One Step Ahead Using Data Mining Techniques Loan Fraud Investigation/Analytics

  • Himani
  • Dr. Lakshmi Shankar Singh
Keywords: Data analysis methods, a scam, loan fraud, loan identification, data mining


Background: loan fraud refers to any deceptive or dishonest activity to obtaining or misusing a loan it involves intentionally providing false information or manipulating the loan process for personal gain. Loan fraud is illegal and can have serious consequences, including financial loss, damaged credit, and potential legal action. Lenders employ various measures, such as background checks, verification processes, and fraud detection systems, to mitigate the risks of loan fraud.

Many businesses across various industries have expressed worry about loan fraud; this causes billion- rupees losses every year. Thus, in order to deal with this ongoing and expanding issue, firms use data mining approaches. The purpose of this paper is to analyze studies that have been done in the last ten years to identify financial fraud using data mining techniques and to inform academic researchers and business professionals of the latest developments.

Financial organizations place a high value on loan fraud detection because of the losses that may be prevented by using an effective fraud detection system. This is a topic that is regularly brought up in scientific study.

Objective:  The aim of this research is to describe a machine learning method to loan identification of fraud using data mining techniques while comparing a machine learning algorithm using statistical frameworks in fraud detection.

Methods: The study suggests a method for enhancing performance through machine learning and data mining approaches. The writers employed two datasets for the training phase. The first set of data is unprocessed, whereas the second set has been pre-processed using techniques for feature engineering and selection. All classifiers' performance significantly improved after being evaluated on pre-processed data, according to the results.

Result: Finally, they draw the conclusion that, when compared to machine algorithms for learning, using machine learning algorithms straight to raw data produces poor results for statistical models, and that the suggested approach—which makes use of feature design and selection techniques—helps to enhance performance. A variety of financial applications, including credit cards and health insurance, were found to have fraud using data mining techniques.

Author Biographies


Department of Sir Chhotu Ram Institute of Engineering And Technology, Chaudhary Charan Singh University (Campus), Meerut India.

Dr. Lakshmi Shankar Singh

Department of Sir Chhotu Ram Institute of Engineering And Technology, Chaudhary Charan Singh University (Campus), Meerut India.


1. V. G. T. Costa, A. C. P. L. Carvalho, S. Barbon, "Strict Very Fast Decision Tree: a Memory conservative algorithm for data stream mining", May 2018.
2. A. Aye Khine, H. Wint Khine, "A Survey of Decision Tree for Data Streams to Detect Credit Card Fraud", PROMAC-2019.
3. F. A. Sunny, M. I. Khan, M. S. Satu and M. Z. Abedin, "Investigating external audit records to detect fraudulent firms employing various machine learning methods", Proceedings of the Seventh International Conference on Mathematics and Computing, pp. 511-523, 2022.
4. R. Van Belle, B. Baesens and J. De Weerdt, "Catchm: A novel network- based credit card fraud detection method using node representation learning", Decision Support Systems, pp. 113866, 2022.
5. Brabazon, J. Cahill, P. Keenan and D. Walsh, "Identifying online credit card fraud using artificial immune systems", IEEE Congress on Evolutionary Computation., pp. 1-7, 2010.
6. vAbbott, D., Matkovsky, P. & Elder, J. (1998). An Evaluation of High-End Data Mining Tools for Fraud Detection. Proc. of IEEE SMC98.
7. Aleskerov, E., Freisleben, B. & Rao, B. (1997). CARDWATCH: A Neural Network-Based Database Mining System for Credit Card Fraud Detection. Proc. of the IEEE/IAFE on Computational Intelligence for Financial Engineering, 220-226.
8. Goldenberg, A., Shmueli, G., Caruana, R. & Fienberg, S. (2002).Early Statistical Detection of Anthrax Outbreaks by Tracking Overthe-Counter Medication Sales. Proc. of the National Academy of Sciences, 5237-5249

9. Jensen, D., Rattigan, M. & Blau, H. (2003). Information Awareness: A Prospective Technical Assessment. Proc. Of SIGKDD03, 378- 387.
10. Shah. M. (2019). A Case Study on Increasing of Banking Frauds in India. Parichay: Maharaja Surajmal Institute Journal of Applied Research, 2(1), 20-23.
11. Dogra. A. Banking Frauds in India: Case Studies of Nirav Modi and Vijay Mallya Case. International Journal of Creative Research Thoughts, 6(1), 855-860.
12. R. Goyal, A. Kumar, "Review on Credit Card Fraud Detection using Data Mining Classification Techniques & Machine Learning Algorithms", International Journal of Research and Analytical Reviews, Vol. 7, No. 1, 2020, pp. 972-975.
13. G. Marinakos, S.Daskalaki, "Imbalanced customer classification for bank direct marketing", Journal of Marketing Analytics, Vol. 5, No. 1, 2017, pp. 14-30.
A. Abdallah, M. A. Maarof, A. Zainal, "Fraud detection system: A survey", Journal of Network and Computer Applications, Vol. 68, 2016, pp. 90-113.
14. K. Janaki, V. Harshitha, S. Keerthana, Y. Harshitha, "A Hybrid Method for Credit Card Fraud Detection Using Machine Learning Algorithm", International Journal of Recent Technology and Engineering, Vol. 7, No. 6S4, 2019, pp. 235-239.
15. M. A. Sheikh, A. K. Goel, T. Kumar, "An approach for prediction of loan approval using machine learning algorithm", Proceedings of the IEEE International Conference on Electronics and Sustainable Communication Systems, 2-4 July 2020, pp. 490-494.
How to Cite
Himani, & Dr. Lakshmi Shankar Singh. (1). One Step Ahead Using Data Mining Techniques Loan Fraud Investigation/Analytics. Revista Electronica De Veterinaria, 25(1S), 251-255. Retrieved from