With the widespread use of credit card technology, credit card fraud cases have been increasing. AutoEncoders use the method of calculating errors in reconstructed data to make reasonable judgments about the category of data and return accurate classification answers. Compared to supervised algorithms, AutoEncoders can better handle imbalanced and unlabeled data. In this study, a deep AutoEncoder model is used for credit card fraud detection, which includes a multi-layer network of encoders and decoders and implements the method of reconstructing data to find the error threshold and achieve classification of fraud cases. The final model has a recognition accuracy of 91%. The study shows that based on deep AutoEncoders, this project can achieve relatively accurate credit card fraud anomaly detection.
Please note that this project is released with a Contributor Code of Conduct. By participating in this project you agree to abide by its terms.
If you think you can help in any of these areas or in many areas we haven't thought of yet, then please take a look at our Contributors' guidelines.
If you want to report a problem or suggest an enhancement we'd love for you to open an issue at this github repository because then we can get right on it. But you can also contact Yuki(Yuxin) and Sherry(Siyue) by email yuxin.yuki.chen@gmail.com and sygaoca@gmail.com.