What is the principle of logistic regression algorithm?

Logistic regression is a process: faced with a regression or classification problem, the cost function is established, and then the optimal model parameters are iteratively solved by optimization method, and the quality of the solved model is verified by testing.

Although Logistic regression has "regression" in its name, it is actually a classification method, which is mainly used for two classification problems (that is, there are only two outputs representing two categories respectively). In the regression model, y is a qualitative variable, such as y=0 or 1. Logistic method is mainly used to study the probability of some events.

Applicable conditions of Logistic regression model

1, the dependent variable is a binary classification variable or the incidence of events, and it is a numerical variable. However, it should be noted that the index of repeated counting phenomenon is not suitable for Logistic regression.

2. Both residuals and dependent variables should obey binomial distribution. Binomial distribution corresponds to classified variables, so it is not a normal distribution, and then it is not a least square method, but a maximum likelihood method to solve the problem of equation estimation and test.

3. There is a linear relationship between independent variables and logistic probability.

Refer to the above content: Baidu Encyclopedia -logistic Regression