Predictive Modeling in Underwriting - Case Study

Background and Purpose

Predictive modeling is increasingly being used in life insurance underwriting, within fluid-less accelerated underwriting (AUW) programs, in fully underwritten programs and for facultative underwriting.  Predictive models optimize the use of available data to enhance underwriting decisions, predict customer behavior and improve risk selection to better manage mortality.  For the consumer, the automated decisions from these models whether it is an accelerated or fully underwritten policy, provide a consistent and objective underwriting outcome with a quicker turnaround time, thus shortening the time to policy issuance and improving the overall customer experience.

In order to promote a deeper understanding of predictive modeling and how it impacts underwriting, the SOA’s Reinsurance Research section is interested in developing a research report using a case study approach to help practitioners and actuaries develop, evaluate, implement and monitor predictive models in underwriting.

Research Objective

The SOA Reinsurance Research Section is seeking researchers to develop a case study using predictive model(s) in underwriting.  With recent trends towards accelerated underwriting, a case study applicable for AUW would be of high interest.  The following are examples of potential applications of predictive models in life insurance underwriting:

  • assign underwriting risk class in accelerated underwriting using a triage or straight through processing method, which also would assign some risks as declines and/or refer to an underwriter for full underwriting
  • identify cases most likely to misrepresent their risk, e.g. smokers that self-disclose as non-smokers
  • quantify the protective value of underwriting evidence (e.g. labs, exams)
  • any other similar use in the life accelerated underwriting context

The expected research deliverables include:

  • Best practices related to defining the project scope, developing a clear understanding of business objectives, establishing roles and responsibilities, what a company should look for in finding a partner to help develop a predictive model for underwriting, etc.
  • Data:
    • how to obtain, assemble and prepare underwriting data. How to handle and assess disparate data sources, new data sources, 3rd party data and unknown outcomes such as mortality. Considerations and best practices, challenges, limitations.
    • The researcher should provide the dataset(s) for developing the model and make it available as part of the research report. This dataset can be sample data, i.e. it does not need to be actual data. However, it should resemble an actual underwriting dataset so that the methodology and analysis are easy to understand.
  • Model development: methodology, choice of models (statistical vs machine learning, etc.), rationale, pros/cons (e.g. black box vs transparency, etc.)
  • Model validation: how to assess a model, evaluation metrics, train vs test data, cross validation
  • Model results:
    • how to translate and apply model results to be used in underwriting
    • how to quantify the actuarial impact (e.g. mortality impact)
    • reserving implications
  • Model implementation: implementation options and integration, communication with various internal and external stakeholders, including regulators.
  • Monitoring/Reporting: key metrics, how to assess that the model is performing as expected
  • Model retraining: how to refine and update the model, how frequently do you update the model, automatic retraining
  • Full model code in R or Python


To facilitate the evaluation of proposals, the following information should be submitted:

  1. Resumes of the researcher(s), including any graduate student(s) expected to participate, indicating how their background, education and experience bear on their qualifications to undertake the research. If more than one researcher is involved, a single individual should be designated as the lead researcher and primary contact. The person submitting the proposal must be authorized to speak on behalf of all the researchers as well as for the firm or institution on whose behalf the proposal is submitted.
  2. An outline of the case study or studies. Details should be given regarding the data including the volume and data elements, modeling techniques, model assessment and application to underwriting, and possible limitations of the methodology.
  3. A description of the expected deliverables and any supporting data, tools or other resources.
  4. Cost estimates for the research, including computer time, salaries, report preparation, material costs, etc. Such estimates can be in the form of hourly rates, but in such cases, time estimates should also be included. Any guarantees as to total cost should be given and will be considered in the evaluation of the proposal. While cost will be a factor in the evaluation of the proposal, it will not necessarily be the decisive factor.
  5. A schedule for completion of the research, identifying key dates or time frames for research completion and report submissions. The SOA Reinsurance Research Section is interested in completing this project in a timely manner.  Suggestions in the proposal for ensuring timely delivery, such as fee adjustments, are encouraged.
  6. Other related factors that give evidence of a proposer's capabilities to perform in a superior fashion should be detailed.

Selection Process

The SOA Reinsurance Research Section will appoint a Project Oversight Group (POG) to oversee the project.  The SOA Reinsurance Research Section is responsible for recommending the proposal to be funded.  Input from other knowledgeable individuals also may be sought, but the SOA Reinsurance Research Section will make the final recommendation, subject to SOA leadership approval. The SOA's Research Actuary will provide staff actuarial support.


Any questions regarding this RFP should be directed to Ronora Stryker, SOA Research Actuary (phone: 847-706-3614; email:    

Notification of Intent to Submit Proposal

If you intend to submit a proposal, please e-mail written notification by September 13, 2019 to Jan Schuh.

Submission of Proposal

Please e-mail a copy of the proposal to Jan Schuh.

Proposals must be received no later than September 30th, 2019. It is anticipated that all proposers will be informed of the status of their proposal by the end of November 2019.

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 Reinsurance Research Section reserves 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 Reinsurance Research Section also reserves the right to redirect the project as is deemed advisable.

The SOA Reinsurance Research Section plans to hold the copyright to the research and to publish the results with appropriate credit given to the researcher(s).

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

The SOA Reinsurance Research Section 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 Reinsurance Research Section, 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.