Innovation in Actuarial Techniques (Stochastic Modeling) and Actuarial Practices

Background and Purpose

Actuaries have a long history of using stochastic modeling techniques for their work. For example, economic scenario generators have been used for over 10 years in both ERM and ALM. New financial reporting requirements, such as PBR and IFRS17, call for new ways to model insurance risks and heavily rely on stochastic models. Increasingly complicated regulations have made it difficult to perform traditional actuarial functions such as pricing and forecasting using traditional actuarial techniques. While it’s possible to perform first-principles projections of stochastically calculated balances, for many use-cases, model run time and/or compute cost can be prohibitive.

Lately, there has been a keen interest in using predictive models[1] to carry out traditional actuarial tasks. Below is a list of some recent examples sponsored by SOA:

  • A Tour of AI Technologies in Time Series Prediction, by Victoria Zhang
  • Emerging Data Analytics Techniques with Actuarial Applications, by Dr. Marie-Claire Koissi, et. al.
  • Literature Review: Artificial Intelligence and Its Use in Actuarial Work, by Nicholas Yeo, et. al.
  • Cloud Computing and Machine Learning Uses in the Actuarial Profession, by Jonathan Glowacki, et. al.
  • Considerations for Predictive Modeling in Insurance Applications, by Eileen Burns, et. al.

There has also been a fair amount of research into stochastic modeling[2]. Below are some examples:

  • Efficient Dynamic Hedging for Large Variable Annuity Portfolios with Multiple Underlying Assets, by Sheldon Lin, et. al.
  • Efficient Nested Simulation for Conditional Tail Expectation of Variable Annuities, by Ou Dang, et. al.
  • Efficient Simulation Designs for Valuation of Large Variable Annuity Portfolios, by Ben Mingbin Feng, et. al.
  • Fast and Efficient Nested Simulation for Large Variable Annuity Portfolios A Surrogate Modeling Approach, by Sheldon Lin, et. al.
  • Nested Stochastic Modeling for Insurance Companies, by Runhuan Feng, et. al.

We are looking for a research paper that is both practical and futuristic and explores innovation in actuarial techniques and practices, including the potential applications of predictive models for stochastic modeling.

Research Objective

The report should scan the industry for recent developments in actuarial techniques and practices associated with stochastic modeling and predictive modeling, and related applications in the insurance space. We look for a discussion on potential applications and considerations, such as pros and cons of each modeling technique, how to handle a black box solution, regulations, etc. The report should include case studies, with an end-to-end process of utilizing predictive modeling to solve stochastic modeling challenges. Innovations that impact actuarial work but are not related to the core modeling process should be considered out of the scope.

The ideal researcher should have hand-on experience in solving practical business problems with predictive models, understand the concerns of stakeholders, both internal and regulators, and be inspiring to prompt actuaries in adopting innovative solutions.


The proposal should include a definition of scope, how the paper will be approached, the expected number of case studies and if these will be related.

Selection Process

The Actuarial Innovation and Technology Program Steering Committee (AITPSC) oversees the selection of projects. The AITPSC will review each proposal and is responsible for recommending proposals to be funded.  Input from other knowledgeable individuals also may be sought, but the AITPSC will make all final decisions, subject to SOA leadership approval. SOA will provide staff actuarial support to develop and publish the final material.


Any questions regarding this RFP should be directed to David Schraub, SOA Senior Practice Research Actuary (phone: 847-706-3560; email:

Notification of Intent to Submit Proposal

If you intend to submit a proposal, please e-mail written notification by May 15, 2021 to Korrel Crawford (

Submission of Proposal

Final proposals for the project should be sent via e-mail by June 1, 2021 to Korrel Crawford at 

Note: Proposals are considered confidential and proprietary.


The selection of a proposal is conditioned upon and not considered final until a Letter of Agreement is executed by both the Society of Actuaries and the researcher.

The SOA and AITPSC reserve the right to not award a contract for this research. Reasons for not awarding a contract could include, but are not limited to, a lack of acceptable proposals or a finding that insufficient funds are available. The SOA and AITPSC also reserve the right to redirect the project as is deemed advisable.

The SOA and AITPSC plan to hold the copyright to the research and to publish the results with appropriate credit given to the researcher(s).

The SOA and AITPSC may choose to seek public exposure or media attention for the research. By submitting a proposal, you agree to cooperate with the SOA and AITPSC in publicizing or promoting the research and responding to media requests.

The SOA and AITPSC may also choose to market and promote the research to members, candidates and other interested parties. You agree to perform promotional communication requested by the SOA and AITPSC, which may include, but is not limited to, leading a webcast on the research, presenting the research at an SOA meeting, and/or writing an article on the research for an SOA newsletter.

[1] By predictive modeling, we refer to techniques in machine learning and artificial intelligence such as generalized linear modeling, neural networks, etc.

[2] By stochastic modeling, we refer to more traditional techniques of financial modeling doing first-principles projections of assets and liabilities on a stochastic set of economic scenarios.