WTW has announced the launch of the latest version of its Radar pricing software. Radar 4.15 introduces a “market-first” capability that makes it easier for insurers to benefit from the predictive power of machine learning without sacrificing the ability to accurately interpret the outcomes of increasingly complex models, the company said.
“The innovation underpinning Radar 4.15 is groundbreaking, for the first time giving insurers access to state-of-the-art, speed-to-accuracy performance that goes hand-in-hand with unrivalled levels of transparency,” said Serhat Guven, managing director at WTW. “Technological advances will inevitably continue to reshape the insurance landscape, yet it will only be possible to harness the full potential of these technologies if customers and regulators trust they are being used by insurers responsibly.”
AI-based and machine-learning tools have the benefit of higher predictive performance and accelerated speed to market – yet, by their nature, they are more complex and less transparent, preventing the user from fully understanding the model they are creating, WTW said. This “black box” nature can pose significant risks if deployed without due caution, including amplifying bias risks that lead to discriminatory decisions. Regulators are rapidly running out of patience for pricing that is perceived to be unfair, WTW said.
“Radar 4.15’s powerful new algorithm addresses the black-box limitations of machine learning by offering insurers a ‘best of both worlds’ solution that combines the pure predictive power of the machine learning approach of gradient boosting with the exceptional interpretability and transparency of generalised linear models,” Guven said.
Other updates in Radar 4.15 include enhancements to Radar Base and Radar Workbench.