Cyber-fraud detection methodology by using machine learning algorithms

Abstract

Cybercrime covers a wide array of illegal online activities such as hacking and identity theft, while cyber fraud specifically involves deceptive practices like phishing and fraudulent financial transactions. The rise in technology and digital communication has exacerbated cyber fraud. Although prevention technologies are advancing, fraudsters continually adapt, making effective detection methods essential for identifying and addressing fraud when prevention fails. The proposed model aims to reduce online fraud through new detection algorithms. It utilizes statistical and machine learning techniques, including logistic regression, random forest, and naïve Bayes, to identify non-transactional fraud behaviors. By analyzing a meticulously collected and fine-tuned dataset, the study enhances detection capabilities beyond traditional transaction-focused approaches. The algorithms monitor user interactions and device characteristics to create profiles of normal behaviors and detect deviations indicative of fraud. The evaluation of proposed model showed 100% accuracy. A unified model incorporating all decision-making processes was used, leading to a voting phase and accuracy assessment. This approach consolidates multiple algorithms into a single framework, proving highly effective for comprehensive fraud detection. The research demonstrates the value of integrating machine learning techniques with real-world data to advance fraud detection and emphasizes the importance of continual adaptation to address evolving cyber threats.