Hey, I'm Peter Mangoro Data Analytics Student

A comprehensive machine learning system for detecting fraudulent transactions in mobile money services using unsupervised anomaly detection. Implements Isolation Forest algorithm to identify potentially fraudulent transactions with ~2% accuracy rate.

Developed an interactive fitness tracking application using Streamlit and Python. Features include workout analytics, progress visualization, and personalized recommendations based on user data patterns.

Built a predictive analytics model using machine learning to identify patients at high risk of readmission within 30 days. Utilized patient demographics, medical history, and treatment data to achieve 85% accuracy in predicting readmissions.

Developed a comprehensive market sentiment analysis system using Python and machine learning techniques. Analyzed social media data, news sentiment, and market indicators to predict stock price movements with 78% accuracy.

Conducted comprehensive analysis of traffic violation data using Jupyter Notebooks and Python. Identified patterns in violation types, locations, and time periods to help improve traffic safety and enforcement strategies.