Future Prediction of Regional City Using Causal Inference Based on Time Series Data

Abstract

Regional cities in Japan have a lot of social issues. Various measures are being considered to solve these social issues, but it is difficult to ascertain and implement practical and effective measures. In this study, we proposed a new causal inference for selecting indicators that have causal relations with the social issues. If there was a causal relation between two sets of time series data, the slope of the approximation line of the time-shifted correlation coefficients at the base time returned a negative value. The causal inference was verified by using samples of time series data. In addition, we achieved future predictions by the vector autoregressive model using the causal indicators. The model was verified using the actual time series data of 87 regional cities. As a result, it was possible to simulate future predictions and to calculate the effects by introducing practical and effective measures to solve social issues.