Update README.md

README.md

@@ -10,55 +10,98 @@ tags:
 pinned: false
 short_description: Streamlit template space
 ---
-# 💳 Credit Card Fraud Detection – Streamlit App
+# 💳 Credit Card Fraud Detection
 
-An end-to-end Machine Learning project for detecting fraudulent credit card transactions.
+Real-time fraud detection using Machine Learning and an interactive Streamlit dashboard.
 
-🚀 **Live demo:** [HuggingFace Space link]
+## 🚀 Live App
+👉 [HuggingFace Space link]
 
 ---
 
 ## 📌 Problem
 
-Credit card fraud detection is a highly imbalanced classification problem where fraudulent transactions represent a very small percentage of the data.
+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 correctly identify fraudulent transactions while minimizing false positives.
+The goal is to:
+
+- Detect fraudulent transactions
+- Minimize false negatives
+- Provide real-time predictions
 
 ---
 
 ## 📊 Dataset
 
-- European cardholders dataset
-- PCA-transformed features (V1–V28)
-- Time & Amount
-- Highly imbalanced
+Source: Kaggle – Credit Card Fraud Detection
+
+### Features
+
+The dataset contains:
+
+- **Time** → seconds since first transaction  
+- **Amount** → transaction value  
+- **V1 – V28** → PCA-transformed anonymized features  
+
+### 🔐 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 **V1–V28**
+
+These components:
+
+- Are **not directly interpretable**
+- Capture the **underlying transaction patterns**
+- Retain the information needed for fraud detection
+
+In other words:
+
+> V1–V28 are orthogonal principal components representing the variance of the original feature space while ensuring data anonymization.
 
 ---
 
-## ⚙️ Model
+## 🧠 Model
 
-- Algorithm: *(fill in — Logistic Regression / Random Forest / XGBoost)*
-- Evaluation metric: **ROC-AUC**
-- Trained on balanced data using proper preprocessing
+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
 
 ---
 
-## 🖥️ App Features
+## 🎯 Streamlit App Features
 
 ### 🔍 Prediction
+
 - Manual transaction input
 - Random transaction generator
 - Fraud probability score
-- Real-time prediction
+- Adjustable decision threshold
+- Downloadable prediction report
 
 ### 📊 Model Insights
+
 - ROC Curve
 - Confusion Matrix
-- Feature Importance
+- AUC score
+- Feature importance (tree-based models)
 
 ---
 
-## 🧠 Tech Stack
+## ⚙️ Tech Stack
 
 - Python
 - Scikit-learn
@@ -68,17 +111,27 @@ The goal is to correctly identify fraudulent transactions while minimizing false
 
 ---
 
-## 📈 Key Learnings
+## 🧠 What I Learned
 
 - Handling imbalanced datasets
-- Fraud detection strategies
-- Model evaluation with ROC-AUC
-- Deploying ML apps using Streamlit & HuggingFace
+- 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
 
 ---
 
-## 🚀 Run Locally
+## 🚀 Future Improvements
+
+- SMOTE / class weighting
+- XGBoost / LightGBM
+- SHAP explainability
+- Real-time API deployment
+
+---
+
+## 👤 Author
+
+Beyza Topbas
 
-```bash
-pip install -r requirements.txt
-streamlit run src/streamlit_app.py
+Machine Learning Portfolio Project