Year: 2025
Type: article
Abstract: In today's digital world, online transactions have become a part of everyday life, offering convenience, speed, and ease of use. However, they also come with risks like fraud, phishing, and data breaches. To tackle these challenges, we propose a machine learning-based fraud detection model that leverages feature engineering. By analyzing large volumes of data, the model learns, adapts, and improves over time, enhancing bothstability and accuracy in identifying fraudulent activities. These techniques play a crucial role in detecting online transaction fraud. By analyzing a dataset of online transactions, machine learning algorithms can spot unusual patterns that indicate fraudulent activity. Among these, the Random Forest Classifier has proven to be the most effective, achieving an impressive accuracy of 94.94%, outperforming other models in identifying suspicious transactions.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4409218743