2024, Vol. 5, Issue 1, Part A
Fraud detection using deep learning
Author(s): Sarthak Rout and Khyati Jaiswal
Abstract: Fraud detection is a critical aspect of various industries, such as finance, e-commerce, and insurance, to safeguard against fraudulent activities. Machine learning (ML) techniques have emerged as powerful tools for fraud detection, enabling the identification of patterns and anomalies that indicate fraudulent behavior. This paper explores two distinct approaches to fraud detection using ML: classical machine learning and neural networks. The classical machine learning approach utilizes K-means clustering to group similar transactions and three types of logistic regression models to predict the probability of a transaction being fraudulent. The neural network approach employs a simple neural network, Gaussian noise addition, and oversampling, scaling, and PCA to enhance model performance. A general outline for fraud detection model building is proposed, encompassing data preprocessing, feature engineering, data splitting, model selection, model training, model evaluation, imbalanced data handling, ensemble methods, threshold optimization, monitoring and updating, explainability and interpretability, and compliance and security.
DOI: 10.22271/27083969.2024.v5.i1a.37
Pages: 07-11 | Views: 840 | Downloads: 400
Download Full Article: Click Here
How to cite this article:
Sarthak Rout, Khyati Jaiswal. Fraud detection using deep learning. Int J Electr Data Commun 2024;5(1):07-11. DOI: 10.22271/27083969.2024.v5.i1a.37
