How to leverage AI and third-party data in catastrophe modelling (378)

InsTech - insurance & innovation with Matthew Grant & Robin Merttens

InsTech

Entrepreneurship, Investing, Business

4.8 • 50 Ratings

🗓️ 26 October 2025

⏱️ 29 minutes

🔗️ Recording | iTunes | RSS

🧾️ Download transcript

Summary

In this special episode of the podcast, originally hosted by Indico Data’s Unstructured Unlocked, Matthew Grant, CEO of InsTech, joins Tom Wilde and Michelle Govea to discuss how insurers are harnessing third-party data and AI to make more informed, efficient underwriting decisions. With over 25 years in catastrophe modelling and analytics, Matthew shares his view on where the real innovation is happening and where insurers are still facing friction. From the rising value of external data sources to the operational impact of generative AI, the conversation is packed with insights that go beyond the buzzwords. InsTech is sharing this episode to highlight the practical challenges and opportunities facing carriers and reinsurers as they modernise their approach to risk. What you’ll learn Why many insurers still struggle to access the most basic risk data What third-party data needs to prove before it’s trusted in underwriting How AI is changing both the speed and depth of catastrophe modelling When it makes sense for carriers to build proprietary models—and when it doesn’t What reinsurers have taught the market about effective model use The quiet power of improving underwriting efficiency, not just accuracy How better data and analytics can help insurers write more risk with more confidence If you like what you’re hearing, please leave us a review on whichever platform you use or contact Matthew Grant on LinkedIn. Discover more episodes of Tom Wilde's and Michelle Gouveia's podcast at Indico Data's Unstructured Unlocked. Sign up to the InsTech newsletter for a fresh view on the world every Wednesday morning. Continuing Professional Development This InsTech Podcast Episode is accredited by the Chartered Insurance Institute (CII). By listening, you can claim up to 0.5 hours towards your CPD scheme. By the end of this podcast, you should be able to meet the following Learning Objectives: Measure the practical value of generative AI in improving underwriting efficiency and catastrophe modelling accuracy. Specify the thresholds third-party data must meet—cost and confidence—before it can support underwriting decisions. Explain how insurers are approaching the build vs buy decision when it comes to proprietary AI models. If your organisation is a member of InsTech and you would like to receive a quarterly summary of the CPD hours you have earned, visit the Episode 378 page of the InsTech website or email [email protected] to let us know you have listened to this podcast. To help us measure the impact of the learning, we would be grateful if you would take a minute to complete a quick feedback survey.

Transcript

Click on a timestamp to play from that location

0:00.0	Hello, welcome or welcome back to the podcast.
0:12.0	Zoya here, and this week we are reversing roles slightly.
0:15.7	Matthew Grant is the interviewee of Indicodace's Unstructured Unlocked Podcast with Tom Wilde and Michelle Gavea.
0:23.4	We felt that on episode 24, our very own Matthew, the conversation was just too good, so we
0:28.9	would like to reshare the insights from his 25-year career in catastrophe modeling.
0:35.2	Together with Tom and Michelle, he explores how carriers really are using
0:39.4	third-party data today, from pulling facts out of submissions without re-kying, to testing
0:45.1	sassolite and LIDAR derived attributes, to deciding when proprietary models beat off-the-shelf
0:50.6	tools. They explore while wildfire and severe connective storms stretched traditional
0:55.6	cat models, how reinsurers and regulators influence adoption, and where early movers can say yes
1:01.9	to risks others avoid. As always, if you enjoy this episode, do check out other podcast
1:07.2	episodes by Indicodea on their website. Hope you enjoy this one.
1:18.1	Welcome to Unstructured Unlocked, a podcast where listeners discover how insurers are entering the
1:23.6	decision era, utilizing artificial intelligence to refine their decision-making processes,
1:29.0	boost underwriting profitability, and achieve premium growth.
1:37.0	Welcome to another episode of Unstructured Unlocked. I'm your co-host, Tom Wilde. And I'm your co-host,
1:42.5	Michelle Gaubeye. And today, Michelle, we've got a great guest, Matthew Grant from Instech.
1:48.5	Matthew's got a really fascinating background in risk modeling.
1:53.0	I'll let Matthew introduce himself, but we have a great topic today talking about how to leverage
1:58.4	third-party data to help in quantifying risk. So, Matthew, welcome to the show.
2:05.7	Thanks, Tom. Thanks, Michelle. It's great to be on the other side of the microphone, and I need to make
2:09.6	sure I don't have bad habits that I ask my guests not to have. Very briefly, I mean, as he said,
	...

Please login to see the full transcript.

Previous episode | Next episode

Disclaimer: The podcast and artwork embedded on this page are from InsTech, and are the property of its owner and not affiliated with or endorsed by Tapesearch.

Generated transcripts are the property of InsTech and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.