Bringing The Power of AI to Insurance
We create tools that incorporate the power of machine learning into your existing pricing process.
Our Vision
Soteris delivers AI-based pricing software to the insurance industry. We are working hard to revolutionize the entire insurance value-chain and would love to stay in touch with updates.
The Technology
Our first learning system understands the complicated combinations of factors that drive your insurance risk - at a level of complexity beyond which humans can see - then uses what it has learned from your existing data to score both current policies and future submissions to help you triage and price them.
As a test, we fed this system a set of actual insurance policy and claim data, then asked it to 'score' a separate set of policies it had never seen before. Each policy's score represents the system's estimate of the probability that the previously-unseen policy would lead to a claim. To test its predictive accuracy, we then sorted those policies top-to-bottom based solely on the assigned score and split those policies into ten equal-sized buckets, best scores to worst. We then calculated the eventual claims rate for each bucket. The graph below displays the result -- the Soteris scoring system demonstrates a clear ability to predict which policies are likely to lead claims, and which ones are not.
Our software has demonstrated the ability to raise our customers' profitability **over 60%**.
« Best Scores
Worst Scores »
Who We Are
Sunit N. Shah, Ph.D.
Dr. Shah entered the insurance industry in 2005, spending six years building pricing models for life insurance. He subsequently joined the $16 billion hedge fund firm Pine River Capital Management in 2013, where he priced risk within financial markets as the second-in-command on the macro and commodities trading team. While there, he spent two years building a reinsurance company from the ground up. He is an author of Behavioral Finance and the Principal-Agent Problem in Finance. Prior experience includes the Boston Consulting Group and adjunct faculty positions at the University of Virginia. He received his Ph.D. in Economics from the University of Virginia, focusing in Econometrics, Finance, and Game Theory.
Founder & CEO
Hao Xia
Mr. Xia is a seasoned engineering leader, with over a decade’s experience in building mission-critical software systems. He cut his teeth at Microsoft, where he worked on the distributed components and protocols that guaranteed the high availability of SQL Azure, and was the co-inventor of two US patents. He then joined Optimizely’s Backend team, responsible for the data infrastructure and pipelines that were processing billions of events per day, powering Experimentation and Personalization at scale. Realizing how much latent signals lied in those data, he later started and led the Machine Learning team at Optimizely, and launched Recommendations, Stats Accelerator, and Adaptive Audiences over the years. Most recently, he was leading the Service Infra team at Flexport, supporting the engineering-wide re-architecture and SOA migration initiatives. Mr. Xia has a M.Sc. in Computer Science from McMaster University with a focus on Optimization and Game Theory, and a B.Eng. in Computer Software from Tsinghua University.
Backend Engineering Lead
Wei Ling Heng
Ms. Heng's background is in Product Management and Business Strategy. She built her product chops at LinkedIn and Atlassian, where she focused on human-centered product development. At LinkedIn, she was on the founding teams of new B2B product lines and launched new products, including Pages, Pipeline Builder and Talent Insights, helping customers to more effectively reach and engage users. More recently, as a Product Manager at Atlassian, she led the Confluence mobile team and built the roadmap to increase mobile user acquisition and innovated on the user experience during COVID-19. Other relevant experiences include Product Marketing at Microsoft as well as strategy roles at Bain & Company. She holds a B.A. in Economics from Stanford University.
Product Lead
Wei Hao, Ph.D.
Dr. Hao's background is in statistics and machine learning research, with a specific focus on problems in the applied sciences. As a graduate student, he worked on developing novel and scalable methods in the field of genomics for understanding the genetic architecture of heritable traits such as disease risk. He was previously a data scientist at Google, where he worked on machine learning problems for multiple areas of Google Assistant. He holds an A.B. in Physics and a Ph.D. in Computational Biology, both from Princeton University.
Machine Learning Engineer
D. Scott Phoenix
Mr. Phoenix is the co-founder and CEO of Vicarious, which does fundamental scientific research into the nature of intelligence with the goal of building machines that exceed human intelligence. He is an advocate for the development of safe AI and a leading signatory on the Future of Life Institute's Open Letter on Artificial Intelligence. Before co-founding Vicarious, Mr. Phoenix was CEO of Frogmetrics (Y-Combinator S2008), Entrepreneur in Residence at Founders Fund, and CXO at OnlySecure and MarchingOrder. Mr. Phoenix earned his BAS in Computer Science and Entrepreneurship from the University of Pennsylvania.
Advisory Board - Co-Founder & CEO, Vicarious
William Jewett
Mr. Jewett has over 30 years of experience in the insurance and reinsurance industry. Until May of 2012, Mr. Jewett was President and Board Member of Endurance Specialty (NYSE: ENH), a Bermuda-based insurance and reinsurance company. Prior experience includes Converium Reinsurance, Centre Re, NAC Re, and Prudential Re. He earned his BA in History and Science at Harvard University and his MBA from The Wharton School at the University of Pennsylvania.
Advisory Board - Former President, Endurance Speciality Holdings
Join Soteris
Loading openings...
The Power of AI in Insurance
Over time, we plan to revolutionize insurance across the value-chain.
- Our tools rank incoming submissions so your underwriters can focus on the best ones.
- Our tools deliver modernized pricing using state of the art machine-learning techniques.
- We plan to develop solutions to detect fraud/slippage within claims.
- Our systems will allow your business to streamline its claims processing.
Our Investors
YCombinatorEarly In: AirBnb, Dropbox, Stripe
AmplifyEarly In: DataDog
KhoslaEarly In: Square, Lookout
FoundationEarly In: Netflix, LendingClub
Data CollectiveEarly In: Square, Elastic, PlanetLabs
WINEarly In: Applovin, Okta, Pagerduty
ClocktowerEarly In: Chime, Tala, Steady
Want to connect?
Whether you are interested in seeing a demo of our technology, partnering for a proof-of-concept, or just learning more about Soteris, we would love to talk.