George Muriithi's Projects
Clustering bank loan customers using KMeans clustering and predicting their loan statuses using XGBClassifier. The prediction model is explained with SHAP values.
An Android mobile app to monitor driver drowsiness.
Interactive visualization of geographical data through choropleth maps, geographical maps and real maps.
An investment portfolio of stocks is created using Long Short-Term Memory (LSTM) stock price prediction and optimized weights. The performance of this portfolio is better compared to an equally weighted portfolio and a market capitalization-weighted portfolio.
House Prices Prediction and Credit Default Risk Prediction competitions. Advanced decision tree-based regression and classification models are used.
Detecting stock market phases using a Gaussian mixture model.
Hospital selection in a population and the TSP with MTZ formulation are solved using Gurobi.
The Korea National Oil Corporation was interested in purchasing shale gas wells from the United States and wanted to predict their production to select wells that maximize profit.
Teslaβs stock price is predicted over some months using an LSTM model. Tweets about Tesla are used to improve prediction accuracy.
This is an end-to-end project in the agricultural domain. A Convolutional Neural Network (CNN) model is trained to detect whether a tomato plant has a particular disease by using a picture of its leaf. The model can be accessed from a mobile application or a web page.