I contributed to building the entire machine learning pipeline for the project. My work involved cleaning and preprocessing the dataset, performing feature engineering, and handling imbalanced data using SMOTE. I trained and evaluated multiple models including Logistic Regression, Random Forest, and XGBoost, tuning their hyperparameters to achieve higher accuracy and recall. I also worked on visualizing key insights from the dataset and analyzing performance metrics to choose the best-performing model. This project gave me valuable experience in applying machine learning to real-world fraud detection problems and improved my understanding of data handling, model optimization, and evaluation techniques.
Log in or sign up for Devpost to join the conversation.