Investigation of Total Debit and Credit Card Spending by Sectors with Different Learning Algorithms

Öz

Global economic activity is expanding day by day. On an individual level, people are meeting their needs; furthermore, they are frequently driven by discounts to make unnecessary purchases. Similarly, companies must actively engage in this economic activity and satisfy consumer demands to sustain their commercial operations. Governments are tasked with encouraging this growth while maintaining a balance through savings or precautionary measures. In this context, the usage of debit and credit cards, the cornerstone of modern economic activity, is rapidly increasing. This study aims to use various learning algorithms to classify spending volumes on debit and credit cards in Türkiye. To this end, classification successes will be achieved with the help of learning algorithms, and their results were compared to determining the top performing algorithms. The algorithms used in this study ‘Deep learning algorithm’, ‘Artificial neural network classifier’, ‘Conjunctive rule algorithm’, and ‘Alternating Decision tree algorithm’. The performance of these algorithms was evaluated using criteria such as ‘True positive rate’, ‘F-measure’, ‘Roc area value’, ‘Kappa statistic’, ‘Mean absolute error’, and ‘Root mean square error’. The analysis revealed that the Alternating Decision tree algorithm was the most successful, achieving a classification accuracy of 85.10%.

Anahtar Kelimeler

• Learning algorithms
• Debit card
• Credit card
• Decision trees

Destekleyen Kurum

No

Etik Beyan

The authors declare that ethical rules were followed throughout the preparation of this study.

Teşekkür

No

Banka ve Kredi Kartı Toplam Harcamasının Sektörlere Göre Farklı Öğrenme Algoritmaları ile Araştırılması

Öz

Dünya üzerinde ekonomik hareketlilik her geçen gün artmaktadır. Bireysel anlamda insanlar ihtiyaçlarını karşılamakta; bunun yanında ihtiyacı olmasa bile indirim etiketi üzerinden harcama yapmaktadır. Firmalarda benzer şekilde ticaretlerini devam ettirebilmek adına bu ekonomik hareketliliğe katılmak ve insanların ihtiyaçlarını karşılamak zorundadır. Ülkeler bu durumu teşvik ederek, tasarruf yaparak ya da tedbir alarak dengede tutmakla yükümlüdür. Bu bağlamda ekonomik hareketliliğin en önemli noktası olan banka ve kredi kartlarının kullanım yoğunluğu ve ekonomik hareketlilikteki payı hızla yükselmektedir. Bu çalışmada, Türkiye’deki banka ve kredi kartlarının harcama tutarlarının sınıflandırılmasında bazı öğrenme algoritmalarının kullanılması amaçlanmaktadır. Bu doğrultuda öğrenme algoritmaları yardımıyla sınıflandırma başarıları elde edilecek ve sonuçlar karşılaştırılarak hangi algoritmanın en başarılı sınıflandırma performansı gösterdiği belirlenecektir. Çalışmada öğrenme algoritmalarından ‘Derin öğrenme algoritması’, ‘Yapay sinir ağları sınıflandırıcısı’, ‘Birleşik kural algoritması’ ve ‘Değişmeli karar ağaçları algoritması’ kullanılmıştır. Algoritmaların performanslarını incelemek için ise kullanılan sınıflandırma performans kriterleri sırasıyla: ‘Doğru pozitif oranı’, ‘F-ölçütü’, ‘Roc değeri’, ‘kappa istatistiği’, ‘ortalama mutlak hata’ ve ‘Kök ortalama hata kare’ dir. Yapılan analizler sonucunda %85,10 ile Değişmeli karar ağaçları algoritması en başarılı sınıflandırma algoritması olarak belirlenmiştir

Anahtar Kelimeler

• Öğrenme algoritmaları
• Banka kartı
• Kredi kartı
• Karar ağaçları

Destekleyen Kurum

Yok

Etik Beyan

Yazarlar, bu çalışmanın hazırlanması boyunca etik kurallara uyulduğunu beyan ederler.

Teşekkür

Yok

Kaynakça

1. Afriyie, J. K., Tawiah, K., Pels, W. A., Addai-Henne, S., Dwamena, H. A., Owiredu, E. O., ... & Eshun, J. (2023). A supervised machine learning algorithm for detecting and predicting fraud in credit card transactions. Decision Analytics Journal, 6, Article 100163. https://doi.org/10.1016/j.dajour.2023.100163
2. Agrawal, R., Khanna, A., & Hamdare, S. (2025). Analyzing and rewarding credit card spending habits in India: A machine learning approach. International Journal of Computational Intelligence Systems, 18(1), Article 165.
3. Ahmed, S., Khan, Z. A., Mohsin, S. M., Latif, S., Aslam, S., Mujlid, H., ... & Najam, Z. (2023). Effective and efficient DDoS attack detection using deep learning algorithm, multi-layer perceptron. Future Internet, 15(2), Article 76.
4. Al Bataineh, A., Kaur, D., & Jalali, S. M. J. (2022). Multi-layer perceptron training optimization using nature inspired computing. IEEE Access, 10, 36963–36977.
5. Alarfaj, F. K., Malik, I., Khan, H. U., Almusallam, N., Ramzan, M., & Ahmed, M. (2022). Credit card fraud detection using state-of-the-art machine learning and deep learning algorithms. IEEE Access, 10, 39700–39715.
6. Alashwali, E., Mysuru Chandrashekar, R., Lanyon, M., & Faith Cranor, L. (2024, September). Detection and impact of debit/credit card fraud: Victims' experiences. In Proceedings of the 2024 European Symposium on Usable Security (pp. 235–260).
7. Anong, S. T., & Routh, A. (2022). Prepaid debit cards and banking intention. International Journal of Bank Marketing, 40(2), 321–340.
8. Borzekowski, R., Kiser, E. K., & Ahmed, S. (2008). Consumers' use of debit cards: Patterns, preferences, and price response. Journal of Money, Credit and Banking, 40(1), 149–172.

9. Breiman, L., Friedman, J., Stone, C. J., & Olshen, R. A. (1984). Classification and regression trees. CRC Press.
10. Central Bank of the Republic of Türkiye. (2025). Total debit and credit card spending. EVDS Data Portal. Erişim tarihi: 27 Aralık 2025, https://evds2.tcmb.gov.tr/index.php?/evds/serieMarket/#collapse_2
11. Chen, L., Li, D. L., Zheng, H. F., & Qiu, C. Z. (2025). Deep learning and radiomics-driven algorithm for automated identification of May-Thurner syndrome in iliac CTV imaging. Frontiers in Medicine, 12, Article 1526144.
12. David, B., Abel, F., & Patrick, W. (2016). Debit card and demand for cash. Journal of Banking & Finance, 73, 55–66.
13. Davis, R. H., Edelman, D. B., & Gammerman, A. J. (1992). Machine-learning algorithms for credit-card applications. IMA Journal of Management Mathematics, 4(1), 43–51.
14. De Comité, F., Gilleron, R., & Tommasi, M. (2003, June). Learning multi-label alternating decision trees from texts and data. In International Workshop on Machine Learning and Data Mining in Pattern Recognition (pp. 35–49). Springer, Berlin, Heidelberg.
15. Dornadula, V. N., & Geetha, S. (2019). Credit card fraud detection using machine learning algorithms. Procedia Computer Science, 165, 631–641.
16. Filiz, E. (2023). Evaluation of match results of five successful football clubs with ensemble learning algorithms. Research Quarterly for Exercise and Sport, 94(3), 773–782.
17. Foscht, T., Maloles III, C., Swoboda, B., & Chia, S. L. (2010). Debit and credit card usage and satisfaction: Who uses which and why–evidence from Austria. International Journal of Bank Marketing, 28(2), 150–165.
18. Freund, Y., & Mason, L. (1999, June). The alternating decision tree learning algorithm. In Proceedings of the 16th International Conference on Machine Learning (ICML) (Vol. 99, pp. 124–133).
19. Fu, G., Jin, Y., Sun, S., Yuan, Z., & Butler, D. (2022). The role of deep learning in urban water management: A critical review. Water Research, 223, Article 118973.
20. Fürnkranz, J., & Kliegr, T. (2015, July). A brief overview of rule learning. In International Symposium on Rules and Rule Markup Languages for the Semantic Web (pp. 54–69). Springer, Cham.
21. Holmes, G., Pfahringer, B., Kirkby, R., Frank, E., & Hall, M. (2002, August). Multiclass alternating decision trees. In European Conference on Machine Learning (pp. 161–172). Springer, Berlin, Heidelberg.
22. Huse, H., Haugland, S. A., & Hunneman, A. (2025). Integrating credit and debit data for enhanced insights into borrowing behavior and predictive modeling of credit card delinquency. The Journal of Finance and Data Science, Article 100166.
23. Jabbar, M. A., Deekshatulu, B. L., & Chandra, P. (2014, November). Alternating decision trees for early diagnosis of heart disease. In International Conference on Circuits, Communication, Control and Computing (pp. 322–328). IEEE.
24. Jaskowiak, P. A., Costa, I. G., & Campello, R. J. (2022). The area under the ROC curve as a measure of clustering quality. Data Mining and Knowledge Discovery, 36(3), 1219–1245.
25. Keller, J. M., & Tahani, H. (1992). Implementation of conjunctive and disjunctive fuzzy logic rules with neural networks. International Journal of Approximate Reasoning, 6(2), 221–240.
26. Khatri, S., Arora, A., & Agrawal, A. P. (2020, January). Supervised machine learning algorithms for credit card fraud detection: A comparison. In 2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence) (pp. 680–683). IEEE.
27. Kim, Y. S., & Lee, M. (2010). A model of debit card as a means of payment. Journal of Economic Dynamics and Control, 34(8), 1359–1368.
28. Kumar, R., & Indrayan, A. (2011). Receiver operating characteristic (ROC) curve for medical researchers. Indian Pediatrics, 48(4), 277–287.
29. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444.
30. Liu, K. Y., Lin, J., Zhou, X., & Wong, S. T. (2005). Boosting alternating decision trees modeling of disease trait information. BMC Genetics, 6(Suppl 1), Article S132.
31. Ma'rifah, S. L., & Faridatussalam, S. R. (2023, February). An analysis of the effect of debit card transaction nominals, credit card nominals, emoney nominals on the level of the total money in circulation in 2013- 2022. In Proceeding Medan International Conference on Economic and Business (Vol. 1, pp. 1576–1583).
32. Mehrish, A., Majumder, N., Bharadwaj, R., Mihalcea, R., & Poria, S. (2023). A review of deep learning techniques for speech processing. Information Fusion, 99, Article 101869.
33. Mohammadi, K., Zhao, H., Zhai, M., & Tung, F. (2023). Ranking regularization for critical rare classes: Minimizing false positives at a high true positive rate. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 15783–15792).
34. Morariu, D., Crețulescu, R., & Breazu, M. (2017). The WEKA multilayer perceptron classifier. International Journal of Advanced Statistics and IT&C for Economics and Life Sciences, 7(1).
35. Murtagh, F. (1991). Multilayer perceptrons for classification and regression. Neurocomputing, 2(5-6), 183–197.
36. Nguyen, T., Doncescu, A., & Siegel, P. (2016). Performance comparison of ADTree and Naive Bayes algorithms for spam filtering. World Academy of Science, Engineering and Technology, International Journal of Mathematical, Computational, Physical, Electrical and Computer Engineering, 10(5), 265–270.
37. Obi, J. C. (2023). A comparative study of several classification metrics and their performances on data. World Journal of Advanced Engineering Technology and Sciences, 8(1), 308–314.
38. Puh, M., & Brkić, L. (2019, May). Detecting credit card fraud using selected machine learning algorithms. In 2019 42nd International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO) (pp. 1250–1255). IEEE.
39. Putra, H. S., Huljannah, M., Anis, A., & Azhar, Z. (2021). Debit and credit cards: Money velocity risks. Jurnal Ekonomi & Studi Pembangunan, 22(2), 228–243.
40. Sadineni, P. K. (2020, October). Detection of fraudulent transactions in credit card using machine learning algorithms. In 2020 Fourth International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (ISMAC) (pp. 659–660). IEEE.
41. Scholnick, B., Massoud, N., Saunders, A., Carbo-Valverde, S., & RodríguezFernández, F. (2008). The economics of credit cards, debit cards and ATMs: A survey and some new evidence. Journal of Banking & Finance, 32(8), 1468–1483.
42. Sharifani, K., & Amini, M. (2023). Machine learning and deep learning: A review of methods and applications. World Information Technology and Engineering Journal, 10(7), 3897–3904.
43. Sharma, R., Kim, M., & Gupta, A. (2022). Motor imagery classification in brainmachine interface with machine learning algorithms: Classical approach to multi-layer perceptron model. Biomedical Signal Processing and Control, 71, Article 103101.
44. Shinde, P. P., & Shah, S. (2018, August). A review of machine learning and deep learning applications. In 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA) (pp. 1–6). IEEE.
45. Ughetto, L., Dubois, D., & Prade, H. (1999, July). Implicative and conjunctive fuzzy rules-A tool for reasoning from knowledge and examples. In Proceedings of the AAAI/IAAI Conference (pp. 214–219).
46. Van Zyl, J., & Cloete, I. (2004, August). An inductive algorithm for learning conjunctive fuzzy rules. In Proceedings of 2004 International Conference on Machine Learning and Cybernetics (Vol. 7, pp. 4181– 4187). IEEE.
47. Venkatesan, E. V., & Velmurugan, T. (2015). Performance analysis of decision tree algorithms for breast cancer classification. Indian Journal of Science and Technology, 8(29), 1–8.
48. Wahab, F., Khan, I., & Sabada, S. (2024). Credit card default prediction using ML and DL techniques. Internet of Things and Cyber-Physical Systems, 4, 293–306.
49. Wang, W., Qiao, L., & Lin, B. (2022). Tabular machine learning using conjunctive threshold neural networks. Machine Learning with Applications, 10, Article 100429.
50. WekaDeeplearning4j. (2025). Deep learning user guide. Erişim tarihi: 28 Aralık 2025, https://deeplearning.cms.waikato.ac.nz/user-guide/data/ Wright, J. (2003). Pricing in debit and credit card schemes. Economics Letters, 80(3), 305–309.
51. Yilmazkuday, H., & Yazgan, M. E. (2009). Effects of credit and debit cards on the currency demand. Applied Economics, 41(17), 2115–2123.
52. Zinman, J. (2009). Debit or credit?. Journal of Banking & Finance, 33(2), 358– 366.