 77(5), 5198–5219. https://doi.org/10.1007/S11227-020-03481-X
28. Koumétio, C. S. T., … W. C.-2018 6th I., & undefined 2018. (n.d.). Optimizing the prediction of telemarketing target calls by a classification technique. Ieeexplore.Ieee.Org. https://ieeexplore.ieee.org/abstract/document/8629675/?casa_token=wz6gYTmH5-YAAAAA:iLYTvjFGCXGf2QM0xM_kz8w3uB3o99DNBq39Sjk1Ae7DyJgssxfbJqLrAQvIqi9ohc7FoVHhqzVjsA
29. Moro, S., Cortez, P., & Rita, P. (2014). A data-driven approach to predict the success of bank telemarketing. Decision Support Systems, 62, 22–31.
30. Moro, S., Laureano, R., & Cortez, P. (2011). Using data mining for bank direct marketing: An application of the crisp-dm methodology.
31. Rahman, M., on, V. K.-2020 4th I. C., & undefined 2020. (n.d.). Machine learning based customer churn prediction in banking. Ieeexplore.Ieee.Org. https://ieeexplore.ieee.org/abstract/document/9297529/?casa_token=x7HcTf2ZbyQAAAAA:VyWmUgpWMF8Q_zfxNAxZt9F0ki9ZFaIkGvfsFQHAceXpZTRZlqmvEzAJrKnYsm4-u0kYSeAyBFDEgA
32. Raiter, O. (2021). Segmentation of bank consumers for artificial intelligence marketing. International Journal of Contemporary Financial Issues, 1(1), 39–54.
33. Ruangthong, P., & Jaiyen, S. (2015). Bank direct marketing analysis of asymmetric information based on machine learning. 2015 12th International Joint Conference on Computer Science and Software Engineering (JCSSE), 93–96.
34. Shao, M., Bin, G., Wu, S., Jin, W., & He, Y. (n.d.). Three data mining models to predict bank telemarketing. Iopscience.Iop.Org. https://doi.org/10.1088/1757-899X/490/6/062075
35. Stéphane, C., Tekouabou, K., Hassan, S., Koumetio, S. C., Cherif, W., & Silkan, H. (2019). A data modeling approach for classification problems: application to bank telemarketing prediction. Dl.Acm.Org, Part F148154. https://doi.org/10.1145/3320326.3320389
36. Sundarkumar, G. G., Ravi, V., & Siddeshwar, V. (2015). One-class support vector machine based undersampling: Application to churn prediction and insurance fraud detection. 2015 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), 1–7.
37. Sungur, F., & Bakır, H. (2023). Yapay Zekâ Teknikleri Kullanılarak IOT Cihazlarda DDos Saldırı Tespiti. International Journal of Advanced Natural Sciences and Engineering Researches, 7(7), 275–280.
38. Wang, Z. H. E., Wu, C., Zheng, K., Niu, X., Access, X. W.-I., & undefined 2019. (n.d.). SMOTETomek-based resampling for personality recognition. Ieeexplore.Ieee.Org. https://ieeexplore.ieee.org/abstract/document/8827490/
39. Wu, J., Chen, X. Y., Zhang, H., Xiong, L. D., of Electronic …, H. L.-J., & undefined 2019. (n.d.). Hyperparameter optimization for machine learning models based on Bayesian optimization. Elsevier. https://www.sciencedirect.com/science/article/pii/S1674862X19300047
40. Wu, X., & Liu, H. (2022). Application of Big Data Unbalanced Classification Algorithm in Credit Risk Analysis of Insurance Companies. Journal of Mathematics, 2022.