TEJU: Fraud Detection and Improving Classification Performance for Bankruptcy Datasets Using Machine Learning Techniques

9 Pages Posted: 14 Jun 2019

See all articles by Srikanth Panigrahi

Srikanth Panigrahi

GMR Institute of Technology (GMRIT)

Kolla Saitejaswi

Department of Computer Science and Engineering, GMR Institute of Technology Rajam, AP

Dharmaiah Devarapalli

Shri Vishnu Engineering College for Women

Date Written: February 24, 2019

Abstract

Fraud detection is one the major challenge problem. In this paper addressing of problem is fraud detection and improving performance. The fraudulent are changing day by day and it became very difficult to identify which data fraud and which is legitimate. In this paper addressing design a framework TEJU as fraud detection and improving classification performance for bankruptcy datasets using machine learning techniques. So we can reduce the problem by using machine learning techniques of kNN and main objective apply distance between two patterns compute similarity with classified into each class wise. Then experimental results based on framework to improve performance analysis of accuracies, ROC curve values and error rate.

Suggested Citation

Panigrahi, Srikanth and Saitejaswi, Kolla and Devarapalli, Dharmaiah, TEJU: Fraud Detection and Improving Classification Performance for Bankruptcy Datasets Using Machine Learning Techniques (February 24, 2019). Proceedings of International Conference on Sustainable Computing in Science, Technology and Management (SUSCOM), Amity University Rajasthan, Jaipur - India, February 26-28, 2019, Available at SSRN: https://ssrn.com/abstract=3356511 or http://dx.doi.org/10.2139/ssrn.3356511

Srikanth Panigrahi (Contact Author)

GMR Institute of Technology (GMRIT) ( email )

Rajam, 532127
India

Kolla Saitejaswi

Department of Computer Science and Engineering, GMR Institute of Technology Rajam, AP ( email )

Dharmaiah Devarapalli

Shri Vishnu Engineering College for Women ( email )

India

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
88
Abstract Views
698
rank
323,275
PlumX Metrics