Membership / Notices to Members
Publications & Research
Research

Sarvate and Van Oirbeek Win the 2026 Ronald Bornhuetter Loss Reserve Prize

Ronald Bornhuetter Loss Reserving Prize

The CAS is excited to announce two winners of the 2026 Ronald Bornhuetter Loss Reserve Prize: Roger Sarvate, ACAS, a consulting actuary at Taylor & Mulder, and Robin Van Oirbeek, a senior data scientist at Ageas Re. Sarvate and Van Oirbeek will each receive $5,000.

This prize commemorates the work of Ronald Bornhuetter, FCAS (1957) and is given to the authors of the best papers submitted in response to a call for papers regarding reserves. Papers are judged by the CAS Reserves Working Group on the basis of originality of ideas, clarity of presentation, and contribution to the literature on loss reserving.

“These two papers represent the kind of research the CAS is proud to recognize because they both advance the science and practice of loss reserving in meaningful ways,” said Chandrakant (Chandu) Patel, FCAS, chair of the CAS Reserves Working Group.

“Van Oirbeek’s paper creates groundbreaking distribution-based methodology that develops a Negative Binomial Chain-Ladder (NB-CL) model that embeds the Chain-Ladder method within a full likelihood-based framework, allowing for estimating claim count variability. Sarvate’s paper illustrates the use of Bayesian techniques to create a diagnostic and interpretive tool to analyze loss development dynamics, inform reserve model design, and offer additional insight into the drivers of reserve movement.  

The papers provide actuaries with innovative tools to better understand uncertainty, improve reserve estimates, and support more informed decision making. Their originality, technical rigor, and practical relevance make them valuable contributions to the actuarial literature.”

Sarvate’s paper, “Attribution of Loss Development Dynamics: A Bayesian Structural Time Series Approach,” proposes a complementary Bayesian time series framework that treats loss development data as a collection of time series and applies Bayesian Structural Time Series (BSTS) models to decompose observed losses into interpretable components.

Van Oirbeek’s paper, “The Negative Binomial Chain-Ladder: A Full Likelihood Model for Claim Count Reserving,” develops a negative binomial chain-ladder (CL) model that embeds the CL method within a full likelihood-based framework.


Both winners will present their research at the 2026 Casualty Loss Reserve Seminar (CLRS), September 14 to 16 in Las Vegas:

  • Roger Sarvate, ACAS will present at session AR-7, “Understanding What Drives Loss Development: A Bayesian Structural Time Series Approach" on Wednesday, September 16, from 11:00 a.m. to 12:00 p.m. PDT.
  • Robin Van Oirbeek will present at session AR-9, "A Likelihood for the Chain-Ladder: The Negative Binomial Model for Claim Counts," on Wednesday, September 16. The session will be offered twice, from 9:30 to 10:30 a.m. and again from 1:00 to 2:00 p.m. PDT.

Learn more and register for the 2026 Casualty Loss Reserve Seminar at clrs.casact.org.