Casualty modelling firm Praedicat is mining scientific literature in order to flag up casualty exposures, promising to provide insurers insights into potential liabilities seven years before public awareness and potentially bruising litigation.
That is the word from Bob Reville, CEO of Praedicat who tells Bermuda:Re that Praedicat is mining data from millions of scientific journals in order to identify trends and hypotheses that point to future liability exposures and litigation.
“Every mass litigation that we investigated, was preceded by peer-reviewed science by some number of years. We realised that a hypothesis that some product, chemical, substance or exposure can result in bodily injury first emerges years before general acceptance within the scientific community, before public awareness and before the first litigation.” Praedicat aims to identify these trends and pinpoint liability exposures years before they hit re/insurers.
“The idea was to develop a text-based data mining system that aggregates the results of peer-reviewed scientific literature. The system examines new hypotheses regarding potential casualty exposures and applies analytics and scoring around these results to determine how the science will evolve over time. This is then used to predict where the science will go and create a probabilistic framework around the evolution of casualty exposures.”
As Reville explains, while in catastrophe modelling historical data can prove invaluable in understanding and modelling risk, in the casualty space past losses are not an indicator of future liabilities. “In the liability space there is a fundamental problem with the actuarial approach. After any mass litigation the world changes—companies go out of business and products are removed from market”.
Reville realised that Praedicat would need to take a forward-thinking approach to potential liability threats. This is where the millions of peer-reviewed articles of the US National Library of Medicine come in, delivering the data mined by the firm and ultimately the oversight achieved through its analytics.
Reville says that the company tracks more than 24,000 bio-medical journals, providing it with an unprecedented overview of scientific hypotheses that may ultimately develop its risks in the liability space.
Casualty liabilities being explored by Praedicat include NFL concussions, mobile phones, chemical exposures, electromagnetic frequency exposure, pesticides, plastics and foods, says Reville.
He says that the company has carried out a significant amount of “back-casting”, examining liability claims such as asbestos and Bisphenol A in order to “get a sense of how early a hypothesis emerges in the scientific community versus the point of public awareness, scientific acceptance and claims.”
Reville says that Praedicat can identify the emergence of hypotheses on average seven years before public awareness of casualty exposures emerge. Such insights will prove invaluable to re/insurers.
Reville says that Praedicat has been working with early access clients for a number of years, with their involvement delivering invaluable feedback to its work.
“This is our entire R&D approach. It is a large development effort and frankly it would be disastrous to develop our capabilities in a vacuum and then dump it on the market”. Praedicat’s capabilities have been well-received by participants, he says.
Reville says the hope is that the software will enable re/insurers to better understand liability catastrophe exposures that have a “unique convergence of cat and liability tails”—low likelihood and high pay out, but with claims that may pay out over decades. He adds that he “expects significant innovation in the management of such risks as the analytics develop”.
Reville adds that the company is looking to “develop a comprehensive and scalable solution for identifying emerging risks, supported by footprints in the scientific literature”, with the ultimate objective being a world that is “cleaner, safer and healthier”.
Addressing whether Praedicat will be hosted on RMS(one)—Hemant Shah, CEO of RMS is a director of Praedicat—Reville says that while he would be happy for that to happen, the company is not building its capabilities in that way at this point. “Casualty remains a distinct market”, he concludes.
Praedicat, casualty, insurance, RMS, liability