Year-3 project carried out in a team of 6 as part of the Introduction to AI module. The goal was to analyze two complex datasets and apply Machine Learning algorithms (in R) to them.
• Regression: predicting a song's release year from audio timbre features (Million Song Dataset).
• Classification: categorizing exoplanets from the NASA catalog.
We carried out a complete exploration of the data (cleaning, handling missing values, correlation matrices) before rigorously designing and evaluating several predictive models. The work is documented in a detailed analysis report that you can read below.