Machine learning-Predicting numerical data: regression

Linear regression

Pros : Results are easy to understand and computationally uncomplicated

cons : Poor fitting of non-linear data

applicable data type : numeric and nominal type data

The goal of regression is to predict the target value of the numerical type. The most straightforward approach is to write a calculation formula for the target value based on the input. This formula is the so-called regression equation (regression equation), wherein the parameters are regression coefficients , the process of finding these regression coefficients is regression .

The return is generally referred to as linear regression (linear regression).

The matrix form of a unary linear regression can be written, which is noise , B is the regression coefficient (slope)

　　

Or, where Y, X, A, are n-dimensional vectors , and B is a scalar. Because this is a feature.

If it becomes a D-dimensional attribute, then B is a D-dimensional vector made up of regression coefficients, and x becomes the matrix of Nxd , which can be written as

　　

Or, where x is the matrix of NX (D+1) (the first column element is 1, the remaining columns are X1...XN), and W is the vector of (d+1) X1

Machine learning-Predicting numerical data: regression