Sapiens TL
Follow Us



Electronic Chat with John C. Siegman

The insurance industry has always run on data – actuarial tables, driving records, demographic information. But the insurance data field has been revolutionized by technology and the ability to garner data from a wide swath of sources, the diversity of which would have been unimaginable in years past.

Timely, accurate, cost-effective property data is especially important at a time when extreme weather is increasing exposure to wind, hail, tornado, lightning, earthquakes, floods, and wildfires. HazardHub is a third-generation provider of national property-level hazard risk databases, translating huge amounts of geospatial digital data into easy-to-understand answers, providing risk assessments that can be used to make real-world decisions. The company also tracks manmade risks and elements including brownfields, Superfund cleanups, fire hydrant locations, and leaking underground storage tanks.

We spoke with HazardHub Founder John Siegman on how insurance’s reliance on data has changed over the years, and the role of technology in its acquisition.

Insurance has always relied on data (actuarial, demographic, etc.) for basic operations like rating and claims. What new sources are in use and how is insurance using the data?

There are a lot of new data available from IoT, from better geospatial sources, from drones, from social media, from everywhere. The key to all of this information is in being able to easily integrate it and trust it and then make more automated decisions using it. Also, a lot of this new information is complicated.  It needs to be easily explained. Don't mistake simplicity of the explanation for a lack of depth in the information. The use of the data depends on the data itself. Insurers are using our information for prefill, automated rating, marketing and customer education, underwriting and actuary, profitability analysis, and a little bit in claims.

In the past, insurers were challenged with extracting data from their own systems for use. How has insurtech assisted in this process?

Lots of insurers still face that issue as those systems were not designed to be used in the ways that insurers would like to make use of them. Many of our customers establish secondary systems to replicate the base data in their policy admin system but make it more readily available throughout their organization. There are insurtechs that focus on making internal data accessible. We focus on enhancing that internal data to make it actionable.

What are the regulatory and privacy challenges involved in incorporating new data for insurance use?

Everybody gets hung up on this, but it's a lot easier than most companies think it is. Privacy challenges are always a concern with any data that contain personally identifiable information (PII). When you’re using those data, plenty of security procedures have to be in place. That said, there are many good substitutes for PII data. Lots of data, including ours, has no PII. From an ease of implementation, it's always easier to start with non-PII data.

AI and machine learning play pivotal roles in processing large volumes of new data. What other tech tools are changing how insurance uses data?

AI and machine learning require huge amounts of data to be successful in their implementation. Having access to data sources with thousands of variables allows companies to maximize their AI/ML investment. The results of those processes then permeate the organization, from loss/cost models to how a chatbot responds.

How specifically does HazardHub use big data? Has your approach changed in recent years, and how do you see it evolving in the near future?

Our company is big data: Four terabytes of geospatial data, and it will be almost eight terabytes by the end of the year. And we're only focused on one area, geospatial risk. We use a lot of complex data to bring you a simple-to-understand answer regarding any given risk factor. But unlike others, we provide you all of the data that goes into that simplified score. That goes back to regulatory concerns, which are minimal as our customers can explain our scores. Our approach really hasn't changed -- we have constantly been evolving.  More data is better. We understand for a lot of customers there is too much data to implement all at once. That said, our customers can store and keep our data forever. When they have time to explore new data correlations and create new decision trees, the data will simply be there for them to access when and however they need it.


Featured articles


Guidewire MR


The Email Chat is a regular feature of the ITA Pro magazine and website. We send a series of questions to an insurance IT leader in search of thought-provoking responses on important issues facing the insurance industry.


April 5th – 7th, 2020
The Diplomat Resort
Hollywood, FL
Become a member today to receive updates –


only online

Only Online Archive

ITA Pro Buyers' Guide

Vendor Views

Partner News