Combination of BP Neural Network and Logistic Regression its Application

Both BP neural network and logistic regression are widely applied in the field of nonlinear relationship analysis. This paper combines the logistic regression model and BP neural network for small sample prediction to establish a new nonlinear fitting model and apply it to practice. The new model effectively extracts the main control variables under multi-factor interference. The accuracy of the prediction model is further improved, which is highly consistent with the significance test of logistic regression.