Year: 2024
Type: article
Abstract: Banking fraud transactions refer to unauthorized or deceptive activities involving bank accounts or financial transactions. Various machine- learning algorithms can be employed to detect such fraudulent activities. This study examines several algorithms suitable for classifying transactions as either fraudulent or legitimate. The research utilizes the Banking Fraud Transactions dataset, often characterized by high imbalance. To address this issue, we are implementing multiple machine learning algorithms like Random Forest, K-Nearest Neighbour, and Decision Tree. Additionally, feature selection techniques are employed, and the dataset is divided into training and test sets. The algorithms evaluated in the study include Random Forest and KNN. The findings indicate that each algorithm demonstrates high accuracy in detecting banking fraud transactions. The proposed model holds promise for detecting other irregularities within financial transactions. Key Words: Banking Fraud Transactions, Machine Learning Algorithms, Imbalanced Dataset
DOI: 10.55041/ijsrem40117
Authors: Malepu Shrishanth, L Nitish Reddy, K Harshavardhan Reddy, G Mahesh, Mrs P Venkata Pratima
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4405849238