Distilling actionable insights from big travel demand datasets for city planning

EasyChair Preprint 1346

Abstract

Working towards a more data-informed land use, amenities and infrastructure planning process, the Singapore Urban Redevelopment Authority (URA) harnesses big data and spatial analytics to deepen its understanding of urban activity and mobility patterns. Big travel demand datasets from public transport and ride-hailing services enable planners to observe mobility patterns at a high level of detail for large numbers of users, trips, and trip types. Since August 2018, the URA has been working with leading technology company and ride-hailing operator Grab to understand how daily commute patterns vary between existing and new transport modes, and how the volume of activities in each area evolves across different times of day. This paper describes the novel dataset and analytical techniques utilised to study the relationship between urban activity and mobility. It will also report how spatiotemporal characteristics of the urban environment, such as land use mix, location accessibility, and peak-hour travel demand, influence commutes by different modes in each area. By studying mobility over a range of travel modes, this method of analysis will provide city planners with richer insights to better assess infrastructure requirements for new developments. The findings are also useful for emerging transport providers, who can improve service delivery across short- and medium-term time scales.

Keyphrases: Big Data, Data Science, data analysis, land use planning, ride-hailing, transport modelling, urban planning, urban studies

@booklet{EasyChair:1346,
  author    = {Alvin Chua and Serene Ow and Kevin Hsu and Yazhe Wang and Michael Chirico and Zhongwen Huang},
  title     = {Distilling actionable insights from big travel demand datasets for city planning},
  howpublished = {EasyChair Preprint 1346},
  year      = {EasyChair, 2019}}