Developing an Intelligent Credit Card Fraud Detection System with Machine Learning

https://doi.org/10.55529/jaimlnn.21.45.53

Authors

  • Omkar Dabade Computer Department, Cusrow Wadia Institute of Technology, Pune, India.
  • Aditya Admane Computer Department, Cusrow Wadia Institute of Technology, Pune, India.
  • Deepak Shitole Computer Department, Cusrow Wadia Institute of Technology, Pune, India.
  • Vitthal Kamble Computer Department, Cusrow Wadia Institute of Technology, Pune, India.

Keywords:

Ada Boost, Classification, Credit Card, Fraud Detection, Predictive Modeling, Majority Voting.

Abstract

Credit card fraud is a significant issue in the economic services sector. Each year, billions of rupees are lost due to credit card fraud. Due to confidentiality concerns, there are an absence of studies examining actual credit card records. In this paper, machine learning algorithms are employed to detect credit card fraud. First, standard models are utilized. Then, hybrid techniques consisting of Random Forest, AdaBoost, XGBoost, and majority voting are implemented. To evaluate the effectiveness of the version, a set of publicly accessible credit card records is utilized. Then, credit card records from a real-world economic institution are analyzed. The experimental results suggest that Random Forest and majority voting accomplish precise accuracy estimates for detecting credit card fraud instances.

Published

2022-01-30

How to Cite

Omkar Dabade, Aditya Admane, Deepak Shitole, & Vitthal Kamble. (2022). Developing an Intelligent Credit Card Fraud Detection System with Machine Learning. Journal of Artificial Intelligence,Machine Learning and Neural Network , 2(01), 45–53. https://doi.org/10.55529/jaimlnn.21.45.53

Similar Articles

1 2 3 4 > >> 

You may also start an advanced similarity search for this article.