Identifying Financial Fraud Transactions Using Decision Tree Classifier Algorithm

Abstract

Fraud in financial transactions is a critical issue for businesses, governments, and consumers, causing substantial financial losses and  eroding trust in financial systems. Rule-based systems and other conventional fraud detection techniques have trouble identifying  complex fraudulent activity. This research applies various machine learning (ML) algorithms to detect fraud in financial transactions. The  research compares the performance of supervised ML techniques, such as random forest, logistic regression, and decision tree classifier,  using a publicly available Kaggle dataset. It evaluates the models based on accuracy, precision, recall, and F1 scores. To address data  imbalance in both undersampling and oversampling techniques, with a focus on oversampling techniques such as Synthetic Minority  Over-Sampling Method (SMOTE) to enhance model performance. Results show that the Decision Tree Classifier, when used with  oversampling, outperforms other models, achieving a 99% accuracy in detecting fraudulent transactions. This highlights the effectiveness  of using ensemble and hybrid models in combination with oversampling to enhance the identification of fraud. The findings emphasize the importance of using advanced ML techniques and robust data preprocessing for detection of financial fraud.