Machine learning is a class of non-linear estimation techniques that leverage modern development in computing power. However, most models in the course still require heavy mathematics for deeper understanding and precise application on specific business situation.

The course covers basic classification models, such as linear and non-linear regressions along with Logistic and Probit models. A departure from linear format model will touch Support Vector Machine (SVM) and Decision Tree models. Along with data grouping techniques such as K-means and kNN, students are given how to leverage Ensemble modeling.

The second part of the course mainly focuses on Principal Component Analysis (PCA), a special case of Factor Analysis (FA), which will be extended to generalized non-linear models. Such hidden factor finding idea will be applied to recommendation engine and pattern recognition.

PCA and FA are necessary requirements for Deep Learning, and recommendation engine is for Reinforcement Learning.