Fraud Detection of Credit Cards Using Neuro-fuzzy Approach Based on TLBO and PSO Algorithms

Document Type: Original Research (Full Papers)

Authors

1 Faculty of Computer and Information Technology Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran

2 Faculty of Computer and Electrical Engineering, Tarbiyat Modarres University, Tehran, Iran

Abstract

The aim of this paper is to detect bank credit cards related frauds. The large amount of data and their similarity lead to a time consuming and low accurate separation of healthy and unhealthy samples behavior, by using traditional classifications. Therefore in this study, the Adaptive Neuro-Fuzzy Inference System (ANFIS) is used in order to reach a more efficient and accurate algorithm. By combining evolutionary algorithms with ANFIS, the optimal tuning of ANFIS parameters is achieved by the Teaching-Learning-Based Optimization (TLBO) and the Particle Swarm Optimization (PSO). The aim of using this approach is to improve the network performance and to reduce calculation complexities compared to gradient descent and least square methods. The proposed algorithm is implemented and evaluated on credit cards data to detect fraud. The results demonstrate superior performance of the designed scheme compared to other intelligent identification methods.

Keywords

Journal of Computer & Robotics

Volume 10, Issue 2
Summer and Autumn 2017
Pages 57-68

Files

History

  • Receive Date: 14 September 2016
  • Revise Date: 05 November 2016
  • Accept Date: 18 January 2017

Share

How to cite

Statistics