To understand the concept of fraud detection in UPI transactions and its importance in the financial sector.
To explore different machine learning algorithms and techniques suitable for handling imbalanced data in fraud detection.
To develop a classification model using machine learning algorithms to detect fraudulent UPI transactions.
To evaluate the performance of the developed model in terms of accuracy, precision, recall, and F1-score.
Review literature on fraud detection in UPI transactions and imbalanced data handling in machine learning.
Collect and preprocess a dataset of UPI transactions for model training and testing.
Implement and tune machine learning algorithms such as Random Forest, Support Vector Machine, and XGBoost for fraud detection.
Evaluate the performance of the developed model and compare it with existing fraud detection methods.
Write a research report documenting the methodology, results, and conclusions of the project.
