Build an AI-powered Traffic Safety Guide

Contact: James Hodson,

Short Description: SDG03 aims to halve global deaths and injuries from road traffic accidents by 2030.

Detailed Description: Each year, more than 1.25 million people die as a result of traffic accidents, and between 20 to 50 million more suffer from non-fatal traffic related injuries. This causes substantial physical and economic losses to affected individuals, their families and nations as a whole. According to WHO, the cost of traffic accidents sums up to 3% of GDP in many countries.

Projects will include data mining, machine learning and predictive analytics models and algorithms, applied over static and possibly real-time traffic related data, to be able to detect, visualize and even predict dangerous road sections and conditions. The results will lead towards a traffic safety data management platform and visualization engine, which could be used to assist planners and policy makers to improve the infrastructure. Additionally, the same platform combined with real-time data could be used to develop services for end-users, assessing their real-time traffic safety score and adding a safety related aspect to the routing engines and navigation devices. Successful projects will have the opportunity to present their products in front of city leaders, researchers, and policy-makers at the AI for Good Foundation Global Conference in 2019, and FIA + EuroRap conference on traffic safety in 2019. Depending on results, AI4Good will assist with forming a consortium of partners to bring the research results into real-world service.


Available Data Sets:

– 3 years of Traffic Related Data from the whole country of Slovenia (available on request)

– List of online, real-time live traffic related data from Slovenia (use JSON formatter):

– Star safety rating of EU roads (We need to contact EuroRap) – they have the data and are usually willing to share (1480 traffic-related data-sets from US, including accidents)

– Bureau of Transportation Statistics:

– Live accidents around Houston:

– Collecting your own mobility patterns data using existing mobile apps, or a library to develop your own:

– Road traffic death rates statistics: