Registration and Breakfast: 9:00am-9:20am
Session 1: Research Collaborations with Illinois Risk Lab
Title: Jump-start Analytics Research with Illinois Actuarial Program
Abstract: The University of Illinois has long been recognized in the insurance industry as a cradle for high-caliber actuaries. As we celebrate the 60th anniversary of the founding of the Illinois Actuarial Program this year, we are excited to share a new mission and vision of the program, which is not only to continue delivering high quality actuarial education but also to become a center of excellence in analytics research.
Over the last few years, the program has been successful with research projects sponsored by professional organizations and funding agencies. As we explore new ways for education and research collaborations, this is a great moment to reflect on our accomplishments and invite suggestions for building new partnerships.
Title: Affordable, Adequate and Stable Annuities in Today's World: Fantasy or Reality?
Abstract: I introduce a class of investment-linked annuities that extends existing annuities by allowing portfolio shocks to be gradually absorbed into the annuity payouts. Consequently, our new class enables insurers and pension providers to offer an affordable and adequate annuity with a stable payout stream. We show how to price and adequately hedge the annuity payouts in a general financial environment. In particular, our model accounts for various stylized facts of stock returns such as asymmetry and heavy-tailedness. Furthermore, we show that our annuities are consistent with reference-dependent preferences.
Title: Boosting Derivatives Pricing with Machine Learning
Abstract: In the derivatives world, zillion computations need to be done on a daily basis: models need to be calibrated, derivative instruments need to be priced, hedge positions need to be calculated, risk management indicators need to be determined, etc... With the “Fundamental Review of the Trading Book” (FRTB) luring around the corner, an even larger computational challenge is coming to every bank's direction. There is of course the ongoing challenge of counterparty exposure calculations for complex portfolios. Fortunately machine learning can help as we illustrate in our presentation. For once this is a practical application of machine learning, not yet another trial to beat the stock market with deep learning predictions. In this contribution, we show how one can deploy machine learning techniques in the context of traditional quant problems. We illustrate that for many classical problems, we can arrive to speed-ups of several orders of magnitude by deploying machine learning techniques based on Gaussian process regression. The price we have to pay for this extra speed is some loss of accuracy. However, we show that this reduced accuracy is often well within reasonable limits (for example within bid-ask spread) and hence very acceptable from a practical point of view.
Session 2: Predictive Analytics
Title: Insurance Analytics
Abstract: Insurance as a discipline has long embraced analytics and market trends signal an even stronger relationship going forward. Other industries have recently embraced the predictive nature of analytics; this talk will emphasize historical precedence that demonstrates why the predictive nature has long been a key feature of insurance industry analytics.
To distinguish insurance analytics from applications in other industries, I focus on our data, the regulatory environment, and the dependence of outcomes. I will use examples from medical malpractice as well as personal general insurance, automobile and homeowners, to underscore these different aspects of insurance analytics. I argue that because of these fundamental differences, the insurance industry will need experts trained not only in modern analytics techniques but who are also well versed in the insurance marketplace.
Title: Insurance: Risk Pooling and Price Segmentation
Abstract: Insurance is usually defined as "the contribution of the many to the misfortune of the few". This idea of pooling risks together using the law of large number legitimates the use of the expected value as actuarial "fair" premium. In the context of heterogeneous risks, nevertheless, it is possible to legitimate price segmentation based on observable characteristics. But in the context of "Big Data", intensive segmentation can be observed, with a much wider range of offered premium, on a given portfolio. In this talk, we will briefly get back on economical, actuarial and philosophical approaches of insurance pricing, trying to link a fair unique premium on a given population and a highly segmented one. We will then get back on recent experiments (so-called "actuarial pricing game") organized since 2015, where (real) actuaries were playing in competitive (artificial) market, that mimic real insurance market. We will get back on conclusions obtained on two editions, the first one, and the most recent one, where a dynamic version of the game was launched.
Title: What a Corporate Executive Learned When He Went Back to College.
Abstract: Mark Vonnahme has worked in business and academia for 47 years. Two distinct careers but both have provided an opportunity to impact future leaders. As Professor Vonnahme looks back on his career, he will provide perspectives on “ The Business Exec going back to school “ , what he learned and the importance of the academic business partnership in developing future leaders in Risk Management and Insurance.
Session 3: Retirement Planning Analytics
Title: Intergenerational Risk-Sharing Plans: Optimality and Fairness
Abstract: We discuss optimal design for stylized Intergenerational Risk Sharing (IRS) pension plans. We study an IRS plan under which both contributions and pension benefits are adjusted based on the level of pension assets. Our optimization focuses on the stability of members’ lifetime consumption, both in the contribution and benefit phases, through formulating the optimization as an ergodic control problem. We illustrate the drawbacks of unconstrained optimization and demonstrate the importance of including regulatory requirements for the sake of fairness across generations. In this formulation, the employers are not included; implicitly, it is assumed that employer contributions would be paid as salary to the workers if not required for the plan, so the employer risk is eliminated.
Title: Harnessing psychology and technology to improve retirement outcomes
Abstract: This talk will explore how two distinct intellectual revolutions have the potential to change the future of retirement. The behavioral economics revolution has provided rigorous insights into how we can design interventions so that deeply embedded psychological biases can be leveraged to help people save. The big data/AI revolution promises to substantially increase access to and reduce the cost of advice and customized retirement solutions.
Coffee: 3:00pm – 3:20pm
Session 4: Together We Do More: Building Industry & Academic Partnerships
Abstract: This session features panelists who have worked in both industry and academia to discuss ways they have brought their experiences in both realms together to benefit students and researchers. They will discuss the successes and challenges faced in bringing "real world" experience and hands-on activities into the classroom and present ideas for engaging industry and academics in partnerships that add value.
- Lynne McChristian (Director, Office of Risk Management & Insurance Research Senior Instructor University of Illinois)
- Ian Duncan (University of California at Santa Barbara)
- Ken Williams (CAS)
- Tom Edwalds (DePaul University)
Outstanding Student Research Prize Presentation
Reception: Immediately following the symposium
(Deloitte Office Building, 29th Floor, 111 S. Wacker Drive, Chicago. )
More information about the reception: https://math.illinois.edu/alumni/illinois-actuarial-science