Detecting Credit Card Fraud Using High-Recall and Fast-Detection Techniques

This This Every year, credit card fraud costs billions of dollars, making it a serious issue. By recognizing patterns that point to fraudulent transactions, machine learning can be used to detect credit card fraud. The actual loss of a credit card or the theft of private credit card data is referred to as credit card fraud. For detection, a variety of machine-learning techniques can be applied. The goal of this research is to create a machine learning model that can identify credit card fraud. A holdout dataset of omitted transactions will be used to evaluate the model after it has been trained on a dataset of past credit card transactions. Three machine learning models are used in our method: linear discriminant analysis, linear regression, and K-nearest neighbor. Later, operators, and more conditional phrases like "IF" and "THEN" used adding operators, like ">" and ‘'\\\\\\\\," to the outcomes.Across the four evaluated fraud datasets, the features extracted with this suggested technique yielded recall values of 1.0000, 0.9701, 1.0000, and 0.9362. As a result, this methodology achieves higher recall than other methods that use individual machine learning models.