Predictive Analysis of Urban Population Growth Using Least Squares Regression

Abstract

The growth of urban population is a significant topic in the context of sustainable development, urban planning, and utilization of resources. Efficient prediction models are crucial for planners and governments to make decisions upon. This study gives a quantitative prediction of urban population growth using the Least Squares Regression (LSR), which is a fundamental tool in statistics and predictive modeling. Drawing on past urban population figures of major metropolitan cities from genuine official records, this work applies LSR to forecast population trends with a solid mathematical framework. We derive the full-theory backed regression model and tune it with real information from the World Bank and United Nations databases. The research finds that LSR provides an accurate approximation for short- to mid-term population prediction when the linearity of data is preserved. The research also determines the accuracy and error margin of the model prediction using Root Mean Square Error (RMSE) and R-squared values. The research reveals how mathematical modeling—here regression—can be helpful for the solution of urbanization issues when applied to real-life demographic statistics.