Presto

As a risk predictive tool PRESTO
is the first of its kind

PRESTO goes beyond traditional risk tools that offer static assessments based on historical data.

It dynamically understands and predicts risks by considering various attributes that influence risk levels, offering prescriptive recommendations to proactively address potential events.

PRESTO employs machine learning algorithms to assess and manage individual workers’ Occupational Health and Safety risks, taking into account past incidents, training history, and years in the position.

Additionally, it considers real-time factors such as weather conditions, the worker’s physical state (monitored through wearables), social media interactions, and implicit risks associated with specific operations to provide a comprehensive risk assessment.

PRESTO calculates a numeric risk index based on its assessments.

When this index surpasses a predefined threshold, the system triggers alerts and suggests preventive actions to mitigate incidents in situations where the risk level is considered excessive.

PRESTO calculates a numeric risk index based on its assessments.

When this index surpasses a predefined threshold, the system triggers alerts and suggests preventive actions to mitigate incidents in situations where the risk level is considered excessive.

Talk to our Team

Learn more about the range of our services.

Safety & Sustainability

Data Discovery and Analitycs

PRESTO represents a leap in industrial safety for the railway sector, specifically tailored to the needs of Italy’s leading railway engineering company.

In the demanding and dynamic environment of railway engineering, PRESTO’s predictive capabilities are pivotal. The tool harnesses real-time biometric data to craft risk indices, providing a nuanced understanding of workplace hazards. This digital advancement ensures heightened worker safety by anticipating potential incidents, thereby embedding a culture of prevention over reaction.

prestoData Discovery and Analitycs

How to make sense of your safety and sustainability data sets?

Using our 100+ years’ combined expertise and applying artificial intelligence and machine learning techniques we will provide useful insights for your safety and sustainability management and support your performance improvement.

ADAM provided data discovery and anaytics services to several large manufacturing companies to identify incident patterns and improve data management for prevention.
br> ADAM supported Finscience in the definition of an alternative ESG score to help investors and companies looking to measure sustainability performances.

Case Study

Presto application to a railway construction site

From November 2021 to November 2022, Italferr, alongside Elettri-Fer and Salc, trialed PRESTO to enhance on-site safety. The approach involved comprehensive initial assessments, including a review of work plans and extensive field observations. Workers were integral to the process, from initial consultations about the project and devices to providing vital feedback on the system's efficacy. By leveraging wearables and IoT systems, PRESTO offered a dynamic predictive model that informed decision-making, minimized human error, and cultivated a secure working environment. The tangible benefits were seen in improved risk communication and a more informed, safety-conscious workforce.

PRESTO may represent a leap in industrial safety for the railway sector, specifically tailored to the needs of Italy’s leading railway engineering company.

In the demanding and dynamic environment of railway engineering, PRESTO's predictive capabilities are pivotal. The tool harnesses real-time biometric data to craft risk indices, providing a nuanced understanding of workplace hazards. This digital advancement ensures heightened worker safety by anticipating potential incidents, thereby embedding a culture of prevention over reaction.

Safety data analytics

We helped a large chemical company based in Italy to understand where there is room to improve their safety management and performance based on their past incident and near miss data. In the data discovery phase we used rule based techniques and topic mining algorithms to develop insights to prioritise future safety programs and initiatives.

References & collaborations

Research