Journals / Karaelmas Fen ve Mühendislik Dergisi / 2026 / Cilt: 16 Sayı: 1

Anomaly Detection in Credit Card Fraud Using Comprehensive Machine Learning Techniques

Kapsamlı Makine Öğrenmesi Teknikleri Kullanılarak Kredi Kartı Dolandırıcılığında Anomali Tespiti

Vedat Marttin(BİLECİK ŞEYH EDEBALİ ÜNİVERSİTESİ)0000-0001-5173-2349
Abdullah Alawad(BILECIK SEYH EDEBALI UNIVERSITY)0009-0000-8953-1497
Pages
20–37
Publication Date
2026-04-21
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

These methods consistently achieved accuracy scores above 0.99 and AUC values above 0.96, highlighting their effectiveness in addressing class imbalance and identifying complex fraud patterns.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Machine learning (ML) and deep learning (DL) have significantly advanced, enabling transformative applications in natural language processing, computer vision, and speech recognition.
📊
Key Findings & Data:This progress demands accurate and efficient modeling, particularly for large datasets.
💡
Conclusion & Impact:These methods consistently achieved accuracy scores above 0.99 and AUC values above 0.96, highlighting their effectiveness in addressing class imbalance and identifying complex fraud patterns.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Kredi kartı dolandırıcılığı tespiti · makine öğrenimi (ML) · yapay zeka (AI)

Abstract

Machine learning (ML) and deep learning (DL) have significantly advanced, enabling transformative applications in natural language processing, computer vision, and speech recognition. This progress demands accurate and efficient modeling, particularly for large datasets. In credit card fraud detection, diverse DL and ML approaches have been employed to enhance performance and reliability. This study utilized the Creditcard.csv dataset, consisting of 284807 European transactions with 30 PCA-transformed features and a ‘Class’ variable for legitimacy or fraud. The dataset was preprocessed and evaluated under both imbalanced and balanced conditions. Ten models, including Logistic Regression (LR), Naive Bayes (NB), K-Nearest Neighbors (KNN), Decision Trees (DT), Random Forest (RF), Support Vector Machine (SVM), XGBoost, Gradient Boosting (GB), LightGBM (LGBM), and Autoencoders (AE), were assessed using precision, recall, F1 score, and AUC. All experiments were conducted in Python. The findings demonstrate the strong fraud detection capabilities of LGBM (RandomOverSampler), RF, and KNN, while XGBoost (RandomOverSampler) achieved nearly perfect AUC. Ensemble learning methods such as RF, XGBoost, and LGBM demonstrated superior generalization and robustness. These methods consistently achieved accuracy scores above 0.99 and AUC values above 0.96, highlighting their effectiveness in addressing class imbalance and identifying complex fraud patterns.

Özet

Makine öğrenimi (ML) ve derin öğrenme (DL), doğal dil işleme, bilgisayarlı görme ve konuşma tanıma alanlarında dönüştürücü uygulamalara olanak tanıyarak önemli ölçüde ilerlemiştir. Bu ilerleme, özellikle büyük veri kümeleri için doğru ve verimli modelleme gerektirmektedir. Kredi kartı dolandırıcılığı tespitinde, performansı ve güvenilirliği artırmak için çeşitli DL ve ML yaklaşımları kullanılmaktadır. Bu çalışmada, 30 PCA dönüştürülmüş özelliğe ve meşru veya dolandırıcılık için bir ‘Sınıf’ değişkenine sahip 284807 Avrupa işleminden oluşan Creditcard.csv veri kümesi kullanılmıştır. Veri kümesi ön işleme tabi tutulmuş ve hem dengesiz hem de dengeli koşullar altında değerlendirilmiştir. Lojistik Regresyon, Naif Bayes, K-En Yakın Komşu algoritmasıı, Karar Ağaçları, Rastgele Orman, Destek Vektör Makinesi, XGBoost, Gradyan Artırma, LightGBM ve Otokodlayıcılar dahil olmak üzere on model, hassasiyet, geri çağırma, F1 puanı ve AUC kullanılarak değerlendirilmiştir. Uygulamalar Python’da gerçekleştirilmiştir. Bulgular, LGBM (RandomOverSampler), Random Forest ve K-Nearest Neighbors’ın güçlü dolandırıcılık tespit yeteneklerini ortaya koyarken, XGBoost (RandomOverSampler) neredeyse mükemmel AUC’ye ulaşmıştır. Random Forest, XGBoost ve LightGBM gibi topluluk öğrenme yöntemleri ise üstün genelleme ve sağlamlık sergilemiştir. Bu yöntemler, sürekli olarak 0.99’un üzerinde doğruluk puanları ve 0.96’nın üzerinde AUC değerleri elde ederek, sınıf dengesizliğini giderme ve karmaşık dolandırıcılık modellerini belirlemedeki etkinliklerini vurgulamıştır.

🔖

Cite This Article

Marttin, V., Alawad, A. (2026). Anomaly Detection in Credit Card Fraud Using Comprehensive Machine Learning Techniques. Karaelmas Fen ve Mühendislik Dergisi, Cilt: 16 Sayı: 1, 20–37. https://doi.org/10.7212/karaelmasfen.1760701

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (28)

  1. Alarfaj, FK., Malik, I., Khan, HU., Almusallam, N., Ramzan, M., & Al-Qurishi, M. (2022). Credit card fraud detection using state-of-the-art machine learning and deep learning algorithms. IEEE Access, 10: 39713-39727. https://doi: 10.1109/ACCESS.2022.3166891
  2. Bentéjac, C., Csörgő, A. & Martínez-Muñoz, G. (2021). A comparative analysis of gradient boosting algorithms. Artificial Intelligence Review, 54(3):1937–1967. https://doi:10.1007/s10462-020-09896-5
  3. Bisong, E. (2019). Google Colaboratory. In: Building Machine Learning and Deep Learning Models on Google Cloud Platform. Apress, Berkeley, CA. pp.59-64. https://doi:10.1007/978-1-4842-4470-8_7
  4. Btoush, EALM., Zhou, X., Gururajan, R., Chan, KC., Genrich, R., & Sankaran, P. (2023). A systematic review of literature on credit card cyber fraud detection using machine and deep learning. PeerJ Computer Science, 9:e1278. https://doi:10.7717/peerj-cs.1278
  5. Charbuty, B. & Abdulazeez, A. (2021). Classification based on decision tree algorithm for machine learning. Journal of Applied Science and Technology Trends, 2(01):20–28. https://doi:10.38094/jastt20165
  6. Fletcher, T. (2009). Support vector machines explained. Tutorial Paper, 1118:1–19.
  7. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning,1(2). Cambridge: MIT Press,USA, 800 p.
  8. Hafez, IY., Hafez, AY., Saleh, A., Abd El-Mageed, AA. & El-Mageed, AA. (2025). A systematic review of AI-enhanced techniques in credit card fraud detection. Journal of Big Data, 12(1): 6. https://doi:10.1186/s40537-024-01048-8
  9. Huang, C., Tu, PM. & Lin, CY. (2023). Making data analysis easier: A case study on credit card fraud detection based on PyCaret. 4th International Conference on Management Science and Engineering Management (ICMSEM 2023),pp.1203. Atlantis Press. https://doi:10.2991/978-94-6463-256-9_122
  10. Kaggle (2025). Anomaly detection credit card fraud dataset. https://www.kaggle.com/code/annastasy/anomaly-detection-credit-card-fraud/input
  11. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W.,. & Liu, TY. (2017). LightGBM: A highly efficient gradient boosting decision tree. 31st Conference on Neural Information Processing Systems (NIPS 2017),pp.1-9, Long Beach, CA, USA.
  12. Kumar MS., Soundarya V., Kavitha S., Keerthika ES., & Aswini E. (2019). Credit card fraud detection using random forest algorithm.3rd International Conference on Computing and Communications Technologies (ICCCT),pp.149, IEEE,Chennai, India. https://doi: 10.1109/ICCCT2.2019.8824930.
  13. Li, W., Yin, Y., Quan, X., & Zhang, H. (2019). Gene expression value prediction based on XGBoost algorithm. Frontiers in Genetics (10):1077. https://doi:10.3389/fgene.2019.01077
  14. Meenakshi FI. & Singh S. (2021). Comparison and analysis of logistic regression, naive bayes and knn machine learning algorithms for credit card fraud detection. International Journal of Information Technology, 13(4):1503–1511. https://doi:10.1007/s41870-020-00430-y
  15. Nishad, AK., Pandey, N., & Pandey, VK. (2024). Credit card fraud detection using machine learning.1st International Conference on Advances in Computing, Communication and Networking (ICAC2N),pp.380, IEEE, Greater Noida, India, https//doi:10.1109/ICAC2N63387.2024.10895238
  16. Python 3.8.6, Software. (2025). Python Software Foundation License v2. https://www.python.org
  17. Rahman, R. (2021). Supervised machine learning algorithms for credit card fraudulent transaction detection: A comparative survey. Master Thesis, University of Victoria, Canada, 53 p.
  18. Rathore, AS., Kumar, A., Tomar, D., Goyal, V., Sarda, K., & Vij, D. (2021). Credit card fraud detection using machine learning. 10th International Conference on System Modeling & Advancement in Research Trends (SMART), pp.167, IEEE, Moradabad, India, https://doi: 10.1109/SMART52563.2021.9676262.
  19. Rigatti, SJ. (2017). Random forest. Journal of Insurance Medicine, 47(1):31–39. https://doi:10.17849/insm-47-01-31-39.1
  20. Sharma, MA., Raj, BG., Ramamurthy, B., & Bhaskar, RH. (2022). Credit card fraud detection using deep learning based on auto-encoder. 4th International Conference on Advances in Electrical and Computer Technologies (ICAECT). In ITM Web of Conferences, (50):01001,pp.18, EDP Sciences, Tiruchengode, Tamil Nadu, India. https://doi:10.1051/itmconf/20225001001
  21. Tanouz, D., Subramanian, RR., Eswar, D., Reddy, GP., Kumar, AR., & Praneeth, CV. (2021). Credit card fraud detection using machine learning.5th International Conference on Intelligent Computing and Control Systems (ICICCS),pp.967, IEEE, Madurai, India. https://doi: 10.1109/ICICCS51141.2021.9432308.
  22. Taunk, K., De, S., Verma, S., & Swetapadma, A. (2019). A brief review of nearest neighbor algorithm for learning and classification. International Conference on Intelligent Computing and Control Systems (ICCS),pp.1255, IEEE, Madurai, India. https://doi: 10.1109/ICCS45141.2019.9065747.
  23. Tukur, K., & Usman, AU. (2016). Binary logistic regression analysis on addmiting students using jamb score. Journal of Current Research, 8(01):25235–25239.
  24. Xie, R., Wen, J., Quitadamo, A., Cheng, J., & Shi, X. (2017). A deep auto-encoder model for gene expression prediction. BMC Genomics, 18(9):845. https://doi:10.1186/s12864-017-4226-0.
  25. Xie, Z., & Huang, X. (2024). A credit card fraud detection method based on Mahalanobis distance hybrid sampling and random forest algorithm. IEEE Access, (12):162788–162798. https://doi: 10.1109/ACCESS.2024.3421316.
  26. Zhang, H., & Sheng, S. (2004). Learning weighted naive Bayes with accurate ranking. In Fourth IEEE International Conference on Data Mining (ICDM'04),pp. 567-570. IEEE. Brighton, UK. https://doi: 10.1109/ICDM.2004.10030.
  27. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning,1(2). Cambridge: MIT Press,USA, 800 p.
  28. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W.,. & Liu, TY. (2017). LightGBM: A highly efficient gradient boosting decision tree. 31st Conference on Neural Information Processing Systems (NIPS 2017),pp.1-9, Long Beach, CA, USA.