Abstract:
Credit card fraud is a major challenge for Bank, business owners, credit card users, and transactions services companies, causing every year substantial and growing financial losses. Detecting fraud patterns in credit card transactions is very common problem which is hard to solve. With the ever-growing amount of data generated by credit card transactions, it has become impossible for a human analyst to detect fraudulent patterns in transaction data sets. As a result, the design of credit card fraud detection techniques has increasingly focused in the last decade on approaches based on machine learning (ML) techniques that automate the process of identifying fraudulent patterns from large volumes of data. This project focuses on predictions of whether a credit card transaction is fraudulent or no. To solve this problem, we first build a machine learning model. Then, use existing training data to train the model and evaluate how good its accuracy is.
