https://github.com/pushpakrai/financial-fraud
https://github.com/pushpakrai/financial-fraud
Last synced: 5 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/pushpakrai/financial-fraud
- Owner: pushpakrai
- Created: 2024-12-28T18:50:43.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-12-28T18:54:11.000Z (over 1 year ago)
- Last Synced: 2024-12-28T19:28:59.767Z (over 1 year ago)
- Language: Jupyter Notebook
- Size: 0 Bytes
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Financial Fraud Detection
eCommerce websites often transact huge amounts of money. And whenever a huge amount of money is moved, there is a high risk of users performing fraudulent activities, e.g. using stolen credit cards, doing money laundry, etc. Machine Learning really excels at identifying fraudulent activities. Any website where you put your credit card information has a risk team in charge of avoiding frauds via machine learning.
By leveraging advanced machine learning algorithms, we can achieve the following objectives:
* Minimize costs by enhancing the accuracy of fraud transaction labeling.
* Increase revenue though optimizing customer experience with reduced false dectections.
The project contains:
* Implemented an ML model in Python to detect potential frauds and deployed real-time alert system.
* Analyzed and preprocessed a dataset of 138K+ transactions, employing techniques like duplicate removal, categorical feature encoding, outlier detection, and using resampling techniques to address imbalanced data.
* Built logistic regression, random forest, and gradient boosting models with parameter fine-tuning via grid search, achieving improvements of 14% in F1-score and 1.1% in AUC score over a baseline model.
* Provided actionable business recommendations for future anomaly transaction detection and prevention.