Description

This project focused on using machine learning to analyze historical weather data from European weather stations, with the goal of improving weather prediction accuracy for ClimateWins. Key tasks included data preparation, exploration, and optimization to refine predictive models. Techniques used involved supervised learning models such as K-Nearest Neighbor, Decision Trees, and Artificial Neural Networks, as well as optimization with gradient descent. Findings were summarized with visualizations and presented to support ClimateWins' objective of forecasting weather and extreme events more accurately.

Topics Covered

Machine Learning, data optimization, supervised learning, gradient descent, K-Nearest Neighbor, Decision Tree, Artificial Neural Network, model evaluation

Tools Used

Anaconda, Jupyter Notebook, Python