MACHINE LEARNING ALGORITHM FOR DISCOVERY OF FINANCIAL FRAUDS: BASED ON LOGISTIC REGRESSION

This article presents the use of machine learning algorithms to detect
financial fraudsters. The use of 2 machine learning algorithms is considered, which are the
logistic regression algorithm and the random forest. It is compared which of these algorithms
makes more accurate predictions. We have successfully developed a framework for detecting
fraudulent transactions in financial data. This framework helps understand the nuances of fraud
detection, such as creating derived variables that can help separate classes, resolve class
imbalances, and select the right machine learning algorithm. The advantages of a logistic
regression-based machine learning algorithm for detecting financial fraud include high
classification accuracy, the ability to work with large volumes of data, and interpretability of
the results. In addition, the algorithm can be effectively applied in real time, which makes it
possible to quickly detect fraudulent transactions. In conclusion, logistic regression-based
machine learning algorithm is a powerful tool for detecting financial fraud. Its use helps
financial institutions improve security and reduce the risks associated with fraudulent
transactions.

Regression, logistic regression, machine learning algorithm, financial forecasters, random forest.

1. TESTIMON @ NTNU, Synthetic Financial Datasets for Fraud Detection, Kaggle,

retrieved from https://www.kaggle.com/ntnu-testimon/paysim1

2. Jayakumar et.al., A New Procedure of Clustering based on Multivariate Outlier

Detection. Journal of Data Science 2013; 11: 69-84

3. Jans et.al, A Business Process Mining Application for Internal Transaction Fraud

Mitigation, Expert Systems with Applications 2011; 38: 13351–13359

4. Phua et.al., Minority Report in Fraud Detection: Classification of Skewed Data. ACM

SIGKDD Explorations Newsletter 2004; 6: 50-59.

5. Dharwa et.al., A Data Mining with Hybrid Approach Based Transaction Risk Score

Generation Model (TRSGM) for Fraud Detection of Online Financial Transaction,

International Journal of Computer Applications 2011; 16: 18-25.

6. Sahin et.al., A Cost-Sensitive Decision Tree Approach for Fraud Detection, Expert

Systems with Applications 2013; 40: 5916–5923.

7. Sorournejad et.al., A Survey of Credit Card Fraud Detection Techniques: Data and

Technique Oriented Perspective, 2016

8. Wedge et.al., Solving the False Positives Problem in Fraud Prediction Using

Automated Feature Engineering, Machine Learning and Knowledge Discovery in Databases,

pp 372-388, 2018.

2026-03-22