Modeling and evaluating the residential urban environment perception

Abstract This article discusses the use of machine learning methods for assessing and predicting the perception of urban environment by citizens. The research is based on the analysis of the data collected from social surveys and characteristics of the environment from open sources. The urban environment is seen as a complex system that can be analyzed though the point of view of the urban context. The urban context is formed by the geophisical and social features that forms citizens habitat. At the same time, the perception of the urban environment by citizens depends both on the parameters of the urban environment and on the socio-demographic features of the studied group. The article discusses models for predicting the citizens’ perception of the urban environment and evaluation methods of such models. The authors propose the application of the model on the case of St. Petersburg, Russia.