Timeline: 2017
Team participants: Inon Peled, Francisco C. Pereira, Filipe Rodrigues
Lead Organization: DTU

Research highlights

• Evaluate quality of Floating Car Data product for Danish Road Directorate.
• Analyze data collected over 61 days in 2017 in 1250 strategic road segments.
• Findings show that product performance deteriorates under non-recurrent congestion.

Description

In 2017, the Danish Road Directorate (DRD) considered using a Floating Car Data product, which can observe and predict traffic all over Denmark. Our task was to estimate how reliable and effective the product was. We analyzed data from the product, as gathered from vehicle fleets over 61 days in February-May 2017 in 1250 strategically important road segments. We found that whereas the product mostly provided accurate observations and predictions under normal traffic conditions, the quality of its output deteriorated considerably under non-recurrent congestion — when good quality data was most needed. In fact, under non-recurrent congestion, the product performed similarly to a naive prediction model which simply copied traffic measurements from 30 minutes ago.

Sponsors and Partners

• Danish Road Directorate (DRD)