Credit Card Fraud Detection This project builds a machine learning model to detect fraudulent credit card transactions. It involves preprocessing the data by normalizing features. The dataset is split into training and testing sets, and models like Logistic Regression and Random Forest are trained to classify transactions as legitimate or fraudulent. The model is evaluated using metrics like precision, recall, and F1-score, with a confusion matrix visualizing its performance.
The project uses Python with libraries such as Pandas, NumPy, Scikit-learn, and Imbalanced-learn for data manipulation, model training, and evaluation. Matplotlib and Seaborn are used to visualize the results and assess model effectiveness in detecting fraud.
(https://drive.google.com/file/d/1gdZH-gWNM8SgViSUGC0KKP1MuqLPBpfJ/view?usp=sharing).