Fraud detection of credit card using k-nearest neighbour

Abstract

Credit card fraud detection is a set of policies, tools, methodologies, and practices that credit card companies and financial institutions use to combat identity fraud and stop fraudulent transactions. Fraud in credit card transactions is unauthorized and un-wanted usage of an account by someone other than the owner of that account. Credit card fraud detection involves monitoring the activities of users to estimate, perceive or avoid objectionable behavior, which consists of fraud, intrusion, and defaulting. The credit card fraud detection features use user behavior and location scanning to check for unusual patterns.The K-Nearest Neighbors (KNN) model is a simple but effective machine learning algorithm that can be used for both classification and regression tasks. It works by finding the K nearest neighbors of a new data point in the training dataset and predicting the class or value of the new data point based on the classes or values of its neighbors. In this approach, the results of various machine learning algorithms are used for classifying defaulters and non-defaulters. Without feature selection, only the K-near-est neighbor (KNN) model performs well in terms of precision, while accuracy and re-call are low. Other algorithms, such as Support Vector Machine (SVM), Long Short-Term Memory (LSTM), and Isolation Forest, result in similar classification accuracy, but SVM exhibits a low recall rate. Random Forest (RF) shows a surprisingly high accuracy rate, but the recall rate is not satisfactory. In an attempt to obtain better results, a combination of KNN and Naïve Bayes (NB) algorithms is used, which results in high precision but low recall. To improve the classification accuracy, feature scaling is applied to the dataset, and it is observed that KNN, with feature scaling, does not achieve the highest classification accuracy compared to other models in Table 1. However, it shows good accuracy, precision and a pretty good recall, together, which is better than other models