How efficient is Machine Learning in detecting financial fraud using mobile transaction metadata?
DOI:
https://doi.org/10.47611/jsrhs.v11i3.2865Keywords:
Machine learning, Naïve Bayes Classifier, Fraud detection, dataset, attributes, variablesAbstract
Global data has shown that each day the number of fraudulent transactions is exponentially increasing. As digital fraud continues to increase, machine learning and AI are being used to curb this increase. This paper will focus on the development and analysis of a machine learning model used to detect financial fraud in mobile money transactions. The aim of this paper is to discuss how effective a machine learning model can be in detecting fraud. This algorithm makes use of the Naïve Bayes model to detect fraud. To prove this, the results have been provided by using a confusion matrix, precision and recall which indicate the effectiveness of the model. The accuracy of the developed model is 0.996 with a precision and recall of both above 0.99. This work explores and develops a solution to one of the biggest breaches in digital security.
Downloads
References or Bibliography
“Digital Payment - Different Modes & Benefits of Digital Payment.” Bankbazaar, www.bankbazaar.com/ifsc/digital-payment.html.
DepositAccounts, et al. “Banking 101: 5 Benefits of Online Banking.” Deposit Accounts, 22 Apr. 2019, www.depositaccounts.com/blog/online-banking.html.
Financial Fraud in the Digital Space | Enisa - Europa. www.enisa.europa.eu/publications/enisa-position-papers-and-opinions/financial-fraud-in-the-digital-space.
Smith, Tyler, et al. “Increase in Digital Banking Facilitating Equal Rise in Financial Fraud Attempts.” The Fintech Times, 24 June 2021, https://thefintechtimes.com/increase-in-digital-banking-facilitating-equal-rise-in-financial-fraud-attempts/.
“Different Types of Financial Fraud Explained.” Financial Fraud Explained | Identity Theft and Fraud | Equifax UK, www.equifax.co.uk/resources/identity-protection/different-types-of-financial-fraud-explained.html.
Jones, Marlene. “Fraudulent Wire Transfers: Examples of Fake Emails to Watch For.” Tetra Defense, Marlene Jones Http://Www.tetradefense.com/Wp-Content/Uploads/2022/02/AW-TD_Logo_Landscape_Reverse-Blue-Copy-300x109.Png, 14 Nov. 2021, www.tetradefense.com/incident-response-services/fraudulent-wire-transfers-how-they-happen-and-why-you-may-be-at-risk/#:~:text=Wire%20transfer%20fraud%20has%20grown,to%20another%20person's%20bank%20account.
“5 Methods of Detecting Fraud in Organizations.” Kaufman Rossin, https://kaufmanrossin.com/blog/5-methods-of-detecting-fraud-in-organizations/.
Arjunjoshua. “Predicting Fraud in Financial Payment Services.” Kaggle, Kaggle, 21 Jan. 2018, www.kaggle.com/arjunjoshua/predicting-fraud-in-financial-payment-services/notebook.
Quinn, Megan. “Detecting Financial Fraud with Machine Learning.” Detecting Financial Fraud with Machine Learning, www.bluegranite.com/blog/detecting-financial-fraud-with-machine-learning.
Techlabs, Maruti. “How Machine Learning Is Enhancing Fraud Detection.” Medium, Medium, 16 Sept. 2020, https://marutitech.medium.com/how-machine-learning-is-enhancing-fraud-detection-694f3a2237f.
PAYSIM: A Financial Mobile Money Simulator for Fraud Detection. www.researchgate.net/publication/313138956_PAYSIM_A_FINANCIAL_MOBILE_MONEY_SIMULATOR_FOR_FRAUD_DETECTION.
Jan, Chyan-long. “An Effective Financial Statements Fraud Detection Model for the Sustainable Development of Financial Markets: Evidence from Taiwan.” MDPI, Multidisciplinary Digital Publishing Institute, 14 Feb. 2018, www.mdpi.com/2071-1050/10/2/513.
Kolodiziev, Oleh, et al. “Automatic Machine Learning Algorithms for Fraud Detection in Digital Payment Systems.” SSRN, 14 Jan. 2021, https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3730001.
Huang, Jian, et al. “Deep Learning in Finance and Banking: A Literature Review and Classification - Frontiers of Business Research in China.” SpringerOpen, Springer Singapore, 8 June 2020, https://fbr.springeropen.com/articles/10.1186/s11782-020-00082-6.
“Bayes Theorem - Statement, Formula, Derivation, Examples.” Cuemath, www.cuemath.com/data/bayes-theorem/.
Barone, Adam. “Conditional Probability.” Investopedia, Investopedia, 8 Feb. 2022, www.investopedia.com/terms/c/conditional_probability.asp#:~:text=Conditional%20probability%20is%20defined%20as,succeeding%2C%20or%20conditional%2C%20event.
Majumder, Prateek. “Gaussian Naive Bayes.” OpenGenus IQ: Computing Expertise & Legacy, OpenGenus IQ: Computing Expertise & Legacy, 23 Feb. 2020, https://iq.opengenus.org/gaussian-naïvebayes/#:~:text=Gaussian%20Naive%20Bayes%20is%20a,distribution%20and%20supports%20continuous%20data.&text=Naive%20Bayes%20are%20a%20group,technique%2C%20but%20has%20high%20functionality.
Coursera. “What Is Python Used for? A Beginner's Guide.” Coursera, 22 Sept. 2021, www.coursera.org/articles/what-is-python-used-for-a-beginners-guide-to-using-python.
Markham, Kevin. “Simple Guide to Confusion Matrix Terminology.” Data School, Data School, 3 Feb. 2020, www.dataschool.io/simple-guide-to-confusion-matrix-terminology/.
“Idiot's Guide to Precision, Recall, and Confusion Matrix.” KDnuggets, www.kdnuggets.com/2020/01/guide-precision-recall-confusion-matrix.html.
Jayaswal, Vaibhav. “Performance Metrics: Confusion Matrix, Precision, Recall, and F1 Score.” Medium, Towards Data Science, 15 Sept. 2020, https://towardsdatascience.com/performance-metrics-confusion-matrix-precision-recall-and-f1-score-a8fe076a2262
Published
How to Cite
Issue
Section
Copyright (c) 2022 Vedant Shah
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright holder(s) granted JSR a perpetual, non-exclusive license to distriute & display this article.
