A comparative analysis of financial fraud detection in credit card by decision tree and random forest techniques

• Main Authors: Jena, Amrut Ranjan, Sen, Santanu Kumar, Mishra, Madhusmita, Banerjee, Shrutarba, Dey, Nupur, Saha, Ipsita
• Format: Conference Proceeding
• Language: English
• Subjects: Algorithms; Banking; Credit cards; Decision analysis; Decision trees; Fraud; Fraud prevention; Machine learning
• ISSN: 0094-243X; 1551-7616
• DOI: 10.1063/5.0166542

The rapid evolution of the tools are the basis of the world to turn to use credit cards instead of cash in their daily life, which opens the door to many new ways for fraudulent people to use these cards in a bad way. In order to ensure the safety of users for these credit cards, the credit card's provider should provide a service to protect users from any risk they may face. This paper states financial fraud detection in credit card by applying machine learning classification algorithms. This model helps industries dealing with money transaction directly such as banking, insurance, etc. Credit card fraud detection is a pressing issue to resolve especially for the banking industry. Due to fraudulent activities towards revenue growth and loss of customer's trust has caused these industries to suffer extensively. So these companies need to find fraud transactions before it becomes a big problem for them. The target class distribution is not equally distributed in credit cards to see the fraud detection. It is popularly known as the class imbalance problem or unbalanced data issue. To analyze and find fraud in credit card, we are applying and comparing the results of two machine learning algorithms such as random forest and decision trees.