DYNAMIC PREDICTION OF OUTSTANDING INSURANCE CLAIMS USING JOINT MODELS FOR LONGITUDINAL AND SURVIVAL OUTCOMES
Date: April 22, 2022
Speaker: Lu Yang
Title: Dynamic Prediction of Outstanding Insurance Claims Using Joint Models for Longitudinal and Survival Outcomes
Abstract: To ensure the solvency and financial health of the insurance sector, it is vital to accurately predict the outstanding liabilities of insurance companies. We aim to develop a dynamic statistical model that allows insurers to leverage granular transaction data on individual claims into the prediction of outstanding claim payments. However, the dynamic prediction of an insurer's outstanding liability is challenging due to the complex data structure. The liability cash flow from a claim is generated by multiple stochastic processes: a recurrent event process describing the timing of the cash flow, a payment process generating the sequence of payment amounts, and a settlement process terminating both the recurrence and payment processes. We propose to use a copula-based marked point process to jointly model the three processes. Specifically, a counting process is employed to specify the recurrent event of payment transactions; the time-to-settlement outcome is treated as a terminal event for the counting process; and the longitudinal payment amounts are formulated as the marks associated with the counting process. The dependencies among the three components are induced using the method of pair copula constructions. Compared with existing joint models for longitudinal and time-to-event data such as random effect models, the proposed approach enjoys the benefits of flexibility, computational efficiency, and straightforward prediction.
Bio: Lu Yang is an Assistant Professor in the School of Statistics at the University of Minnesota. She received her Ph.D. in Statistics from the University of Wisconsin-Madison in 2017. Prior to joining UMN, she was an Assistant Professor in Actuarial Science and Mathematical Finance at the University of Amsterdam. Her current research focuses on multivariate analysis, nonparametric estimation of copulas, and regression model diagnostics, especially with discrete and semi-continuous outcomes.
TRENDS IN MORTGAGE RATE MODELING AND THE PREPAYMENT INCENTIVE
Date: April 1, 2022
Speaker: Chris Jones, U.S. Bank Corporate Treasury
Title: Trends in Mortgage Rate Modeling and the Prepayment Incentive
Abstract: Valuing mortgages in the context of the secondary market typically refers valuation of a mortgage-backed security (MBS) or mortgage servicing rights (MSR) asset. One fundamental challenge of this exercise is that model development relies on capturing market processes rooted in behavioral dynamics. In this talk, we will briefly review how MBS and MSRs are constructed, important modeling components, and then discuss how recent trends pre- and post-COVID have impacted models for these instruments.
Bio: Chris Jones is a model development manager at U.S. Bank focusing on the secondary mortgage market. He has 10 years of experience in financial modeling ranging from model risk management, balance sheet modeling, and the corporate investment portfolio. He holds a PhD in mathematics from the University of Pittsburgh.
MODEL-FREE PRICE BOUNDS UNDER DYNAMIC OPTION TRADING
Date: March 25, 2022
Speaker: Dr. Julian Sester
Title: Model-free price bounds under dynamic option trading
Abstract: We extend discrete time semi-static trading strategies by also allowing for dynamic trading in a finite amount of options, and we study the consequences for the model-independent super-replication prices of exotic derivatives. These include duality results as well as a precise characterization of pricing rules for the dynamically tradable options triggering an improvement of the price bounds for exotic derivatives in comparison with the conventional price bounds obtained through the martingale optimal transport approach.
Bio: Julian Sester is a postdoctoral researcher at the NTU, Singapore. His research focuses on Robust Finance, Credit Risk, and Machine Learning applications in finance. Prior to joining the research group in Singapore, in December 2019, he completed his PhD in mathematics under the supervision of Eva Lütkebohmert at the University of Freiburg.
WHY FINANCIAL RESEARCH IS PRONE TO FALSE STATISTICAL DISCOVERIES
Date: March 18, 2022
Speaker: David H Bailey, Lawrence Berkeley National Lab (retired) and University of California, Davis
Title: Why financial research is prone to false statistical discoveries
Abstract: It is a sad fact that few investment funds, models or strategies actually beat the overall market averages over, say, a 10-year window. Even in academic research work, care must be taken to avoid statistical pitfalls, because: (a) the chances of finding a truly profitable investment design or strategy is very low, due to intense competition; (b) true findings are mostly short-lived, as a result of the non-stationary nature of most financial systems; and (c) it is often difficult to debunk a false claim. Backtest overfitting is a particularly acute problem in finance, both in academic research and commercial development, since it is a simple matter to use a computer program to search thousands, millions or even billions of parameter or weighting variations to find an “optimal” setting. In this talk, we summarize many of these pitfalls, explore why they are so prevalent, and present some tools that can be used to avoid them, including the “False strategy theorem”.
Bio: David H. Bailey (recently retired from the Lawrence Berkeley National Laboratory and also with the University of California, Davis) has published studies in computational mathematics, high-performance computing and mathematical finance. He has received the Chauvenet and Merten Hesse Prizes from the Mathematical Association of America, the Levi Conant Prize from the American Mathematical Society, the Sidney Fernbach Award from the IEEE Computer Society and the Gordon Bell Prize from the Association for Computing Machinery. He and his colleague Marcos López de Prado (Cornell University and Abu Dhabi Investment Authority) have published several studies highlighting the dangers of backtest overfitting and other statistical difficulties in mathematical finance. Bailey is editor of the Mathematical Investor blog (https://www.mathinvestor.org)
Co-author: Marcos Lopez de Prado, Cornell University and Abu Dhabi Investment Authority
Viewgraph file: https://www.davidhbailey.com/dhbtalks/dhb-risk-2022.pdf
MACHINE FORECAST DISAGREEMENT AND EQUITY RETURNS
Date: March 4, 2022
Speaker: Turan G. Bali
Title: Machine Forecast Disagreement and Equity Returns
Abstract: We propose a novel measure of divergence of opinion among investors about stock value based on the dispersion in machines’ expected return forecasts. Compared to financial analysts, machines have neither behavioral biases nor conflicts of interest, thus we argue that machine forecast disagreement provides an objective measure of investor disagreement. After introducing a new measure of firm-specific uncertainty proxied by the degree of disagreement of machines’ future return forecasts, we show that this newly proposed, objective measure of uncertainty (or investor disagreement) does have a significant impact on the cross-sectional pricing of individual stocks. We find a significantly negative cross-sectional relation between machine forecast disagreement (MFD) and future stock returns. A long-short portfolio of stocks sorted by MFD provides a six-factor Fama-French (2018) alpha of 0.72% (1.06%) per month for the value-weighted (equal-weighted) portfolio. The return predictability is driven by mispricing rather than compensation for risk. The disagreement premium is also stronger for stocks that are largely held by retail investors, that receive less investor attention and that are costlier to arbitrage.
Bio: Turan G. Bali is the Robert Parker Chair Professor of Finance at the McDonough School of Business at Georgetown University. He received his Ph.D. from the Graduate School and University Center of the City University of New York in 1999. He also held visiting faculty positions at New York University and Princeton University. Professor Bali specializes in asset pricing, risk management, fixed income securities, and financial derivatives. A founding member of the Society for Financial Econometrics, he worked on consulting projects sponsored by major financial institutions and government organizations in the U.S. and other countries. He regularly presents his work at central banks, regulatory agencies, investment banks, hedge funds, and academic conferences. Professor Bali published three books and more than 50 articles in economics and finance journals, including the most prestigious journals in his field such as the Journal of Finance, Journal of Financial Economics, Review of Financial Studies, Journal of Monetary Economics, Management Science, Journal of Financial and Quantitative Analysis, Journal of Business, and Review of Economics and Statistics. He has won several awards, including the Q-Group's Jack Treynor Prize for quantitative research in finance. He currently serves as an Associate Editor of Management Science, Journal of Financial and Quantitative Analysis, Journal of Banking and Finance, Financial Management, and Journal of Portfolio Management. He also serves on the review committees of the National Science Foundation, Research Grants Council of Hong Kong, Social Sciences and Humanities Research Council of Canada, and Scientific and Technological Research Council of Turkey.
FROM OPTION VALUES TO ADDITIVE MODELS
Date: February 25, 2022
Speaker: Lorenzo Torricelli
Title: From option values to additive models
Abstract: We have recently found that certain simple no-arbitrage vanilla option values yield to implied price distributions of logistic type which are known to be infinitely-divisible. When a no-arbitrage term function is also supplied, the corresponding family of distributions determines an additive pure jump process for the underlying security price, which turns out to be a martingale. The use of additive processes in finance dates back to little more than a decade and has proved to successfully model derivative prices on a large number of asset classes. We insert in such literature with a focus on parameter parsimony and simplicity of valuation, while at the same time being able to capture returns skewness, kurtosis, self-similarity and other important stylized facts.
In order to improve the empirical performance of the models, it is possible to augment the logistic distributions with an additional skew parameter. This amounts to study martingale additive processes in the borader class of generalized logistic and generalized Beta distributions. A second extension is obtained by randomizing the logistic scale parameter, an idea similar in spirit to stochastic volatility and Lévy subordination.
Bio: Lorenzo Torricelli is Assistant Professor at the Department of Statistics at the University of Bologna. He holds an MSc in Geometry from Roma Tre university, and one in Mathematics and Finance obtained at Imperial College London. He received his PhD in Mathematics from University College London and completed a Post-Doc at the Ludwig Maximilians Universität of Munich. He previously worked as an Assistant professor at the Department of Economics and Management of the University of Parma and as a financial and data analyst for the Italian pension funds regulator (COVIP) and was a member of the EIOPA occupational pension workgroup.
THE ASYMPTOTIC EXPANSION OF THE REGULAR DISCRETIZATION ERROR OF ITÔ INTEGRALS
Date: February 18, 2022
Speaker: Elisa Alòs
Title: The asymptotic expansion of the regular discretization error of Itô integrals
Abstract: In this talk, we present an Edgeworth-type refinement of the central limit theorem for the discretization error of Itô integrals. Toward this end, we introduce a new approach, based on the anticipating Itô formula. This alternative technique allows us to compute explicitly the terms of the corresponding expansion formula. Two applications to finance are given: the asymptotic of discrete hedging error under the Black-Scholes model and the difference between continuously and discretely monitored variance swap payoffs under stochastic volatility models. Both of these applications shed light on hedging errors usually neglected in the continuous-time framework of mathematical finance. A short introduction to the anticipating Itô's calculus is given at the beginning of the talk. (Joint work with Masaaki Fukasawa).
Bio: Elisa Alòs is an associate professor in the Department of Economics and Business at Universitat Pompeu Fabra (UPF) and a BSE Affiliated Professor. Prior to joining the UPF in January 2001, she was an assistant professor at Universitat Autònoma de Barcelona (UAB). She completed her Ph.D. in Mathematics in 1998 at the University of Barcelona with a dissertation based on Malliavin Calculus techniques applied to the study of stochastic integral equations.
Her research relies on the applications of stochastic analysis in mathematical finance. In particular, it is focused on the application of Malliavin calculus techniques and the use of fractional noises in market modeling. Her main published results are related to the construction of closed-form approximation formulas for option prices for vanilla and exotic options, as well as with the analytical study of the properties of models (for example, the analytical study of the implied volatility skew for stochastic volatility models). Alòs is also associate editor of the SIAM Journal on Financial Mathematics.
DYNAMICS OF ARBITRAGE
Date: February 4, 2022
Speaker: Kateryna Holland
Title: Dynamics of Arbitrage
Abstract: We study the dynamics of cash-and-carry arbitrage using the U.S. crude oil market. Sizable arbitrage-related inventory movements occur at the New York Mercantile Exchange (NYMEX) futures contract delivery point but not at other storage locations, where instead, operational factors explain most inventory changes. We add to the theory-of-storage literature by introducing two new features. First, due to arbitrageurs contracting ahead, inventories respond to not only contemporaneous but also lagged futures spreads. Second, storage capacity limits can impede cash-and-carry arbitrage, leading to the persistence of unexploited arbitrage opportunities. Our findings suggest that arbitrage-induced inventory movements are, on average, price stabilizing.
Bio: Dr. Holland’s research interests are in the area of corporate finance and focus primarily on ownership, government involvement with firms, university innovation, various event studies, and energy. She has published in leading peer-reviewed journals such as the Journal of Financial Economics and the Journal of Corporate Finance. Professor Holland has earned numerous teaching awards and has taught corporate finance at the undergraduate, Masters and PhD levels. She has worked as a power trader prior to earning her Ph.D. degree in Finance
ECONOMIC VALUATION OF DEFINED BENEFIT PENSION LIABILITIES
Date: January 28, 2022
Speaker: Teemu Pennanen
Title: Economic valuation of defined benefit pension liabilities
Abstract: The pensions industry operates largely by pricing annuities and other pension products with the actuarial discounting principle which can be traced back to at least the 19th century. This is in sharp contrast with financial economics and the banking industry where valuations are based on the costs of producing a product's payouts in the face of uncertainties and incompleteness of financial markets. The deficiencies of the classical actuarial methods are widely recognized by the industry but the transformation of the practices has been slow due to the challenges of applying economic valuation principles in pensions. Typical pension liabilities extend over several decades and their payouts depend on longevity developments which are uncertain and largely independent of the investment returns that insurers earn on their funds in financial markets.
We present mathematical models and computational techniques for asset-liability management and valuation of defined benefit liabilities. The valuations look for the cheapest hedging strategy that covers the pension payments until maturity with an acceptable level of risk. Under complete markets assumption, this coincides with the classical replication argument while in the deterministic case, we recover the actuarial “best estimate”. The approach is illustrated by the valuation of the insurance portfolio of the Finnish private sector pension system.
Bio: Teemu Pennanen is a Professor of Financial Mathematics, probability and statistics at King's College London. Before joining KCL, professor Pennanen worked as Managing Director at QSA Quantitative Solvency Analysts Ltd, with a joint appointment as Professor of Mathematics at the University of Jyvaskyla. His research interests include convex optimization, probability and statistics and their applications to financial economics and risk management. Pennanen has authored over 50 journal publications and he has been a consultant to a number of financial institutions including Bank of Finland, The State Pension Fund and Ministry of Social Affairs and Health.
A UNIFIED THEORY OF DECENTRALIZED INSURANCE
Date: December 10, 2021
Speaker: Runhuan Feng
Title: A Unified Theory of Decentralized Insurance
Abstract: Decentralized insurance can be used to describe risk sharing mechanisms under which participants trade risks among each other as opposed to passing risks mostly to an insurer in traditional centralized insurance. There are a wide range of decentralized practices in all kinds of forms developed around the world, including online mutual aid in East Asia, takaful in the Middle East, peer-to-peer insurance in the West, international catastrophe risk pooling, etc. There is also a rich literature of risk sharing in academia that offers other decentralized mechanisms. This work presents a unified mathematical framework to describe the commonalities and the relationships of all these seemingly different business and theoretical models. Such a framework provides a fertile ground for the design and the analysis of hybrid and innovative models.
Bio: Runhuan Feng is a Professor of Mathematics, Statistics, Industrial and Enterprise Systems Engineering, Director of Actuarial Science Program, Director of Predictive Analytics & Risk Management Program, the State Farm Companies Foundation Professorial Scholar at the University of Illinois at Urbana-Champaign. He is the Faculty Lead for Finance and Insurance Sector at the University of Illinois System’s Discovery Partner Institute in Chicago. Runhuan is a Fellow of the Society of Actuaries and a Chartered Enterprise Risk Analyst. As an applied scientist, Runhuan strongly believes that most interesting research problems are discovered in response to the changing needs of the industry and the society. Runhuan’s research has been recognized in the practitioners' community through his applied technical contributions and presentations as invited speakers at industry conferences. His consulting work has been used by the Illinois General Assembly for pension-related legislative proposals.
KELLY CRITERION: FROM A SIMPLE RANDOM WALK TO LEVY PROCESSES
Date: December 3, 2021
Speaker: Austin Pollok
Title: Kelly Criterion: From a Simple Random Walk to Levy Processes
Abstract: The original Kelly criterion provides a strategy to maximize the long-term growth of winnings in a sequence of simple Bernoulli bets with an edge, that is, when the expected return on each bet is positive. The objective of this work is to consider more general models of returns and the continuous time, or high-frequency, limits of those models. The results include an explicit expression for the optimal strategy in several models with continuous time compounding. Given we know how to optimally bet, we seek to find an edge in the financial markets by investigating the volatility risk premium in option returns. With the aid of high frequency volatility forecasts, we are able to capture an economically significant increase in risk premium compared to competing models.
Bio: Austin Pollok is a PhD student in Applied Mathematics at USC, set to graduate this year. His areas of research are in optimal growth strategies, such as the Kelly Criterion, under heavy-tailed processes, high frequency volatility forecasting using machine learning methods, as well as empirical option pricing. He has worked at Capital Group Companies as a quantitative research engineer while completing his PhD.
MODELING HETEROSCEDASTIC SKEWED AND LEPTOKURITIC RETURNS IN DESCRETE TIME
November 19, 2021
Speaker: Joseph Ivivi Mwaniki
Abstract: Popular models of finance, fall short of accounting for most empirically found stylized features of financial time series data, such as volatility clustering, skewness and leptokurtic nature of log returns. In this study we propose a general framework for modeling asset returns which account for serial dependencies in higher moments and leptokurtic nature of scaled GARCH filtered residuals. Such residuals are calibrated to normal inverse Gaussian and hyperbolic distribution. Dynamics of risky assets assumed in Black Scholes model, Duans(1995) GARCH model and other benchmark models for option valuation, are shown to be nested in the proposed framework. Different sets of data are used to support the proposed framework.
ESTIMATING AND TESTING INVESTMENT BASED ASSET PRICING MODELS
November 12, 2021
Speaker: Yao Deng
Abstract: The standard investment-based asset pricing model predicts that stock returns equal investment returns, state-by-state. Yet, typical work in asset pricing only tests the weaker prediction that stock returns and investment returns should be equal on average. We document that by following the traditional methodology of only matching mean moments to estimate the model, most of the time series variation of stock returns is captured by the error terms, not by the predicted investment returns. We then show how to incorporate the model-implied time series restrictions in the estimation and testing of the model using the generalized method of moments, and formulate an external validity specification test. Our method uncovers a tradeoff between cross sectional fit and time series fit: the baseline investment-based model cannot fit both sets of moments simultaneously. Simulation exercises show that our estimation approach improves the power of the standard tests to detect model misspecification, and hence can be useful for improving the specification of future investment-based asset pricing models.
Bio: Yao Deng is an Assistant Professor of Finance at the University of Connecticut. He earned his PhD in Finance and Master in Financial Mathematics from the University of Minnesota. His research interests include empirical and theoretical asset pricing, behavioral finance, and macro finance.
STOCHASTIC CLAIMS RESERVING IN SHORT-TERM INSURANCE CONTRACTS
November 5, 2021
Speaker: Patrick Guge Oloo Weke
Abstract: Claims reserving for general insurance business has developed significantly over the recent past. There has always been a slight mystery in short-term insurance contracts of how to go about reserving for claims, which have not yet come in, and are still in some sense of figment of the future. Stochastic models for triangular data are derived and applied to claims reserving data. The standard actuarial technique, the chain ladder technique is given a sound statistical foundation and considered as a linear model. The chain ladder technique and the two-way analysis of variance are employed for purposes of estimating and predicting the IBNR claims reserves. Insurance claims variables are non-normally distributed and therefore a measure that will capture the dependence among the variables better than the usual correlation is employed. One such method is the use of copulas.
Bio: Patrick Weke is a full Professor of Actuarial Science and Financial Mathematics at the School of Mathematics, University of Nairobi since 2014. He graduated with a B.Sc. (Honours) in Mathematics, Statistics and Computer Science in 1986 from University of Nairobi, an M.Sc. (Mathematical Statistics) in 1988 from University of Nairobi, an M.Sc. (Actuarial Science) in 1992 from The City University, London and a Ph.D. (Applied Actuarial Statistics) in 2001 from Harbin Institute of Technology, China. He is an Honorary Fellow of The Actuarial Society of Kenya (since 2017) and he is also involved in the following academic/professional activities:
- Director, School of Mathematics, University of Nairobi (2014 – 2020)
- Head, Actuarial Science and Financial Mathematics Division (2006 – 2014)
- Advisory Committee Member – Barclays Africa Chair in Actuarial Science, University of Pretoria, South Africa (2013 to date).
- Director, UAP Life Assurance Ltd
He has successfully supervised 11 PhD candidates and over 40 MSc candidates in Actuarial Science and Financial Mathematics. He has published over 50 articles in refereed journals, 2 textbooks, 3 chapters in books and 20 conference proceedings.
ANALYSISI OF PRESCRIPTION DRUG UTILIZATON WITH BETA REGRESSION MODELS
Speaker: Guojun Gan
Abstract: The healthcare sector in the U.S. is complex and is also a large sector that generates about 20\% of the country's gross domestic product. Healthcare analytics has been used by researchers and practitioners to better understand the industry. In this talk, I will present our recent work about the use of Beta regression models to understand the variability of brand name drug utilization across different areas with the U.S. The models are fitted to public datasets obtained from the Medicare & Medicaid Services and the Internal Revenue Service. Integrated Nested Laplace Approximation (INLA) is used to perform the inference. Some numerical results showing the performance of Beta regression models will also be presented.
Bio: Guojun Gan is an Associate Professor in the Department of Mathematics at the University of Connecticut, where he has been since August 2014. Prior to that, he worked at a large life insurance company in Toronto, Canada for six years and a hedge fund in Oakville, Canada for one year. He received a BS degree from Jilin University, Changchun, China, in 2001 and MS and PhD degrees from York University, Toronto, Canada, in 2003 and 2007, respectively. He is also a Fellow of the Society of Actuaries (FSA). His research interests are in the interdisciplinary areas of actuarial science and data science.
POOLING LONGEVITYFOR A BETTER RETIREMENT INCOME: HOW MANY PEOPLE ARE NEEDED?
October 1, 2021
Speaker: Catherine Donnelly
Title: Pooling longevity for a better retirement income: how many people are needed?
Abstract: Pooled annuity funds are a way of converting retirement lump sum into an income stream for life. Their objective is to provide a stable lifetime income to their participants. They rely on the pooling of the participants' longevity risk to do this. The participants bear all of the longevity risk in a pooled annuity fund, rather than it being transferred to an insurance company.
In the talk, I start with why pooled annuity funds should be a decumulation option for retirement. Then I discuss the recent results which Thomas Bernhardt (U. Manchester, UK) and I have produced on the number of people needed for a fund to deliver on its objective.
Bio: Catherine Donnelly is a professor in actuarial math at Heriot-Watt University, Edinburgh and Director of the Risk Insight Lab. An actuary who has worked in pension consultancies before entering academia, she has a keen interest in developing workable solutions to improve people’s financial situation in retirement. She has a PhD in financial mathematics from University of Waterloo, an MSc from University of Oxford and an undergraduate degree in mathematics from University of Cambridge.
A MIXED BOND AND EQUITY FUND MODEL FOR THE VALUATION OF SEGREATED FUND POLICIES
September 24, 2021
Speaker: Frederic Godin
Title: A mixed bond and equity fund model for the valuation of segregated fund policies
Abstract: Segregated fund and variable annuity policies are typically issued on mutual funds invested in both fixed income and equity asset classes. However, due to the lack of specialized models to represent the dynamics of fixed income fund returns, the literature has primarily focused on studying long-term investment guarantees on single-asset equity funds. This article develops a mixed bond and equity fund model in which the fund return is linked to movements of the yield curve. Theoretical motivation for our proposed specification is provided through an analogy with a portfolio of rolling horizon bonds. Moreover, basis risk between the portfolio return and its risk drivers is naturally incorporated into our framework. Numerical results show that the fit of our model to segregated fund data is adequate. Finally, the valuation of segregated fund policies is illustrated and it is found that the interest rate environment can have a substantial impact on guarantee costs.
Bio: I am an Associate Professor at the Mathematics and Statistics Department of Concordia University in Montreal, Quebec, Canada. My research interests are financial engineering, risk management, actuarial science, reinforcement learning, stochastic modeling, dynamics programing, variable annuities and energy markets. I hold the Fellow of the Society of Actuaries (FSA) and Fellow of the Canadian Institute of Actuaries (FCIA) designations. I am part of the Quantact research group.
EFFICIENT EXPOSURE FRONTIERS
April 16, 2021
Speaker: Dilip Madan
Title: Efficient Exposure Frontiers
Abstract: Risk is described by the instantaneous exposure to changes in valuations induced by the arrival rate of economic shocks. The arrival rate mea- sure is typically not a probability measure and often the aggregate arrival rate across all shocks is infinite. Risk management and portfolio theory are conse- quently recast as managing this exposure risk. There is no risk free exposure with all fixed income securities subject to the risks of instantaneous changes in their valuations. The reference return in the economy is that of a zero risk gra- dient return, typically estimated as negative. Required returns on assets with low risk gradients are then negative. It is also observed that required returns are robust to positions on the efficient frontier as well the construction of the frontier itself. Both equity and fixed income security frontiers are constructed as illustrations of efficient risk positions.
BIO: Dilip Madan is Professor of Finance at the Robert H. Smith School of Business. He specializes in Mathematical Finance. Currently he serves as a consultant to Morgan Stanley, Meru Capital and Caspian Capital. He has also consulted with Citigroup, Bloomberg, the FDIC and Wachovia Securities. He is a founding member and Past President of the Bachelier Finance Society. He received the 2006 von Humboldt award in applied mathematics, was the 2007 Risk Magazine Quant of the year, received the 2008 Medal for Science from the University of Bologna and held the 2010 Eurandom Chair. He is Managing Editor of Mathematical Finance, Co-editor of the Review of Derivatives Research, Associate Editor of the Journal of Credit Risk and Quantitative Finance. His work is dedicated to improving the quality of financial valuation models, enhancing the performance of investment strategies, and advancing the efficiency of risk allocation in modern economies. Recent major contributions have appeared inMathematical Finance, Finance and Stochastics, Quantitative Finance, the Journal of Computational Finance, The International Journal of Theoretical and Applied Finance, The Journal of Risk, The Journal of Credit Risk among other journals.
DO JUMPS MATTER IN THE LONG TERM? A TALE OF TWO HORIZONS
March 26, 2021
Speaker: Jean-François Bégin
Title: Do Jumps Matter in the Long Term? A Tale of Two Horizons
Abstract: Economic scenario generators (ESGs) for equities are important components of the valuation and risk management process of life insurance and pension plans. Because the resulting liabilities are very long-lived and the short-term performance of the assets backing these liabilities may trigger important losses, it is thus a desired feature of an ESG to replicate equity returns over such horizons. In light of this horizon duality, we investigate the relevance of jumps in ESGs to replicate dynamics over different horizons and compare their performance to popular models in actuarial science. We show that jump-diffusion models cannot replicate higher moments if estimated with the maximum likelihood. Using a generalized method of moments-based approach, however, we find that simple jump-diffusion models have an excellent fit overall (moments and the entire distribution) at different time scales. We also investigate three typical applications: the value of one dollar accumulated with no intermediate monitoring, a solvency analysis with frequent monitoring, and a dynamic portfolio problem. We find that jumps have long-lasting effects that are difficult to replicate otherwise, so yes, jumps do matter in the long term.
This is joint work with Mathieu Boudreault.
Bio: Jean-François Bégin, PhD, FSA, FCIA is an Assistant Professor in the Department of Statistics and Actuarial Science at Simon Fraser University. His research interests include financial modelling, financial econometrics, filtering methods, high-frequency data, credit risk, option pricing, and pension economics. Before joining SFU, he received his PhD from HEC Montréal.
MODEL MISSPECIFICATION, BAYESIAN VERSUS CREDIBILITY ESTIMATION, AND GIBBS POSTERIORS
March 19, 2021
Speaker: Liang (Jason) Hong
Title: Model misspecification, Bayesian versus credibility estimation, and Gibbs posteriors
Abstract: In the context of predicting future claims, a fully Bayesian analysis – one that specifies a statistical model, prior distribution, and updates using Bayes’s formula – is often viewed as the gold-standard, while Bühlmann’s credibility estimator serves as a simple approximation. But those desirable properties that give the Bayesian solution its elevated status depend critically on the posited model being correctly specified. Here we investigate the asymptotic behavior of Bayesian posterior distributions under a misspecified model, and our conclusion is that misspecification bias generally has damaging effects that can lead to inaccurate inference and prediction. The credibility estimator, on the other hand, is not sensitive at all to model misspecification, giving it an advantage over the Bayesian solution in those practically relevant cases where the model is uncertain. This begs the question: does robustness to model misspecification require that we abandon uncertainty quantification based on a posterior distribution? Our answer to this question is No, and we offer an alternative Gibbs posterior construction. Furthermore, we argue that this Gibbs perspective provides a new characterization of Bühlmann’s credibility estimator.
Bio: Liang Hong, PhD, FSA, is an Associate Professor in the Department of Mathematical Sciences at the University of Texas at Dallas. His current research interests are actuarial science and foundations of mathematics. In actuarial science, he is primarily interested in applying machine/statistical learning methods, such as Bayesian non-parametric models, conformal prediction, and Gibbs posteriors, to solve important insurance problems.
March 12, 2021
Speaker: Mathieu Rosenbaum
Title: Rough Volatility
Abstract: The goal of this talk is to introduce rough volatility models. We will demonstrate that this approach significantly outperforms conventional ones, both from a statistical and a risk management viewpoint. We will notably illustrate this showing how this new class of models enables us to solve long standing problems in financial engineering.
Bio: Mathieu Rosenbaum is a full professor at École Polytechnique, where he holds the chair “Analytics and Models for Regulation” and is co-head of the quantitative finance (El Karoui) master program. His research mainly focuses on statistical finance problems, regulatory issues and risk management of derivatives. He published more than 65 articles on these subjects in the best international journals. He is notably one of the most renowned experts on the quantitative analysis of market microstructure and high frequency trading. On this topic, he co-organizes every two years in Paris the conference "Market Microstructure, Confronting Many Viewpoints". He is also at the origin (with Jim Gatheral and Thibault Jaisson) of the development of rough volatility models. Mathieu Rosenbaum has collaborations with various financial institutions (investment banks, hedge funds, regulators, exchanges...), notably BNP-Paribas since 2004. He also has several editorial activities as he is one of the editors in chief of the journal “Market Microstructure and Liquidity“ and is associate editor for 10 other journals. He received the Europlace Award for Best Young Researcher in Finance in 2014, the European Research Council Grant in 2016, the Louis Bachelier prize in 2020 and the Quant of the Year award in 2021.
CYCLICAL DESIGN FOR TARGET BENEFIT PENSION PLAN
March 5, 2021
Speaker: Xiaobai Zhu
Title: Cyclical Design for Target Benefit Pension Plan
Abstract: In this paper, we derived the optimal cyclical design of Target Benefit (TB) pension plan. We focused on the stability of the benefit payment, and formulated an optimal control problem using a regime-switching model. We drew a number of remarks to improve the readability of our explicit solution, and made simplifications to enhance the transparency of the risk sharing design. We provided a new yet natural interpretation for a commonly used parameter under the TB context. We highlighted that cautions must be made when studying TB design using optimal control theory. Our numerical result suggested that a 100/0 investment strategies is preferred for the robustness of TB design, and the risk sharing mechanism should include both counter- and pro-cyclical components.
Bio: For my personal information, my full name is Xiaobai Zhu, I am assistant professor at School of Insurance, Southwestern University of Finance and Economics, China, my research interest is on hybrid pension plans and longevity modelling.
DEEP LEARNING MODELS OF HIGH-FREQUENCY FINANCIAL DATA- SEMINAR CANCELED - TO BE RESCHEDULED AT A LATER DATE
February 26, 2021 * 9 am CDT - Seminar Canceled - To Be Rescheduled at a Later Date
Speaker: Justin Sirignano
Title: Deep Learning Models of High-Frequency Financial Data
Abstract: We develop and evaluate deep learning models for predicting price movements in high-frequency data. Deep recurrent networks are trained on a large limit order book dataset from hundreds of stocks across multiple years. Several data augmentation methods to reduce overfitting are analyzed. We also develop and evaluate deep reinforcement learning models for optimal execution problems with limit order book data. "Optimal execution" is the problem of formulating, given an a priori determined order direction (buy or sell) and order size, the optimal adaptive submission strategy to complete the order at the best possible price(s).The performance of deep recurrent models is compared against other types of models trained with reinforcement learning, such as linear VAR models and feedforward neural networks.
Bio: Justin Sirignano is an Associate Professor at the Mathematical Institute at the University of Oxford, where he is a member of the Mathematical & Computational Finance and Data Science groups. He received his PhD from Stanford University and was a Chapman Fellow at the Department of Mathematics at Imperial College London. His research interests are in the areas of applied mathematics, machine learning, and computational methods.
STATIC AND SEMI-STATIC HEDGING AS CONTRARIAN OR CONFORMIST BETS
February 19, 2021
Speaker: Sergei Levendorskii
Title: Static and semi-static hedging as contrarian or conformist bets
Abstract: Once the costs of maintaining the hedging portfolio are properly takeninto account, semi-static portfolios should more properly be thought of as separate classes of derivatives, with non-trivial, model-dependent payoff structures. We derive new integral representations for payoffs of exotic European options in terms of payoffs of vanillas, different from the Carr-Madan representation, and suggest approximations of the idealized static hedging/replicating portfolio using vanillas available in the market. We study the dependence of the hedging error on a model used for pricing and show that the variance of the hedging errors of static hedging portfolios can be sizably larger than the errors of variance-minimizing portfolios. We explain why the exact semi-static hedging of barrier options is impossible for processes with
jumps, and derive general formulas for variance-minimizing semi-static portfolios. We show that hedging using vanillas only leads to larger errors than hedging using vanillas and first touch digitals. In all cases, efficient calculations of the weights of the hedging portfolios are in the dual space using new efficient numerical methods for calculation of the Wiener-Hopf factors and Laplace-Fourier inversion.
Bio: Dr. Levendorskii is a founding partner at Calico Science Consulting in Austin TX. Dr. Levendorskii has developed several models and methods used by the financial services industry. His areas of expertise are Lévy processes with heavy and semi-heavy tails, Financial Mathematics, Real Options, Stochastic Optimization, Applied Fourier Analysis, Spectral Theory, Degenerate Elliptic Equations, Pseudo-differential operators, Numerical methods, Insurance, Quantum Groups, and Fractional Differential Equations. Prior to Calico, he was Chair in Financial Mathematics and Actuarial Sciences, Department of Mathematics and Deputy Director of Institute of Finance, University of Leicester, United Kingdom. He holds a Doctor of Sciences in Mathematics from Academy of Sciences of the Ukraine and he also earned a PhD in Mathematics from Rostov State University."
A MACHINE LEARNING-DRIVEN CRUDE OIL DATA ANALYSIS, WITH APPLICATIONS IN CONTINUOUS-TIME QUADRATIC HEDGING
February 12, 2021
Speaker: Indranil SenGupta
Title: A machine learning-driven crude oil data analysis, with applications in continuous-time quadratic hedging
Abstract: In this presentation, a refined Barndorff-Nielsen and Shephard (BN-S) model is implemented to find an optimal hedging strategy for commodity markets. The refinement of the BN-S model is obtained through various machine and deep learning algorithms. The refinement leads to the extraction of a deterministic parameter from the empirical data set. The analysis is implemented to the Bakken crude oil data and the aforementioned deterministic parameter is obtained for a wide range of data sets. With the implementation of this parameter in the refined model, it is shown that the resulting model performs much better than the classical stochastic models.
Bio: Indranil SenGupta is an Associate Professor at the Department of Mathematics at North Dakota State University (NDSU). He is currently the mathematics graduate program director at NDSU. He received his Ph.D. in mathematics from Texas A&M University in 2010. His research interests include mathematical finance, stochastic processes, and data-science. He was the Associate Editor-in-Chief of the journal Mathematics, 2014-2019. Currently, he is an associate editor in the area of finance and risk management for the Journal of Modelling in Management. He is in the editorial board for several other journals.
SORTING OUT YOUR INVESTMENTS: SPARSE PORTFOLIO SELECTION VIA THE SORTED L1-NORM
February 5, 2021
Speaker: Sandra Paterlini
Title: Sorting out your investments: sparse portfolio selection via the sorted l1-norm
Abstract: We introduce a financial portfolio optimization framework that allows us to automatically select the relevant assets and estimate their weights by relying on a sorted l1-Norm penalization, henceforth SLOPE. To solve the optimization problem, we develop a new efficient algorithm, based on the Alternating Direction Method of Multipliers. SLOPE is able to group constituents with similar correlation properties, and with the same underlying risk factor exposures. Depending on the choice of the penalty sequence, our approach can span the entire set of optimal portfolios on the risk-diversification frontier, from minimum variance to the equally weighted. Our empirical analysis shows that SLOPE yields optimal portfolios with good out-of-sample risk and return performance properties, by reducing the overall turnover, through more stable asset weight estimates. Moreover, using the automatic grouping property of SLOPE, new portfolio strategies, such as sparse equally weighted portfolios, can be developed to exploit the data-driven detected similarities across assets.
Bio: Sandra Paterlini is full professor at the University of Trento, Italy. From 2013 to 2018, she held the Chair of Financial Econometrics and Asset Management at EBS Universität für Wirtschaft und Recht, Germany. Before joining EBS, she was assistant professor in statistics at the Faculty of Economics at the University of Modena and Reggio E., Italy. From 2008 to 2012, she has been a long-term visiting professor at the School of Mathematics, University of Minnesota. Her research on financial econometrics, statistics, operational research and machine learning have been predominantly interdisciplinary and often with an applied angle. Her work experience as a business consultant in finance and as a collaborator of central banks, such as for European Central Bank, Deutsche Bundesbank and the Fed Cleveland, has given her valuable input to guide and validate her research. Furthermore, she spent many years abroad (US, Germany, UK, and Denmark) to broaden and improve her skills further and to establish an international network of collaborators. She has been a consultant on business projects related to style analysis, portfolio optimization and risk management.
Her latest research interests are on machine learning methods for asset allocation, network analysis, risk management and ESG.
A CLUSTER ANALYSIS APPLICATION USING ONLY SOCIAL DETERMINANT VARIABLES TO PREDICT PROFILES OF US ADULTS HAVING THE HIGHEST HEALTH EXPENDITURES
January 29, 2021
Speaker: Margie Rosenberg, University of Wisconsin - Madison
Title: A Cluster Analysis Application Using only Social Determinant Variables to Predict Profiles of US Adults having the Highest Health Expenditures
Abstract: Social determinants of health are defined as the social and physical conditions in which people are born, grow, live, work and age that impact health outcomes. In the late 1960s, Andersen developed a behavioral health framework to help shape a discussion of the impact of social determinants on medical services and other outcomes. Andersen and Newman acknowledged that some populations were not receiving, nor having access to, the same level of medical care as other populations. Our work focuses on social determinants and examining their impact on health expenditures of working aged US adults (20 – 59). We use longitudinal data that are nationally representative of the US adult working‐age civilian non‐institutionalized population. Our study includes Individuals who participated in the National Health Interview Study (NHIS), and who are included in the following two years of the Medical Expenditure Panel Study (MEPS). We form clusters based on the 2010 NHIS demographic, economic, and health‐related characteristics that are commonly used in studies of health care utilization. We use data from the 2010 NHIS cohort to create clusters using a clustering algorithm called Partitioning Around Medoids. Health expenditure distributions for this cohort are examined over the following two years. We validate the approach by applying the centers of the clusters to the 2008 and 2009 NHIS cohorts. Finally, we examine the effectiveness of these clusters in representing the top 5% of health care utilizers. Our findings show that these clusters can provide health care organizations a sampling approach to perform a first‐stage audit using a small segment of the population that can help identify the highest of the utilizers. The approach also identifies those who do not have health expenditures that could signal underutilization. While the profiles designed are representative of US adults, the approach can be applied to any population to reveal the impact of the profiles on utilization. Clusters formed using the data without comorbidities can profile new insureds to allow prospective management of certain individuals. The same group profiles can be used in multiple studies with different outcomes, such as inpatient, outpatient, or drug expenditures.
Bio: Margie Rosenberg, PhD, FSA is the Assurant Health Professor of Actuarial Science Professor at the University of Wisconsin-Madison. Margie’s research interests are in the application of statistical methods to health care, and applying her actuarial expertise to cost and policy issues in health care. Her recent research involves linking social determinants to outcomes such as (i) assessing the impact of delayed attention to oral health issues on emergency department visits and (ii) assessing the impact of unhealthy behaviors on perceived health status and predicting individuals with persistent high expenditures. Prior to her starting on her academic career, Margie worked as a life actuary for Allstate Life Insurance Company in Northbrook, IL.
DYNAMIC SHRINKAGE PROCESSES
November 20, 2020
Speaker: David Matteson, Affiliation: Cornell
Title: Dynamic Shrinkage Processes
Abstract: We propose a novel class of dynamic shrinkage processes for Bayesian time series and regression analysis. Building on a global–local framework of prior construction, in which continuous scale mixtures of Gaussian distributions are employed for both desirable shrinkage properties and computational tractability, we model dependence between the local scale parameters. The resulting processes inherit the desirable shrinkage behaviour of popular global–local priors, such as the horseshoe prior, but provide additional localized adaptivity, which is important for modelling time series data or regression functions with local features. We construct a computationally efficient Gibbs sampling algorithm based on a Pólya–gamma scale mixture representation of the process proposed. Using dynamic shrinkage processes, we develop a Bayesian trend filtering model that produces more accurate estimates and tighter posterior credible intervals than do competing methods, and we apply the model for irregular curve fitting of minute‐by‐minute Twitter central processor unit usage data. In addition, we develop an adaptive time varying parameter regression model to assess the efficacy of the Fama–French five‐factor asset pricing model with momentum added as a sixth factor. Our dynamic analysis of manufacturing and healthcare industry data shows that, with the exception of the market risk, no other risk factors are significant except for brief periods. If time permits, we will also highlight extensions to change point analysis and adaptive outlier detection.
Youtube link to Presentation
TRENDS IN APPLIED MATHEMATICS AND ITS ADOPTION IN THE FINANCE INDUSTRY, OR WHY YOU SHOULD PASS ON BLOCKCHAINS AND BIG DATA
October 30, 2020
Speaker: John Dodson, Options Clearing Corporation
Title: Trends in applied mathematics and its adoption in the finance industry, or why you should pass on blockchains and big data
Abstract: Over the course of the twentieth century, applied mathematics has gradually assimilated and standardized the subjects of probability, statistics, control, and information. While an outside observer of decadal trends in STEM in finance might instead focus on the industry's embrace of computing technology during the Moore's Law era, I claim these quieter developments are ultimately more impactful because they help firms to organize information technology and financial innovation to create lasting value for clients. I will demonstrate this through a survey of the changing role of quants, and make an attempt to describe current opportunities.
QUANTIFYING THE IMPACT OF THE SOCIAL DETERMINANTS OF HEALTH IN THE COVID-19 ERA
October 23, 2020
Speaker: Shae Armstrong, Optum
Title: Quantifying the Impact of the Social Determinants of Health in the Covid-19 Era
Abstract: The Social Determinants of Health (SDoH) are key factors in each person’s environment and life that influence clinical outcomes of their health and wellbeing. These factors include, but are not limited to, income, housing, food security, education, and geography. In the age of Covid-19, understanding these factors and how they correlate to each other is more important than ever. Once we as industry gain insight on these clinical and financial impacts, we need to translate that insight into policy to mitigate root cause issues to better serve patients across the country.
During this lecture we lay the foundation by defining what the Social Determinants of Health are and the various categories they fall into. We will also examine what data sources feed various SDoH models and limitations of said data sources. Next we will conduct a deep-dive examination on a variety of case studies and models aimed at quantifying the short-term and long-term clinical and financial impact of Covid-19. From there we will touch on the future and impact of healthcare data analytics within the healthcare industry and as human beings navigating an unprecedented pandemic.
MULTI-STEP FORECAST OF IMPLIED VOLATILITY SURFACE USING DEEP LEARNING
October 15, 2020
Speaker: Zhiguang (Gerald) Wang, South Dakota State University
Title: Multi-Step Forecast of Implied Volatility Surface using Deep Learning
Abstract: Modeling implied volatility surface (IVS) is of paramount importance to price and hedge an option. We contribute to the literature by modeling the entire IVS using recurrent neural network architectures, namely Convolutional Long Short Term Memory Neural Network (ConvLSTM) to produce multivariate and multi-step forecasts of the S&P 500 implied volatility surface. Using the daily S&P 500 index options from 2002 to 2019, we benchmark the ConvLSTM model against traditional multivariate time series VAR model, VEC model, and LSTM neural network. We find that both LSTM and ConvLSTM can fit the training data extremely well with mean absolute percentage error (MAPE) being 3.56% and 3.88%, respectively. As for out-of-sample data, the ConvLSTM (8.26% ) model significantly outperforms traditional time series models as well as the LSTM model for a 1-day, 30-day, and 90-day horizon, for all moneyness groups and contract months of both calls and puts.
EFFICIENT RISK-SENSITIVITY ESTIMATION FOR EQUITY-LINKED INSURANCE BENEFITS
October 2, 2020
Speaker: Liban Mohammed, University of Wisconsin -Madison
Title: Efficient Risk-sensitivity Estimation for Equity-Linked Insurance Benefits
Abstract: For an organization with billions of dollars in assets, precise risk management is necessary to safeguard those assets. However, when the risks these assets are exposed to depend on the future performance of equities in complex ways, directly estimating them in real-time to the necessary precision can be prohibitively expensive. This talk discusses some approaches to resolving this tension via metamodeling techniques.
YouTube Link to Presentation
ACTUARIAL IMPLICATIONS OF COVID-19
Friday, September 25, 2020
Speaker: Max Rudolph, Rudolph Financial
Title: Actuarial Implications of COVID-19
Abstract: COVID-19 has had a material impact on all practice areas of the actuarial profession, ranging widely include traditional areas like health and mortality claims, assets and economic activity, but also risk management and strategic planning. This session assumes you know many of the basic statistics and provides observations about how analysis of the virus is evolving. Bio: MAX J. RUDOLPH, FSA CFA CERA MAAA. Max Rudolph is a credentialed actuary, active in the Asset-Liability Management and Enterprise Risk Management space for many years. He was named a thought leader in ERM within the actuarial profession, chaired the ERM Symposium, the SOA Investment Section Council and the SOAs Investment Actuary Symposium. He is a past SOA board member and received a Presidential Award for his role developing the CERA credential. He was the subject matter expert for the original Investment and ERM modules, wrote the ERM courseware document and has been involved with the actuarial professions climate change and pandemic efforts. He is a frequent speaker at actuarial seminars and universities, and an award-winning author. For the past 14 years Max has led Rudolph Financial Consulting, LLC, an independent consulting practice, focusing its insurance practice on ERM and ALM consulting. He has completed projects relating to life, health, annuity, and casualty insurers. He is an adjunct professor for Creighton Universitys Heider School of Business, where he focuses on ERM and investment topics.Max has completed a number of well received research reports covering topics such as emerging risks, low growth, low interest rates, investments, systemic risk and ERM. Other topics he has written about include pandemics, ALM and value investing. Many of his papers can be found at www.rudolph-financial.com. He comments on a variety of risk topics from @maxrudolph on twitter.
YouTube Link to Presentation
PRICING IN CONTRACTUAL FREIGHT COMPARED TO FINANCE
February 7, 2020
Speaker: Kaisa Taipale, C.H. Robinson
Title: Pricing in Contractual Freight Compared to Finance
Abstract: In this talk, I’ll discuss the contractual freight business, in which a large shipper makes a contract with a company like CH Robinson to procure carriers (trucks) for their goods over the course of a year for a given rate, as opposed to using the volatile “spot” or transactional market. Because these year-long contracts aren’t legally binding, some shippers treat them more like an American option on the underlying price of freight — but this has game-theoretic economic consequences for the shipper! Dr. Taipale, Data Scientist at C.H. Robinson will also talk about the data science and mathematical skills that are important for her job at C.H. Robinson