Population Prediction Based on Logistic Regression and Random Forest

Abstract

Due to the continuous improvement of quality of life and more stable social environment, the population is growing rapidly. Among them, population forecasting plays an important role in solving the problems brought by population growth. Based on the data indicators such as population, fertility rate and median age in China’s mainland from 1955 to 2022, the logistic regression model is usually used to predict the future population. This model is trained by Hyperopt to obtain the optimal parameters, it can improve the accuracy of the model. In addition, in order to show the differences between different models, this experiment also used random forest model to predict. The experimental results show that the population growth rate will slow down gradually and reach the maximum population in around 2030, after which it will show negative growth. By calculating the mean square error, it shows that the machine learning model can provide learners with accurate population prediction results.