Comparison of Credit Card Fraud Detection Algorithms
Keywords:
Adaboost, Credit card fraud, Machine learning, Random forest, Support vector machine (SVM)Abstract
Credit Card Frauds Detection is a machine learning-based approach, designed to automatically identify credit card transactions that are fraudulent. The problems of credit card fraud have been on the rise, where individuals use someone else's credit card information for illegitimate personal expenses. This kind of fraud falls under identity theft and has become a common problem in recent times. To tackle this problem, machine learning techniques are used in the fields of cybersecurity and data science. Credit card frauds are affecting individuals and financial institutions, leading to significant financial losses and emotional distress for victims. Detecting fraudulent transactions is a challenging task, but machine learning algorithms have been successful in identifying such transactions. It uses classification techniques such as AdaBoost, Random Forest, and SVM to detect anomalies in credit card transactions. This project will focus on analyzing and preprocessing large datasets to identify patterns and trends that can be used to detect fraud. Python programming language and Google Colab are used in this project. Google Colab is an environment that allows users to run numerous machine learning algorithms efficiently.