EUVIMEDEUVIMED entdecken
Crossref

A Robust Machine Learning Framework for Real-Time Fraud Detection in Banking Transactions

Mr. Gaurav B. Landage, Prof. Pragati B. Chandane, Dr. Hemantkumar B. Jadhav, Prof. Jagruti R. Mahajan, Dr. Pradeep M. Patil

International Journal of Advanced Research in Science Communication and Technology · 06.05.2026 · 365

DOI: 10.48175/ijarsct-34851 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Advanced Research in Science Communication and Technology, online erschienen am 06.05.2026. Verfasst von Mr. Gaurav B. Landage und 4 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid expansion of digital banking and online payment systems has resulted in a substantial rise in financial fraud, creating serious security challenges for both customers and financial institutions. Conventional fraud detection methods, which rely heavily on predefined rules, are often ineffective in identifying evolving and complex fraudulent behaviors. To overcome these limitations, this project presents a machine learning–based fraud detection system capable of automatically learning patterns from historical transaction data and detecting fraudulent activities in real time. The proposed system implements and evaluates multiple supervised machine learning algorithms, including Logistic Regression, Decision Trees, Random Forest, and Support Vector Machines (SVM), to classify banking transactions as either legitimate or fraudulent. A publicly available credit card transaction dataset is used for model training and testing, with appropriate data preprocessing and handling of class imbalance. The performance of each model is assessed using standard evaluation metrics such as accuracy, precision, recall, and F1-score. Experimental results indicate that machine learning techniques significantly improve fraud detection accuracy while reducing false positive rates. The system effectively identifies suspicious transactions in real time, enabling timely preventive actions. Overall, the proposed approach enhances the reliability, security, and efficiency of digital banking systems and demonstrates the potential of machine learning as a robust solution for modern financial fraud detection.

Zitieren

APA

Landage, M. G. B., Chandane, P. P. B., Jadhav, D. H. B., Mahajan, P. J. R., & Patil, D. P. M. (2026). A Robust Machine Learning Framework for Real-Time Fraud Detection in Banking Transactions. International Journal of Advanced Research in Science Communication and Technology, 365. https://doi.org/10.48175/ijarsct-34851

Vancouver

Landage MGB, Chandane PPB, Jadhav DHB, Mahajan PJR, Patil DPM. A Robust Machine Learning Framework for Real-Time Fraud Detection in Banking Transactions. International Journal of Advanced Research in Science Communication and Technology. 2026:365. doi:10.48175/ijarsct-34851

BibTeX
@article{Landage2026,
  author = {Landage, Mr. Gaurav B. and Chandane, Prof. Pragati B. and Jadhav, Dr. Hemantkumar B. and Mahajan, Prof. Jagruti R. and Patil, Dr. Pradeep M.},
  title = {A Robust Machine Learning Framework for Real-Time Fraud Detection in Banking Transactions},
  journal = {International Journal of Advanced Research in Science Communication and Technology},
  year = {2026},
  pages = {365},
  doi = {10.48175/ijarsct-34851}
}
Kostenlos starten →