Assessing Modal Shift Readiness for Sustainable Mobility among Potential Private Mobility Adopters Using Machine Learning and Scenario Simulation

Primary data were collected through a structured questionnaire survey in the study area during commute hours (8:30-10:30 a.m. and 6:00-8:00 p.m.) on weekdays, which was electronically delivered (tablets and mobile devices) and collected. This method helped to reduce data entry, transcription errors, and improve data quality. Respondents were selected purposively from residential blocks and workplaces in Sectors I–V to capture diverse socio-economic groups.本研究于工作日通勤时段（上午8:30-10:30与下午6:00-8:00）在研究区域内开展结构化问卷调查以收集原始数据，问卷通过平板电脑与移动设备电子发放并回收。该方法可有效降低数据录入与转录误差，提升数据质量。研究采用目的性抽样方式，从I-V区的居民区与工作场所中选取受访者，以覆盖多样化的社会经济群体。