From biases to opportunities: leveraging Location-Based-Service (LBS) data for next-generation transportation planning

Location-Based-Service (LBS) data sourced from numerous mobile devices that now accompany people everywhere has the potential to revolutionize the practice of transportation planning in data collection, model development and policy designs. Its potential is however hampered by the lack of transparency on the part of researchers, transportation professionals, and LBS data ven- dors. There is also a dearth of understanding about how LBS data is generated and what the associated data quality attributes are. At the same time, transportation agencies now face over- whelming demand from LBS data vendors globally. The first aim of this paper is to provide an overview of the biases in LBS data. Specifically, we point out the key difference in data generation between LBS and household travel survey (HTS), and present data quality issues and their effects on the resulting mobility metrics that are commonly used in the planning process. We point out that passively-generated LBS data has been found to be unstable over time, sparse within a 24- hour time frame, and have representation biases. The second aim of the paper is to present our perspectives on how LBS data can aid HTS data and transform the field of transportation plan- ning. We lay out four methodological advances (e.g., data pre-processing and HTS and LBS fusion in privacy-aware mobility digital twins) that the community shall pursue to realize the full promise of LBS data. Last and equally important, we discuss ways that the community can collaborate to establish benchmark datasets and standards for trip inference and reporting while adhering to privacy constraints.