## Seminar Categories

- AMS Intro to Research Seminar (1)
- Applied and Computational Math Colloquium (1)
- Applied and Computational Mathematics Seminar (1)
- Automorphic Forms and Number Theory (1)
- Colloquium (6)
- Combinatorics Seminar (10)
- Differential Geometry and Symplectic Topology Seminar (1)
- Dynamical Systems (1)
- First Year Seminar (12)
- IMA Data Science Lab Seminar (2)
- IMA MCIM Industrial Problems Seminar (4)
- Math Physics Seminar (2)
- MCFAM Seminar (4)
- Ordway Lecture Series (3)
- PDE Seminar (1)
- Probability Seminar (3)
- Representations of p-adic groups (1)
- Special Events and Seminars (4)

## Current Series

Fri Sep 14 |
## MCFAM Seminar5:30pm - Vincent Hall 16How to Get the Most Out of the MFM MFM 2nd Yr. Student/Alumni Panel, U of M - School of Mathematics - MCFAM |

Fri Sep 21 |
## MCFAM Seminar5:30pm - Vincent Hall 16Topological Data applied to Finance Kaisa Taipale - 2018 MCFAM Summer Seminar Students, University of Minnesota |

Fri Oct 05 |
## MCFAM Seminar5:30pm - Vincent Hall 16CCAR (Comprehensive Capital Analysis and Review) and Basel Framework - Risk Management Modeling Dr. Xu Li Dr.Xu Li will give an overview of what he is does in Market Risk Analytics as a SVP of Risk Analytics at Citi. He will then focus on a default model that is useful for both CCAR, the stress testing framework set out by the Federal Reserve (IDR) and Basel framework which is the international regulatory framework for banks (IRC, DRC). He will show the general ideas on modeling the default risks and discuss some options on the modeling choices. |

Fri Oct 12 |
## MCFAM Seminar5:30pm - Vincent Hall 16Interpreting Constraints in Mean Variance Optimization Chris Bemis, Head of Quantitative Analysis and Research, Whitebox Advisors, UMN Math Dpt. Affiliated Faculty We study the effect linear constraints have on risk in the context of mean variance optimization (MVO). Jagannathan and Ma (2003) establish an equivalence between certain constrained and unconstrained MVO problems via a modification of the covariance matrix. We extend their results to arbitrary linear constraints and provide alternative interpretations for the effect of constraints on both the input parameters to the problems at hand and why ex-post performance is improved in the constrained setting. |

Fri Oct 26 |
## MCFAM Seminar5:30pm - Vincent Hall 16Dynamic Linear Models Katy Micek, 3M Finance Dynamic linear models (DLMs), a subset of state space models, describe the output of a dynamic system as a function of a non-observable state process affected by random errors. Because DLMs can be used either for traditional time series analysis tasks (making inferences on observed states or prediction future observations) or for feature generation in machine learning tasks, they are a very useful tool for any data scientist who works with time series data. As a data scientist on the Data Analytics team for 3M Finance, I work primarily with time series data from the general ledger. Our team both leads data science projects and assists in organizational development of internal capabilities around data science. |

Fri Nov 09 |
## MCFAM Seminar5:30pm - Vincent Hall 16Macroecomic Analysis and Insight - Steepness of the Yield Curve As of September 2018 Ujae Kang, UnitedHealth Group Ujae Kang will present on the Federal Reserve over the years and its influence on the yield curve. Then, he will cover what to expect from the Federal Reserve in the coming years. Bio: Ujae Kang is Director of Enterprise Risk Management at UnitedHealth Group. He is an Associate of the Society of Actuaries and has an Master of Financial Mathematics from the University of Minnesota's School of Mathematics. He also provides economic research and insights to UnitedHealth Group's Asset Liability Management Committee as well as to other investors. For more information on Ujae go to linkedin.com/in/ujaeaugustinekang |

Fri Nov 30 |
## MCFAM Seminar5:30pm - Vincent Hall 16The Effect of the Risk Corridors Program on Marketplace Premiums and Participation Pinar Karaca Mandic, MILI Director/Carlson Finance Professor We investigate the effect of the Risk Corridors (RC) program |

Fri Dec 07 |
## MCFAM Seminar5:30pm - Vincent Hall 16Data Visualization in R Chen Zhang, Sr. Consultant, Analytics & Research at Travelers; Ph.D. in Statistics from UConn; UMN MFM Alumnus Data visualization is often overlooked by people working with data and/or modeling but can in fact reveal very useful insight into problems at hand. R is an open-source programming language for statistical computing and graphics with increasing popularity among practitioners in data science and machine learning in recent years. The "ggplot2" package in R, in particular, provides very powerful, intuitive and versatile tools for data visualization. An overview of these tools will be presented in this talk accompanied by a live demo. |

Fri Feb 01 |
## MCFAM Seminar5:30pm - Vincent Hall 16Computational Issues in Making Math Models Operational in Insurance Scott Monitor, VP & Financial Engineer - MFM alumnus, FSA Many insurance companies offer a wide array of investment guarantees, and some of these are complicated and have no clear analytical solution. In order to manage these contracts and along with increased scrutiny from regulatory bodies, companies are having to value these contracts more frequently and in a greater number of runs. We will demonstrate methodologies and computational approaches to be able to perform analysis on these contract that can be actionable and timely. |

Fri Feb 08 |
## MCFAM Seminar5:30pm - Vincent Hall 16Today's Seminar - Canceled Jie Ding, School of Statistics - University of Minnesota In the era of big data, analysts usually explore various statistical models or machine learning methods for observed data in order to facilitate scientific discoveries or gain predictive power. Whatever data and fitting procedures are employed, a crucial step is to select the most appropriate model or method from a set of candidates. Model selection is a key ingredient in data analysis for reliable and reproducible statistical inference or prediction, and thus central to scientific studies in fields such as ecology, economics, engineering, finance, political science, biology, and epidemiology. There has been a long history of model selection techniques that arise from researches in statistics, information theory, and signal processing. A considerable number of methods have been proposed, following different philosophies and exhibiting varying performances. The purpose of this talk is to bring an overview of them, in terms of their motivation, large sample performance, and applicability. I will provide practically relevant discussions on theoretical properties of state-of- the-art model selection approaches, and share some thoughts on controversial views on the practice of model selection. Bio for Jie Ding |

Fri Feb 15 |
## MCFAM Seminar5:30pm - Vincent Hall 16Simulating the Greeks of American Options P.A. (Phuong Anh) Nguyen, University of Minnesota Abstract: In this paper, we implement an efficient simulation-based method for estimating the Greeks of American options. We perform a least square regression to determine the optimal stopping rule that is applied to calculate the Greeks, which are derived via a path-wise derivative approach. We prove that this method provides asymptotically unbiased simulation estimators for the Greeks. In addition, we propose a boundary integral technique as a faster way to approximate gamma. This technique can also be used to calculate delta and theta. Our paper is the first to provide complete simulation-based approximations for all of the Greeks (delta, gamma, theta, rho, and vega) of American options. To make the computational process more efficient, we incorporate a Brownian Bridge into the numerical simulations. We then extend the application to American basket options. Bio: P.A. Nguyen is a PhD candidate in the University of Minnesota's Industrial Systems Engineering (ISyE) Doctoral Program. She is working with Dr. Dan Mitchell whose focus is in the area of financial engineering, specifically applying stochastic control to problems in finance and quantitative risk management. P.A. is also an alumna of the Master of Financial Mathematics (MFM) at the University of Minnesota (2014) and is currently a teaching assistant for the MFM. She worked in enterprise risk management, primarily in credit risk and interest rate risk areas, for a few years before joining UMNs ISyE PhD program. |

Fri Feb 22 |
## MCFAM Seminar5:30pm - Vincent Hall 112The Prospect of a Forgivable Premium Insurance Policy Kyle Jore, University of Minnesota Despite low premiums and high subsidies, farmers view crop insurance programs as a gamble. One explanation, in a revenue protection program, is that farmers exhibit loss aversion when premiums are just above coverage. Introducing a model for conditional loss aversion (CLA), in the context of cumulative prospect theory, it can be shown that the introduction of a forgivable premium can remove the producers loss aversion. This would result in producers being willing to spend more on an insurance program and thus, allow for a reduction in the implied subsidy. |

Fri Mar 08 |
## MCFAM Seminar5:30pm - Vincent Hall 16MCFAM Seminar Yuepeng Perry Li, CFA, FRM, Parametric Portfolio Associates LLC |

Fri Mar 29 |
## MCFAM Seminar5:30pm - Vincent Hall 112MCFAM Seminar TBA |

Fri Apr 12 |
## MCFAM Seminar5:30pm - Murphy Hall 130Model Development & Delivery in Real World Quant Finance Florian Huchede, Director & FX Lead Quant - CME Group Over the last 10 years, financial companies have been increasingly using quantitative models for decision making. Well performing models can provide automatic and objective decision making as well as a certain ability to synthesize complex issues. However, models expose companies to model risk, higher development cost and longer delivery time. In this MCFAM seminar, we will cover how to reduce the model risk and time to market by using a model design process. Furthermore, we will apply the process on a particular example: OTC FX option volatility calibration. Bio: Florian Huchedé is a Director of Quantitative Risk Management at CME Group. He leads an international team of quantitative analysts that work on designing, implementing and filing quantitative algorithms on various applications (settlement, pricing, data cleansing, risk management, product creation and large optimization). Furthermore, he is the lead quant for the FX and Equity asset classes. Florian graduated from the Financial Mathematics program at University of Chicago (2010). He completed his undergraduate studies and MS in Engineering at Ecole Francaise dElectronique et dInformatique in Paris, France (2007). Prior to joining CME Group, he worked at Credit Agricole Asset Management Alternative Investment and at The Option Clearing Corporation. With more than 10 years of experience, Florian is focused on innovation, creativity and giving back to the quant community. He holds three U.S. patents on risk management and financial products. Furthermore, he initiated a joint research program between University of Chicago and CME Group in 2012. Since then, the program has expanded and is being utilized by many other companies. |