Introduction

In the previous chapter, we concluded our examination of the response variable, and developed a few example machine learning models using scikit-learn. However, the features we used, EDUCATION and LIMIT_BAL, were not chosen in a systematic way.

In this chapter, we will start to develop techniques that can be used to assess features one by one. This will enable making a quick pass over all the features to see which ones could be expected to be useful for predictive modeling. For the most promising features, we will see how to create visual summaries that serve as useful communication tools.

Next, we will begin our detailed examination of logistic regression. We'll learn why logistic regression is considered to be a linear model, even if the formulation involves some non-linear functions. As a key consequence of this linearity, we will see why the decision boundary of logistic regression could make it difficult to accurately classify data. Along the way, we'll learn how to write...