Comparison Of 6 Machine Learning Models in Estimating Population Growth

Abstract

With the rapidly increasing population globally, it is essential for policymakers to be able to accurately predict or gain an idea of the forecast of population growth to be able to make effective regulations that can benefit the general public. Therefore, the development of a machine learning model to estimate future population growth is crucial. In this article,  various machine learning models such as linear regression, logistic regression, decision trees, random forest, neural networks, and support vector machines are discussed and the benefits and downsides of each are considered. Factors impacting population growth are also discussed to conclude the qualities needed for a model to most suitably perform the task of population prediction. In the end, it is shown that random forest is the best model for this job as it can give a generalized pattern for its results as well as handle complex data types. This paper provides predictions and insights based on machine learning to predict future demographic trends, which can provide useful information for policymakers, researchers, and society in various fields.