Deployed a real-time loan default risk prediction system as a Streamlit app, integrating multiple models (Random Forest, XGBoost). Implemented data preprocessing and feature engineering to improve model accuracy. Used Retrieval-Augmented Generation (RAG) to fetch relevant resources based on user input, which were then passed to GPT to generate clear, human-readable risk explanations. CI/CD enabled via GitHub Actions, with Dockerized deployment on AWS for scalability and reliability. Designed a user-friendly interface for effective risk assessment.
Using the dataset, finding the factors that influence price negotiations while buying a house.
Cardiovascular diseases are the leading cause of death globally. It is therefore necessary to identify the causes and develop a system to predict heart attacks effectively. The data below has information about the factors that might have an impact on cardiovascular health.
Identifying the causes and develop a Machine learning model that predicts heart attacks effectively.
Facial recognition is a biometric alternative that measures the unique characteristics of a human face. Applications available today include flight check-in, tagging friends and family members in photos, and “tailored” advertising.
Developing a facial recognition program with deep convolutional neural networks.