Urban modeling of shrinking cities through Bayesian network analysis using economic, social, and educational indicators: Case of Japanese cities.

Abstract

Shrinking cities due to low birthrates and aging populations represent a significant urban planning issue. The research question of this study is: which economic, social, and educational factors affect population decline in Japanese shrinking cities? By modeling shrinking cities using the case of Japanese cities, this study aims to clarify the indicators that affect the population change rate. The study employed Bayesian network analysis, a machine learning technique, using a dataset of economic, social, and educational indicators. In conclusion, this study demonstrates that social and educational indicators affect the population decline rate. Surprisingly, the impact of educational indicators is more substantial than that of economic indicators such as the financial strength index. Considering the limitations in fiscal expenditures, increasing investment in education might help solve the problem of shrinking cities because of low birthrates and aging populations. The results provide essential insights and can function as a planning support system.