SELECTED WORK / CASE STUDY
Fraud Detection System
Machine learning model for detecting fraudulent credit card transactions
Project Overview
Built an fraud detection system using logistic regression to identify fraudulent credit card transactions. The model analyzes 28 anonymized features (V1-V28) and transaction amounts to classify transactions as legitimate or fraudulent.
This project uses the dataset from Kaggle - Fraud Detection Database.
Python
Scikit-learn
Pandas
NumPy
Streamlit
Logistic Regression
Random Forest
XGBoost
SMOTE
Class Weight
Application Demo
Best Model Performance
Accuracy
0.9995
Precision
1.0000
Recall
0.7263
F1-Score
0.8415
ROC-AUC
0.9564
Average Precision (AP)
0.8423