This course provides an advanced foundation in modern statistical and machine learning methods used in data science, covering four major areas: the Expectation–Maximization (EM) algorithm for parameter estimation in mixture and latent-variable models; Support Vector Machines (SVMs) including margin-based classifiers, kernel methods, multi-class strategies, and the Proximal SVM; Multidimensional Scaling (MDS) for visualizing similarity data, creating perceptual maps, and interpreting latent dimensions; and Structural Equation Modelling (SEM), focusing on latent constructs, model specification, estimation, and interpretation. Together, these modules equip students with theoretical understanding and practical skills for analyzing complex data, building predictive models, and interpreting multivariate relationships.
- BCM Teacher: Dona Joseph