In this first post I describe my life's journey and why I want to learn data science

This is the first article dealing with classification problem and discusses logistic regression as a tool to predict qualitative variables.

How to discourage large coefficents in linear regression? How to perform variable selection? These questions are answered in this article.

Concept of train-test-validation split is discussed to improve model performance. In addition, a related concept of cross-validation is discussed.

I introduce regression problem and two simple statistical learning methods to tackle it. These are simple linear regression, parametric model, and K-nearest-neighbor algorithm, non-parametric model.

We will discuss the difference between supervised and unsupervised learning. Furthermore, we will introduce notion of indpendent, and dependent variable for supervised learning.

What is data? What is the best way to arrange it?

What errors arise from conducting a test? What is confusion matrix?