#Anomaly-Detection-Credit-Card In this project study we will use various predictive models to see how accurate, models detecting whether a transaction is a normal payment or a fraud.
Problems and Project Purpose
Credit Card Fraud Defection is a challenging task. This is due to several features that should be examined for accurate and timely detection of Credit Card Fraudulent Transactions. It is imperative that credit card companies are able to identify fraudulent credit card transactions so that customers are not charged for unauthorized transactions. The purpose of this project is to develop a machine learning classification predictive model that can best be leveraged in credit card fraud detection. This model that can be utilized by credit card companies for significantly prevent the loss of billions of dollars to credit card fraudulent transactions.
Our Goals: Understand distribution of the data. Create a 50/50 sub-dataframe ratio of "Fraud" and "Non-Fraud" transactions. (Near Miss Algorithm) Determine the Classifiers we are going to use and decide which one has a higher accuracy. Create a Neural Network and compare the accuracy to our best classifier. Understand common mistaken made with imbalanced datasets.