Why AI is the future of underwriting
Purpose-built artificial intelligence (AI) technologies offer huge benefits for underwriting effectiveness and enabling scale at a lower cost. Laila Beane, chief customer officer and head of consulting at Intellect SEEC, will lead delegates through these benefits in Intelligent Insurer’s Underwriting Innovation USA online conference running from November 10 to November 12.
Intellect SEEC is an insurtech provider for commercial insurance that delivers enhanced underwriting processes for its clients through its suite of interrelated products. These include Magic Submission, which uses machine learning models and third party data sources to reduce intake cost, improve data quality and risk data footprint of broker submissions; Risk Analyst, which provides comprehensive risk insights and predictive scores on any entity; and Xponent, for underwriting efficiency and collaboration across underwriters, brokers and risk specialists.
“We look at the underwriting process very differently: from the point of broker submission.”
Here, Beane outlines what she will be discussing during the conference.
What are the main points you aim to address in your presentation?
We’ll look at the way underwriting is done, examining the whole process very differently to show how to improve combined ratios, improve underwriter effectiveness and manage portfolios much more effectively.
What will be your special areas of focus?
I’m going to focus on an alternative way of looking at new busines and renewals and ensuring a profitable portfolio. I’ll discuss ways to automatically match appetite up front and route through STP, so the underwriter focuses only on a small subset of high value or complex cases.
We’ll look at machine learning and AI technologies that can make human-like judgement calls. We’ll examine the risks of a renewal account. For example, given the current economy, how do you predict whether the good customer of the past is a good customer for you to renew?
What sort of solutions do you offer in relation to this, and how has the industry responded?
The first thing we introduced was our collaboration workbench and dynamic data packages to suit varied carrier use cases. We can create new data packages in less than a week.
Our latest product introduced into the North American market, Magic Submission, does AI extraction and enrichment across all document types, all structures, purpose-built for all commercial lines. A core feature is its capability to extract contextually from infinite versions of Excels, understand and convert free text to ISO and NAICS.
It extracts, validates, enriches, integrates and offers a simple user interface for exception handling, with all supporting information at the user’s fingertips. Our capability to bring innovation and technology contextually to commercial lines has enabled our products to gain a lot of traction in the industry.
How do your solutions help with underwriting?
We look at the underwriting process very differently: from the point of broker submission, our AI models automatically understand what the broker is requesting and extract information from the email and bundled documents such as PDFs from broker submissions.
It’s a matter of intelligently extracting key pieces of data across varied document types and from subset documents and providing one combined output in 87 percent less time, with key information validated and additional risk insights provided.
From an additional risk insights perspective, we look at factors around company, location and person. Examples include credit rating, vehicles they own, investors, sentiment of employees and customers, hazards, frequency and type of safety violations, building and property information, environmental, crime, neighbours, subcontractors, litigations—multiple factors that give you some predictors of loss in the future.
We draw on 8,000+ data sources, contextualise key information and provide Intellect Scores and Grades with substantiating evidence—so we cut down the underwriter’s time by 50 to 60 percent while giving them insights they may not otherwise have had. This also enables STP when appetite is matched up front.
What do you hope attendees get out of your presentation?
Improving combined ratios by looking at underwriting in an innovative way. Leveraging AI and taking a data-first approach—from broker submissions to quote and bind; profitably rebalancing their portfolios at time of renewal; and ways to proactively target selective risks for higher underwriting profitability.
What steps do they need to take to get there?
Depending on the maturity of the carrier in AI technologies, it may be prudent to take small steps, prove and then scale fast. With COVID-19, changes to our economy and workplace have caused higher focus on innovative thinking and transformative strategies.
New risks are continuously emerging and insurers need to revisit their best-suited appetite and segments. On an operational front, reducing the cost to quote and bind, and improving the speed to respond to brokers are a key focus, since brokers generally submit the same business to multiple carriers.
The biggest challenge we have seen is not how or where to start, but changing the mindset of people who are reluctant to adopt AI. Carriers are still figuring out effective change management across the organisation and geos.
Laila Beane is one of the speakers at Intelligent Insurer’s Underwriting Innovation USA a virtual event addressing how to accelerate underwriting profitability in a world of changing risks, taking place between November 10 and 12, 2020. Full details can be found here
