Scenarios for Mobility Improvement Based on Individual Socioeconomic Factors

Abstract

This research investigated various factors related to different mobility improvements based on individual socioeconomic variables. In this study, two sustainable mobility scenarios have been suggested to be implemented in the Central Business District (CBD) area, in which the traffic situation is severely congested. These new mobility improvements are vehicle-free zones and congestion pricing. The two options have been studied and investigated using the binary decision tree method. The main aim of the study is to identify which mobility options are preferred by different groups of people in the city. This will reveal public opinion about the future change in mobility in the city. With the help of the Python programming language and the idea of machine-learning represented by the Decision Tree method, several trials were carried out to get the desired and accurate outcome from the public participation. The study findings showed that the "age" and "gender" variables are significant decision-making factors, whereas the number of trips and mode of transport have no effect on the choice set

Exploring traffic accidents patterns: Spatial distribution and socio-economic determinants

“…The decision tree algorithm was implemented using Python programming to classify the drivers based on their accident history and socio-economic characteristics. The decision tree algorithm is a supervised classification technique that utilizes predictive attributes or features to anticipate the class variable [19][20][21] .…”