Modeling of time use for activities on remote work in provincial areas

Abstract

The purpose of this study is to model the relationship between the time use for activities on remote work and its factors in the provincial areas. Activities include shopping, hobbies, eating out, lessons, and others. Particularly, we focused on partial remote work and access to activities. Therefore, using remote work intention data, not only activity change models but also activity time difference models are constructed for each activity purpose. In the modeling, various machine learning models are applied to compare the learning accuracy. It was verified that applying the RF model to discriminate activity changes increased the estimation accuracy.