Innovations – Predicting risk project

We’ve been working with partners in construction and artificial intelligence to look at whether using analytic tools could help us to predict risk. By linking the power of artificial intelligence with the mass of safety data held by industry, we’ve uncovered insights and patterns that will save lives on construction sites and in other workplaces.

magnifying glass and papers


To prevent people being injured or killed at work, it’s vital:

  • To detect patterns of behaviour
  • then work to change them
  • and prevent the dangerous occurrences they cause.

Collaborating with these partners has enabled us to uncover meaningful insights and develop predictive models that will lead to better, more effective safety inspections.

Watch our Innovations project video for more information and to meet the team.

Read more about our work on Leading Indicators.

    How to get involved

    Collaborate with us to gain unique insights, build new relationships, take the opportunity to contribute ideas and shape the industry, join a like-minded community, hear about new data analytic techniques and learn how they can positively impact your business and improve health and safety.

    Data-sharing: we aim to develop a rich and diverse data pool with varied sources.  We have developed tools to enable safe, secure and anonymised data-sharing. You can contribute your data to the programme. 

    Industry endorsement: we want to solve real problems, which is why industry involvement and endorsement is key. The first phase of the programme involved extensive industry consultation to shape the projects. It is critical that industry remains involved and continues to influence and shape our work. 

    New ideas: innovation is essential to Discovering Safety and we welcome new ideas for projects, topics or tools. 

    For further details or to express an interest in contributing, please contact the project team at

    Key benefits

    This project aims to deliver tangible health and safety benefits:

    • Demonstrating that predictive analytic techniques can be successfully used in health and safety, to spot patterns of risky behaviour and predict their outcomes
    • Showing how these techniques can work as part of a strategy to promote proactive, preventative health and safety
    • Giving organisations the technical capabilities they need to make this happen, and access to suitable analytic tools.

    The project will allow organisations to make better use of their own data, to improve their health and safety performance, prevent injuries and save lives.