Machine Learning Based UPI Fraud Detection
Abstract
Fraud is a large scale problem which affects
the various entities from public sector to private sectors
including government, profit and non-profit
organizations. It is hard to predict the exact scale of the
fraud because most of the time it remains undetected. It
is very important to detect UPI frauds and save the
company’s or the tax payer’s money. The data mining
model developed in this research will help organization
to analyse their UPI transaction and will blow the early
whistle against the fraudsters. In our process, the
system is developed to detect the fraud in UPI by using
the machine learning algorithm. We predict the values
as fraud/non fraud for more accuracy and predict the
future fraud. First, we select and view the dataset for
future purpose. And we split the data as training data
and test data for getting to predict the values. It is
essential to train the models on data which includes
fraud and relevant non fraud. By using the ML
algorithm the system is, to classify the fraud and nonfraud
and results shows that the accuracy, precision,
recall and f1-score and also prediction. This shows that
method used in this project can predict the possibility of
fraud accurately in most of the cases. This module is
the simple and effective way to avoid such frauds and
save those expenditures
Downloads
References
Albizri, D. Appelbaum, and N. Rizzotto,
‘‘Evaluation of UPI statements fraud detection
research: A multi-disciplinary analysis,’’ Int. J.
Discl. Governance, vol. 16, no. 4, pp. 206–241, Dec.
2019.
2. R.Albright, ‘‘Taming text with the SVD.SAS
institute white paper, ’’SAS Inst., Cary, NC, USA,
White Paper 10.1.1.395.4666, 2004.
3. M. S. Beasley, ‘‘An empirical analysis of the
relation between the board of director composition
and UPI statement fraud,’’ Accounting Rev., vol. 71,
pp. 443–465, Oct. 1996.
4. T. B. Bell and J. V. Carcello, ‘‘A decision aid for
assessing the likelihood of fraudulent UPI
reporting,’’ Auditing A, J. Pract. Theory, vol. 19, no.
1, pp. 169–184, Mar. 2000.
5. M.D.BeneishandC.Nichols,‘‘The predictable cost of
earnings
manipulation,’’Dept.Accounting,KelleySchoolBus.,I
ndianaUniv.,Bloomington, IN, USA, Tech. Rep.
1006840, 2007.
6. R. J. Bolton and D. J. Hand, ‘‘Statistical fraud
detection: A review,’’ Stat. Sci., vol. 17, no. 3, pp.
235–249, Aug. 2002.
7. M.Cecchini, H.Aytug, G.J.Koehler, and
P.Pathak,‘‘Making words work: Using UPI text as a
predictor of UPI events,’’ Decis. Support Syst., vol.
50, no. 1, pp. 164–175, 2010.
8. Q. Deng, ‘‘Detection of fraudulent UPI statements
based on naïve Bayes classifier,’’ in Proc. 5th Int.
Conf. Comput. Sci. Educ., 2010, pp. 1032–1035.
9. S. Chen, Y.-J.-J. Goo, and Z.-D. Shen, ‘‘A hybrid
approach of stepwise regression, logistic regression,
support vector machine, and decision tree for
forecasting fraudulent UPI statements,’’ Sci. World
J., vol. 2014, pp. 1–9, Aug. 2014.
10. X. Chen and R. Ye, ‘‘Identification model of logistic
regression analysis on listed Firms’ frauds in
China,’’ in Proc. 2nd Int. Workshop Knowl.
Discovery Data Mining, Jan. 2009, pp. 385–388.
11. Chimonaki, S. Papadakis, K. Vergos, and A.
Shahgholian, ‘‘Identification of UPI statement fraud
in greece by using computational
intelligencetechniques,’’inProc.Int.WorkshopEnterpr
iseAppl.,Markets Services Finance Ind. Cham,
Switzerland: Springer, 2018, pp. 39–51.
12. R. Cressey, ‘‘Other people’s money; a study of the
social psychology of embezzlement,’’ Amer. J.
Sociol., vol. 59, no. 6, May 1954, doi:
10.1086/221475.
13. B. Dbouk and I. Zaarour, ‘‘Towards a machine
learning approach for
earningsmanipulationdetection,’’AsianJ.Bus.Account
ing,vol.10,no.2, pp. 215–251, 2017.
14. Q. Deng, ‘‘Application of support vector machine in
the detection of fraudulent UPI statements,
