Better traffic predictions

 

 

AI for real-time traffic information

 

Using traffic data alongside other types of open data to improve real-time traffic prediction and take actions to reduce congestion?

 

// KEY RESULTS

 

Thanks to better short term traffic prediction, motorists are able to change their route to avoid traffic jams. Less traffic congestion also means a substantial reduction in green-gas emission and positive environmental impact as well as improved urban well-being.

 

The experimentation took place in Paris.

 

// PARTNERS INVOLVED

Partners provided the following data sets: complete databases of speed counters on the roads with real-time information on traffic circulation, weather data. The selected startup - QuantCube - is a FinTech specialized in real-time predictive Analytics based on massive unstructured Data.

 

 

// PAIN POINT & OPPORTUNITY

 

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.

 

 

 

According to the 2017 Traffic Index, all 18 mega cities have congestion levels over 25% (up to 66% for Mexico, and many cities reaching congestion levels over 80% during evening peaks). Mobility is again a “macro” issue with direct correlation to air pollution but also a city’s attractivity and efficiency.

 

 

 

 

Please reload

A program designed by NUMA in partnership with the City of Paris