Computational data analysis projects
Applied statistical modeling and unsupervised learning to real datasets as part of computational data analysis coursework.
Problem
Explore how different statistical models behave when applied to noisy, real-world data.
Approach
Built linear regression models with L1 and L2 regularization and tuned hyperparameters via grid search. In a separate project, applied Gaussian Mixture Models to physiological signals such as heart rate and blood pressure to explore relationships with emotional states.
Validation
Evaluated model behavior through error metrics, parameter sensitivity, and qualitative inspection of learned clusters.
Outcome
Practical experience translating statistical theory into working models and interpreting results with appropriate caution.