Noa Zamstein, a senior data science researcher at Earnix in Israel, has won the CAS Ratemaking Prize for her paper, “Enhancing Actuarial Ratemaking with Synthetic Data for Privacy Preservation.” Zamstein presented her paper at the Ratemaking, Product and Modeling Seminar held in Orlando, Florida, on March 10.
Zamstein explores the use of synthetic data to maintain privacy while preserving analytical integrity. She uses a synthetic generation approach based on kernel density estimation. Results demonstrate high fidelity in preserving statistical relationships while enhancing privacy protection. Zamstein concludes that synthetic data offers a viable solution to balancing privacy and utility in actuarial ratemaking. Data and model development can therefore be shared without exposing sensitive information.
This award is presented to the author of the best paper submitted to the Ratemaking Working Group’s call for papers on technology and the ratemaking actuary. Papers are evaluated on originality of ideas, understandability of complex concepts, contribution to ratemaking literature, thoroughness of ideas expressed and timeliness and relevance of the research. This year’s prize is $15,000.
