|
Download README.md from BeyzaTopbas/Credit_Card_Fraud_Detection_App: direct link, hf CLI and curl.
- Browser
- Download file 2.56 kB
-
https://huggingface.co/spaces/BeyzaTopbas/Credit_Card_Fraud_Detection_App/resolve/main/README.md
- Command line
-
hf download hf://spaces/BeyzaTopbas/Credit_Card_Fraud_Detection_App/README.md
-
curl -L -o README.md https://huggingface.co/spaces/BeyzaTopbas/Credit_Card_Fraud_Detection_App/resolve/main/README.md
2.56 kB
| title: Credit Card Fraud Detection App | |
| emoji: π | |
| colorFrom: red | |
| colorTo: red | |
| sdk: docker | |
| app_port: 8501 | |
| tags: | |
| - streamlit | |
| pinned: false | |
| short_description: Streamlit template space | |
| # π³ Credit Card Fraud Detection | |
| Real-time fraud detection using Machine Learning and an interactive Streamlit dashboard. | |
| ## π Live App | |
| π [HuggingFace Space link] | |
| --- | |
| ## π Problem | |
| Credit card fraud detection is a highly imbalanced classification problem where fraudulent transactions represent a very small fraction of the data. | |
| The goal is to: | |
| - Detect fraudulent transactions | |
| - Minimize false negatives | |
| - Provide real-time predictions | |
| --- | |
| ## π Dataset | |
| Source: Kaggle β Credit Card Fraud Detection | |
| ### Features | |
| The dataset contains: | |
| - **Time** β seconds since first transaction | |
| - **Amount** β transaction value | |
| - **V1 β V28** β PCA-transformed anonymized features | |
| ### π Why PCA? | |
| The original transaction data contains sensitive financial information. | |
| To preserve privacy: | |
| - All original features were transformed using **Principal Component Analysis (PCA)** | |
| - The resulting components are labeled **V1βV28** | |
| These components: | |
| - Are **not directly interpretable** | |
| - Capture the **underlying transaction patterns** | |
| - Retain the information needed for fraud detection | |
| In other words: | |
| > V1βV28 are orthogonal principal components representing the variance of the original feature space while ensuring data anonymization. | |
| --- | |
| ## π§ Model | |
| Baseline model trained using: | |
| - Scaled features | |
| - Train/test split | |
| - ROC-AUC evaluation | |
| ### Evaluation Metric | |
| ROC-AUC was used because: | |
| - The dataset is highly imbalanced | |
| - Accuracy is misleading | |
| - AUC measures class separability | |
| --- | |
| ## π― Streamlit App Features | |
| ### π Prediction | |
| - Manual transaction input | |
| - Random transaction generator | |
| - Fraud probability score | |
| - Adjustable decision threshold | |
| - Downloadable prediction report | |
| ### π Model Insights | |
| - ROC Curve | |
| - Confusion Matrix | |
| - AUC score | |
| - Feature importance (tree-based models) | |
| --- | |
| ## βοΈ Tech Stack | |
| - Python | |
| - Scikit-learn | |
| - Streamlit | |
| - NumPy | |
| - Matplotlib | |
| --- | |
| ## π§ What I Learned | |
| - Handling imbalanced datasets | |
| - Why ROC-AUC is better than accuracy for fraud detection | |
| - Feature scaling impact | |
| - Threshold tuning for business use-cases | |
| - Building ML dashboards for real-time inference | |
| --- | |
| ## π Future Improvements | |
| - SMOTE / class weighting | |
| - XGBoost / LightGBM | |
| - SHAP explainability | |
| - Real-time API deployment | |
| --- | |
| ## π€ Author | |
| Beyza Topbas | |
| Machine Learning Portfolio Project |