# Fraud Detection

1. [Machine Learning for Credit Card Fraud Detection](https://fraud-detection-handbook.github.io/fraud-detection-handbook/Foreword.html) - Practical Handbook, [Git](https://github.com/Fraud-Detection-Handbook/fraud-detection-handbook)

   ![](https://83674056-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-Mgd48oS5_duTKOVE_Et%2Fuploads%2FZM9u8jU9C3kiW9gdCOvZ%2Fimage.png?alt=media\&token=19117aa0-ef72-496a-bbce-5dc1a8890231)
2. [Fraud detection](https://towardsdatascience.com/frauddetection-f801b781410b) on money pools, using social network & pool size, future optimizing using f-beta.
3. [Fraud detection Objectives.](https://nethone.com/post/beginners-guide-to-machine-learning)

   ![](https://83674056-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-Mgd48oS5_duTKOVE_Et%2Fuploads%2F3RX0M0So9mT6C3CNYue2%2Fimage.png?alt=media\&token=9a5e952e-daf4-4c04-bc9b-e807999045d7)
4. [awesome fraud papers](https://github.com/benedekrozemberczki/awesome-fraud-detection-papers) on github
5. [credit card fraud using an autoencoder in keras](https://github.com/curiousily/Credit-Card-Fraud-Detection-using-Autoencoders-in-Keras/blob/master/fraud_detection.ipynb)
6. [graph fraud papers](https://github.com/safe-graph/graph-fraud-detection-papers)
7. [Fraud using flink](https://github.com/afedulov/fraud-detection-demo), [docs](https://flink.apache.org/2020/01/15/advanced-flink-application-patterns-vol.1-case-study-of-a-fraud-detection-system/)
8. [credit card fraud on kaggle](https://github.com/georgymh/ml-fraud-detection)
9. [deep graph for fraud](https://github.com/safe-graph/DGFraud)
10. [Transforming Financial Forecasting with Data Science and Machine Learning at Uber](https://www.uber.com/en-IL/blog/transforming-financial-forecasting-machine-learning/)

Data sets

1. [questionable](https://www.kaggle.com/dmirandaalves/predict-chargeback-frauds-payment) fraud data set, it has no usable features and as a time series it doesn't look too informative
2. credit card fraud detection, everyone hit 99%+, seems too easy.