In the first part of this chapter, we reviewed trading strategies based on regression machine learning algorithms. In this second part, we will focus on the classification of machine learning algorithms and another supervised machine learning method utilizing known datasets to make predictions. Instead of the output variable of the regression being a numerical (or continuous) value, the classification output is a categorical (or discrete value). We will use the same method as the regression analysis by finding the mapping function (f) such that whenever there is new input data (x), the output variable (y) for the dataset can be predicted.
In the following subsections, we will review three classification machine learning methods:
- K-nearest neighbors
- Support vector machine
- Logistic regression