YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
π‘οΈ Fraud Detection in Financial Transactions
This project uses Machine Learning to detect fraud in financial transactions, based on the PaySim dataset.
π Dataset
The data simulates bank transactions and includes columns such as:
amount: the transaction amounttransaction_type: transfer or withdrawalsourceanddestination: involved accountsisFraud: indicates whether the transaction is fraudulent (1) or not (0)
π Results
We trained a Random Forest model, achieving the following evaluation metrics:
| Class | Precision | Recall | F1-Score | Support |
|---|---|---|---|---|
| Non-Fraud (0) | 1.00 | 1.00 | 1.00 | 1,270,904 |
| Fraud (1) | 0.98 | 0.79 | 0.87 | 1,620 |
Accuracy: 1.00
Macro Average: 0.99 | 0.89 | 0.94
Weighted Average: 1.00 | 1.00 | 1.00
π Test the Model
Access the Hugging Face Space to test fraud detection interactively:
π Test Here
Inference Providers NEW
This model isn't deployed by any Inference Provider. π Ask for provider support
