Welcome!

Summary In this project, I explore how graph theory can provide insight into this year’s NBA season. After scraping data from the official NBA statictics webpage, I create Assists Networks by connecting team players through their mutual assists in undirected network graphs. I also created an interactive python dash application to visualize As... Read More

Food, water and housing are fundamental requirements for daily living. Sadly, it has been estimated that around 600 million people globally are exposed to serious health risk due to poor housing, with children being particularly vulnerable. Adequate housing with access to water supply, sanitation and ventilation has long been considered essentia... Read More

Summary As part of the EPFL Machine Learning class, this post aims to report the procedure that led us to the implementation of a deep residual U-Net to extract roads from aerial satellite images. After implementing several machine learning models ranging from classical classification models to neural networks, deep residual U-Nets yielded th... Read More

Summary In this project, I try to detect topics among Quora questions through unsupervised Natural Language Processing machine learning methods. Using textual data from more than 10 000 questions, I implement a Latent Dirichlet Allocation model and fit it to the pre-processed questions. After tuning the model for the optimal number of topics ... Read More

Summary Introduction Forecasting is a technique that uses historical data as inputs to make informed estimates that are predictive in determining the direction of future trends. Businesses utilize forecasting to determine how to allocate their budgets or plan for anticipated expenses for an upcoming period of time. This is typically based ... Read More