Analyses of Daily COVID-19 Cases Across Nations

In this project, I fitted a logistic growth curve to model the COVID-19 cases data and estimated parameters by gradient descent. The growth curve formula was transformed to obtain the initial parameters for optimization. I implemented both the Gaussian Mixture Model with the EM algorithm and the K-means algorithm to cluster the estimated parameters for each country. The association between growth modes and countries was investigated by comparing and analyzing the resulted clusters.