Key points
Organisational safety is often seen as a burden of regulatory requirements, or post-event reporting of accidents.
Projecting data analytics means companies can be proactive, preventing incidents from happening in the first place.
Multiple sources of data can be combined to generate insights that help workplaces tailor their safety efforts and create business efficiencies.
In Australia Last year, about 104K people were the subject of major injuries at work and about 182 people died in a work-related fatality. Workplace health and safety is serious, yet so often it is treated as a reporting requirement: necessary, fulfilled, but ultimately reactive.
Reports on incidents that have happened tell a business how successful they have been at protecting their employees, but hardly much more.
What if it were possible to be better equipped to understand why incidents are happening in the first place and actively employ strategies to prevent them?
What if safety goals could be aligned to the organisational goals? This is already possible and can be adapted by your organisation with the help of a wider range of organisational datasets and advanced predictive analytics.
Reporting of safety in the workplace
Usually, the reporting of workplace incidents widely rest on the Health, Safety and Environment (HSE) or HR functions. While businesses are improving at prevention, for the most part, indicators of safety remain post event.
Anyone who has filled out an incident log knows the hollowness of the process. From this, an organisation can see what happened, to whom, and at what time. Viewed in totality, they may be able to see some patterns, but not always.
Gap indicators for example how many accidents have happened in the last month do little or nothing in order to keep people alive in future events. Instead, assumptions and hypotheses are applied to suspected problems. Sometimes they are correct and often they are not.
Using analytics to develop an understanding
In general, organisations are not good at using the data sources they have available, and even worse when it comes to using highly complex analytics methods, to gain understanding. An evolution from simple to sophisticated data analytics use can be viewed as a maturity curve.
Maturity curve
Organisations at the very basic, normally just report on safety incidents. The descriptive analytics applied to this data is simple but may reveal areas, teams, staff or equipment that are problematic or hazardous.
At the next level, organisations doing analysis on “why this has happened” analytics are merging datasets.
Usually, this is the initial incident data combined with other HR or payroll data. This can highlight correlations between employee behaviour (say nonattendance) and workplace accidents.
More sophisticated businesses use “what will happen” analytics. Here, HR and incident data is augmented with operational, equipment or external data. This level of information, based on large datasets, provides unique insights and actionable findings. Not only can these organisations see what happened during an accident, they can further understand the factors that contributed to the incident occurring in the first place.
Lastly, there are organisations who are engaged in “what should we do”, or optimisation, analytics. These data-savvy organisations benefit from predictive analytics insights and use them to optimise safety functions, making the best possible decisions based on resourcing, operational constraints and organisational goals.
Safety Outlook and analysis
In Australia, most organisations are still at the first step of maturity. Imagine what a company could accomplish if it was using predictive and prescriptive analytics to action its safety efforts?
Some energy industries provide great examples of what the power of data analytics can do when it came to safety on its sector. Some engage with Morshona to understand how to leverage and analyse business and safety data to predict, prevent and report on potential increases and decreases in safety risk.
By using machine learning tools to analyse the sensor data from the power generators and combining that with contractor data and weather information, we were able to highlight a previously unknown link between the generators and the chances of incident.
Actually, accidents were almost two times as likely near generators. Being able to analyse this information further, which would not have been possible from simple incident reports, the energy provider could understand the root causes and improve safety to reduce the number of incidents occurring.
The value of a deep dive
Likewise, our work with another organisation into the causes of heavy vehicle-related safety focused on more than just the number of truck accidents. The company, which has thousands of trucks on the road and sites as part of its fleet, viewed safety incidents involving an employee or a third party as one of its biggest company risks.
By analysing Truck GPS data along with technicians’ sourcing dispatch system and other field workforce data, we were able to identify the risk factors for serious incidents. For instance, technicians interacting with their source dispatch system while operating the heavy machines.
The value of such useful information is that the company can target its response. Rather than paying for a generic safety campaign or intensive training, costs could be significantly reduced by rolling out specific interventions to target specific high risk associates of employees.
Useful steps in improving safety
For businesses that are looking to improve in this area, where to start can be confusing. Here are a few tips:
Find out where your organisation currently sits on the curve. What information is being collated and recorded? What other multiple data sources are available? Where are the cracks? What are the challenges?
Corroborate the value of the data. This could be as simple as starting a small model program and combining HSE data with a few uncommonly used datasets to exhibit the value.
Generate awareness. Ensure those in charge are aware of the model results and what more could be done with additional resources. Align these data insights with business strategy to illustrate organisational value.
Hire people with data skills. Safety can be taught, but sophisticated data analytical skills are best with experience and training.
Safety that speak volumes
By taking a proactive approach to safety, businesses can significantly reduce the number of accidents that occur or prevent incidents altogether.
Using data – not just health and safety data, but all the other multi-data sets that are often created across an organisation – combined with sophisticated machine learning analytics techniques, companies can better understand where the risks are and roll out targeted interventions.
This approach will move safety efforts away from tick-box legislative requirements towards a business practice that drives real benefits and protects people’s lives.
For more information on how to predict and prevent safety in the workplace, talk to Morshona’s HSE Advisory team.
Comments