- Transformer-Based Embeddings: Implemented a transformer-based model to create state-specific embeddings, effectively encapsulating the multifaceted relationships among COVID-19 data features.

- State Clustering: Employed k-means clustering, following dimensionality reduction via PCA and t-SNE, to segment states based on their COVID-19 infection rates, mobility trends, and demographic profiles.

- Correlation Analysis: Conducted an in-depth analysis of the correlation between mobility patterns and COVID-19 statistics using various models including Linear Regression, Lasso, Ridge Regression, and Neural Networks.

- Advanced Modeling: Developed advanced multi-variable regression models and a suite of deep learning models, such as RNNs, LSTMs, CNNs, GNNs, and MLPs, to explore and decipher the complex dynamics between vaccination rates, COVID-19 cases, and mobility trends.