Predicting Traffic Congestion - Datacity

Predicting Traffic Congestion

Home > Challenges > Predicting Traffic Congestion



How can we use traffic data alongside other types of open data to improve real-time traffic prediction?

Current traffic congestion models are based on traffic engineering theories derived from fluid analysis. As a result, they do not take into account traffic data and are limited in making precise, daily predictions. Road traffic operators do not have short-term prediction models (+/- 15 mins) to precisely manage traffic conditions in real time, nor do they have reliable or useful information on motorists.




  • Use case & expected benefits

  • Available ressources

  • Business Opportunities for Partners

  • Startup Laureate

Use case

The Paris Region Director of Highway Authority (DIRIF) network has different ways of communicating with motorists: dynamic message boards, the traffic information website Sytadin, and a partnership with highway engineers via communication devices linking vehicles and infrastructure. Being able to predict traffic congestion would allow for the implementation of traffic management tools (prioritizing one route over another, for example), and would also reduce the risk of accidents.


Traffic can become congested extremely quickly, greatly reducing the pertinence of traffic information made available to motorists. Consequently, and as a result of traffic jams, real-time commute times can be twice as long as the initial estimates. If they could be informed upstream, motorists would be able to change their route to avoid traffic jams.

Expected Benefits

Immediate client: the highway authority (the DIRIF in the Paris region), to whom alerts of potentially problematic situations will be transmitted. The goal is to improve the information provided to motorists and to improve management of traffic conditions so that motorists can benefit from more complete commuting information.


The DIRIF has a wide range of speed counter and traffic counter databases across its network, which can be installed in and around the proposed area of testing:


  • Since 2013, 2500 data loops across the network have been registering data every 6 minutes
  • Since October 2016, sensors have been monitoring average road speed data across the entire network (2500km)
  • 1000 cameras spanning the entire highway network


DIRIF: data expert Romain Rémésy
SETEC: Perrine Cazes, Project Manager

Experimentation field

A suitable interconnected network: a section of highway where there is a sufficient quantity and quality of DIRIF equipment and available data, as well as sufficient data on average road speed.

For example, here are a few possible highway junctions:

  • the RN118 between the A86 and the RN104;
  • the RN104 between the A6 and the A10;
  • the A6 between the RN104 and the A86;
  • the A86 between the RN118 and the A6;
  • the A10 between the A86 and the RN104.

For the start-up, the objective is to market a tool capable of predicting traffic jams in the short-term. This information will then be relayed to highway authorities (especially on France’s 12,000km of freeways, as well as in and around major cities) and to companies that offer GPS navigation software.

For Setec, an engineering and consulting agency that also works with highway infrastructure engineers, this solution can help clients find answers by working with the start-up and help provide traffic-engineering expertise.


QuantCube Technology is a FinTech company specialized in real-time predictive Analytics based on massive unstructured Data. With the combination of technology, data science and business expertise, the company delivers predictive solutions to major institutions and corporates all over the world, in multiple sectors.

Partners' Experts

Perrine Cazes

Mobility Engineer

Romain Rémésy

Chief of the "Observatory and Traffic Engineering" Department

Arnaud Guillé

Chief of the "Amenities and Tunnels Modernization" Department