Sheldon H. Jacobson
KEYNOTE SPEAKER – THURSDAY, SEPTEMBER 24
How Risk-Based Thinking can Inform Decision Making in a COVID-19 World
Since March 2020, the COVID-19 pandemic has affecting every facet of life. Over time, we have learned much about the virus and who is at most risk of poor outcomes. With most of the economy shut down in early spring, the nation has been grappling with how to reintroduce activities back into everyday life. This presentation discusses how risk-based thinking can inform such decisions. By using targeted measures of risk across society, more informed reopening processes can be constructed. Examples of such re-openings are provided to illustrate such findings.
Sheldon H. Jacobson is a Founder Professor of Computer Science at the University of Illinois. He has a B.Sc. and M.Sc. (both in Mathematics) from McGill University, and a MS and PhD (both in Operations Research) from Cornell University. From 2012-2014, he was on leave from the University of Illinois, serving as a Program Director at the National Science Foundation. His research interests span theory and practice, covering decision-making under uncertainty and optimization-based artificial intelligence, with applications in aviation security, public policy, public health, and sports. He has been recognized by numerous awards, including a Guggenheim Fellowship, the IISE David F. Baker Distinguished Research Award, and the INFORMS Impact Prize. He is a fellow of AAAS, IISE and INFORMS. He serves as the Founding Director for the Institute for Computational Redistricting (ICOR), http://redistricting.cs.illinois.edu.
KEYNOTE SPEAKER – FRIDAY, SEPTEMBER 25
The Role of Agility & Analytics in Powering Supply Chains Through Disruptions
Supply chain planning is a complex art under the best of circumstances and even harder during disruptions. Anne will talk about best practices observed during the current pandemic and the importance of both analytics and agility in supporting them.
As Chief Strategy Officer, Anne is responsible for accelerating Kinaxis strategy development to add further value to customers. She and her team collaborate closely with customers, external stakeholders and the rest of the senior executive team to drive the strategic roadmap, thought leadership and identify emerging technologies and new industry opportunities.
A proven leader in analytics and digital transformation, with expertise in operations, supply chain and strategy, Anne has extensive experience in managing supply chains for complex, global organizations. As Executive Director, Global Supply Chain Strategy, Analytics and Systems at Verizon, Anne was responsible for the strategic vision of the company’s global end-to-end supply chain, driving excellence through world-class data-analytics, process innovation and employee empowerment. Before Verizon, Anne spent several years at Cisco where she was responsible for managing advanced analytics, business intelligence and performance management teams.
Anne is a past president of INFORMS (the Institute for Operations Research and Management Sciences), a seasoned industry speaker and has served on several advisory boards. Originally from St. John’s, Newfoundland and Labrador, Anne has a BScH from Acadia University, MASc from the University of Waterloo and an MSc and PhD in Industrial Engineering from Stanford University.
James J. Cochran
Frankenstein for President?
History is littered with egregious failures of political polls to call the winner of an election (President Thomas Dewey?). In each of the four most recent U.S. Presidential elections, national polls have generally agreed on the outcome immediately prior to the casting of the ballots; the general consensus of the polls was wrong in half of those elections (2004 and 2016). There are many possible reasons for these failures, perhaps most notably of which is the unwillingness or inability of respondents to tell pollsters for whom they intend to vote. In this talk, I will describe an approach that addresses this problem for U.S. Presidential elections through i) estimating of the relative value each respondent associates with each possible position on each salient attribute, ii) asking each respondent what position she or he believes each candidate holds on each of these issues, and iii) using these results to estimate the number of votes each candidate will take in the electoral college. Notably, results of this methodology can also be used to find the collection of positions on the salient issues that optimizes one candidate’s expected electoral college votes, determine regions and demographic groups over which a candidate’s support is weak, assess the relative importance of the salient issues, and determine on which important issues the candidate’s position/message is not perceived consistently by the voters. Empirical results of an execution of this methodology for the 2004 U.S. Presidential election will also be discussed.
James J. Cochran Is the Rogers-Spivey Fellow and Associate Dean for Research with the University of Alabama’s Culverhouse College of Business. He has been a Visiting Scholar with Stanford University, the University of South Africa, the Universidad de Talca, Pôle Universitaire Léonard De Vinci, the University of Limpopo, and the University of Namibia. He holds honorary faculty appointments with the University of KwaZulu Natal and the University of Limpopo.
Dr. Cochran’s research focuses on problems at the interface of statistics and operations research, and he has taught a wide range of statistics and operations courses from the introductory undergraduate level through PhD seminars. He has published fourteen book chapters and over fifty research articles, and he is coauthor of seven textbooks in statistics, operations research, and analytics. He is the founding Editor-in-Chief of the Wiley Encyclopedia of Operations Research and the Management Sciences, Wiley Series in Operations Research and Management Science, Oxford Anthology of Statistics in Sports series, and INFORMS Analytics Body of Knowledge. He has served as a consultant to a wide variety of corporations, government agencies, and not-for-profit organizations around the world.
Dr. Cochran established an international teaching effectiveness colloquium series and organized these events in Uruguay, South Africa, Colombia, India, Tanzania, Argentina, Kenya, Nepal, Cameroon, Australia, Croatia, Cuba (twice), Estonia, Fiji, Mongolia, Moldova, Bulgaria, Tunisia, and Grenada. He was a founding co-chair of Statistics without Borders and a founding committee member for INFORMS Pro Bono Analytics initiative. He has delivered keynotes to conferences in twenty-five nations.
Dr. Cochran has received the INFORMS Prize for the Teaching of OR/MS Practice, Mu Sigma Rho Statistical Education Award, Waller Distinguished Teaching Career Award, and Karl E. Peace Award for outstanding statistical contributions for the betterment of society. He is a Fellow of both the American Statistical Association and INFORMS, and he has received both the American Statistical Association’s Founders Award and the INFORMS President’s Award.
Michael P. Johnson, PhD
Ethics and Racial Justice Panelist
Dr. Michael P. Johnson is Professor and Chair of the Department of Public Policy and Public Affairs at University of Massachusetts Boston. Dr. Johnson received his Ph.D in operations research from Northwestern University in 1997, M.S. in operations research from University of California Berkeley in 1990, M.S. in electrical engineering from Georgia Institute of Technology in 1987 and B.S. in mathematics and French from Morehouse College in 1987.
Dr. Johnson’s research interests lie in data analytics and management science for housing, urban planning and community development; inclusive policy and planning interventions for climate adaptation, diversity, equity and inclusion in OR/analytics, and nonprofit service delivery. His methods enable non-profit and public organizations, especially those serving disadvantaged and vulnerable populations, to develop programs and policies that balance economic efficiency, beneficial population outcomes and social equity. Dr. Johnson’s primary analytic methods are community-based data collection, analysis and sharing for local development (‘community data analytics’), and decision modeling using qualitative and quantitative analysis and participatory problem-solving for local impact and social change (‘community-engaged operations research’). He has applied these methods to foreclosed housing redevelopment and community revitalization, and strategy design for vacant property management in distressed neighborhoods, shrinking cities and declining regions. His research and teaching are associated with and bridge the disciplines of decision sciences, public policy, public management, urban planning and community development.
His work has appeared in a variety of journals, edited volumes and conference proceedings. He is lead co-editor of a volume of papers on diversity, equity and inclusion titled INFORMS Editor’s Cut: Diversity and Inclusion: Analytics for Social Impact (INFORMS, 2019), lead co-editor of a special issue of European Journal of Operational Research on community operational research (Elsevier, 2018), lead author of the book Decision Science for Housing and Community Development: Localized and Evidence‐Based Responses to Distressed Housing and Blighted Communities (Wiley, 2016), and editor of the book Community-Based Operations Research: Decision Modeling for Local Impact and Diverse Populations (Springer, 2012).
Narasimhan (NS) Krishnan
Ethics and Racial Justice Panelist
N.S. Krishnan leads Customer and Account Management in North America for AIMMS. He has over 20 years of experience in operations, consulting, supply chain and analytics and is passionate about helping companies make better decisions with prescriptive analytics.
AI, Ethics, and Accountability
The promise of AI can overwhelm our discourse. Hiring and promotion can be faster, cheaper, and less biased; hypertargeting of consumers is a win-win solution getting the right product in the right hands. AI firms then differentiate on supposed accuracy and speed: accuracy in linking intimate knowledge to a specific individual. However, these AI decisions in practice, like all decisions, generate mistakes and biased results that can violate norms, harm individuals, and undermine users rights. In this panel, I will argue that firms that design and develop AI have a particular duty to understand the moral implications of how their technology will be used. In particular, developers have an obligation to design the possibility to identify, judge, and fix mistakes as the AI is used. Finally, this duty is similar to how we understand corporate responsibility in markets today.
Kirsten Martin is the William P. and Hazel B. White Center Professor of Technology Ethics and is Professor of IT, Analytics, and Operations in the Mendoza College of Business at the University of Notre Dame.
She researches privacy, technology, and corporate responsibility. She has written about privacy and the ethics of technology in leading academic journals across disciplines (Journal of Business Ethics, BEQ, Harvard Journal of Law and Technology, Journal of Legal Studies, Washington University Law Review, Journal of Business Research, etc) as well as practitioner publications such as MISQ Executive. She is the Technology and Business Ethics editor for the Journal of Business Ethics and the recipient of three NSF grants for her work on privacy, technology, and ethics. Dr. Martin is also a member of the advisory board for the Future Privacy Forum and a fellow at the Business Roundtable Institute for Corporate Ethics for her work on stakeholder theory and trust. She is regularly asked to speak on privacy and the ethics of big data, including her recent Tedx talk. She has a forthcoming book with Ed Freeman and Bobby Parmar, The Logic of AND: Responsible Business without Trade-Offs.
She earned her B.S. Engineering from the University of Michigan and her MBA and PhD from the University of Virginia’s Darden Graduate School of Business
Novel Supply Chain Network Models Inspired by the COVID-19 Pandemic – From Optimization to Game Theory
The COVID-19 pandemic has dramatically illustrated the importance of labor (and its health and availability) to supply chains from food to healthcare. The pandemic has also revealed the fierce global competition for personal protective equipment (PPEs) and other medical supplies. In this presentation, I will overview some of our timely research on the development and solution of a spectrum of network-based supply chain optimization and game theory models that are inspired by such issues.
Anna Nagurney is the John F. Smith Memorial Professor in the Department of Operations & Information Management in the Isenberg School of Management at the University of Massachusetts Amherst. She is also the Founding Director of the Virtual Center for Supernetworks and the Supernetworks Laboratory for Computation and Visualization at UMass Amherst. She received her AB, ScB, ScM, and PhD degrees from Brown University in Providence, Rhode Island. She devotes her career to education and research that combines operations research / management science, engineering, and economics. In 2020, Professor Anna Nagurney was awarded the Harold Larnder Prize from the Canadian Operational Research Society and was selected to be an IFORS Distinguished Lecturer. She was elected a Fellow of the Network Science Society and received the award at the NetSci Conference at the University of Vermont in Burlington in May. She received the biannual Constantin Caratheodory Prize from the International Society for Global Optimization at its conference in Metz, France in July 2019. She was the Omega Rho Distinguished Lecturer for the INFORMS Annual 2018 Conference in Phoenix, Arizona.
In 2017 and 2018, Professor Nagurney was a Summer Fellow at the Radcliffe Institute for Advanced Study at Harvard University, where she worked on game theory network models for disaster relief and blood supply chains. She was also the co-organizer, with Ilias S. Kotsireas and Panos M. Pardalos, of the 3rd International Dynamics of Disasters Conference, which took place in Greece in July 2017.
She has given plenary and keynote talks in Austria, Germany, Ukraine, Argentina, Colombia, Switzerland, China, Sweden, Italy, Canada, New Zealand, the US, the United Kingdom, and other countries. Professor Nagurney has served on numerous prize and award committees both as a committee member and as Chair.
Ethics & Racial Justice Panelist
Dr. Ndu is a Director in KPMG’s Federal Artificial Intelligence, Analytics, and Engineering practice with over 19 years of experience. He specializes in advanced analytics modeling, risk characterization, and decision optimization frameworks. He currently leads the data analytics team responsible for implementing data-driven transformation of the US government’s background investigation process. Leveraging a range of analytics tools, combined with fluency in programing languages, he has guided the development of machine learning models that improve the efficiency and timeliness of the investigative process. Dr. Ndu earned his Bachelors and Master’s degrees in aerospace engineering and a PhD in reliability engineering, all from University of Maryland College Park.
Prior to joining KPMG, Dr. Ndu worked at Johns Hopkins Applied Physics Laboratory (APL) where he utilized advanced analytics methods in developing probabilistic, physics-based models for evaluating the reliability of aerospace systems. His achievements at APL include developing a risk-informed decision-making framework for NASA’s Radioisotope Power Systems (RPS) program, which enabled characterization of the risk profile of candidate dynamic power converters, establishing the technical framework for risk-informed service life evaluation of the US Navy’s Standard Missile, and advancing the use of conditional inference methods in probabilistic risk analysis of aerospace systems. His prior experience also includes work at the Federal Aviation Administration, the Missile Defense Agency, and NASA Goddard Space Flight Center.
Dr. Ndu also serves as adjunct faculty in the Applied and Computational Mathematics Program at Johns Hopkins University’s Whiting School of Engineering where he teaches courses in Mathematical Statistics.
Applying Moneyball Techniques to the 2020 Election: A 3rd Party Case Study
This case study describes how we built a 100 person all-volunteer data analytics team for the Jo Jorgensen for President campaign. We’ll start with how the Data Analytics group formed and evolved, then delve into 4 kinds of data and 5 analytics approaches, working with Marketing, to do historical analysis, target segment selection, message testing, channel choices, and pilot experiments, including experimental design. The talk wraps with some lessons learned and thoughts for research work after the campaign.
Since retiring in 2014 as a Director of Marketing and before that as a Director of Advanced Development at Teradata (a high-tech enterprise database company), “Dr Dave” has remained active on the Board of Directors for the Teradata University for Academics. In that role he creates materials for faculty and students to learn business analytics, data science, stats, and computer science. After he retired, he gave many Big Data talks, but in 2015 he added sports analytics to his repertoire.
Those talks have become VERY popular. In the past 4 years, he’s given 141 talks and done 138 side meetings at 74 schools to more than 5000 students, faculty, and athletics department personnel. In May 2019, he was the keynote speaker for the NCAA’s first Data Summit, presenting to athletic directors. Since early 2017, in addition to giving talks, he has focused on helping schools do “Moneyball on Campus” sports projects.
In May 2020, he joined the Jorgensen for President as a team lead for a volunteer group of data enthusiasts and has built the group doing election analytics for the campaign. Working closely with the marketing organization, the team is responsible for building propensity models for the best target voter groups.
Dr Dave holds a Ph.D. in Computer Science from Purdue University, and worked at 3 different high-tech database companies over 35 years in industry. A popular speaker and lecturer, he logged over 1.5M frequent flyer miles while helping sales teams and giving talks internationally. Fluent in German. Lives in LA, California 6 houses from the beach.
Joris van de Klundert
Eliminating Waiting Time Inequities for Deceased Donor Kidney Transplantation
Inequities in waiting times for deceased donor organ transplantation have received considerable attention in the last three decades and have motivated allocation policy reforms. This holds particularly true for kidney transplantation in the United States, where more than 90,000 patients are wait listed and waiting times vary considerably among patients from different blood types and ethnic groups. This research presents a novel approach to formally model, analyze, and optimize equity of transplant waiting times and probabilities using queuing models, network flows, and Rawls’ Theory of Justice. The presented formal models address inequities resulting from blood type incompatibilities, which are interrelated to ethnic differences in patient and donor rates. Moreover, we present results of a large empirical study on the deceased donor kidney wait lists in the United States. The case study findings indicate that the allocation policies currently practiced broadly resolve inequities as much as possible.
Joris holds an MSc in Management Informatics from Erasmus University Rotterdam, and a PhD in Operations Research from Maastricht University. He has served as assistant and associate professor of operations research at the Faculty of Sciences of Maastricht University, where he founded, directed, and co-owned spin off Mateum. As of 2008 he served as Full Professor of Value Chain Optimization of the School of Business and Economics of Maastricht University. In this position he initiated the new MSc program in Supply Chain Management & Change and co-developed the newly founded Venlo campus.
As of 2009 Joris chaired the department of Health Services Management & Organisation of the Erasmus School of Health Policy & Management, Erasmus University Rotterdam. From 2011 to 2014 he served as Vice-Dean of Education. Over these years he set up international research collaborations in Asia, the Middle East, Africa, and the America’s, and developed a variety of international executive education programs in healthcare leadership. These activities include assignments for the World Bank and World Health Organisation. He chairs the EU COST action ENC-KEP.
He has published in a wide variety of internationally leading journals (Operations Research, Manufacturing & Service Operations Management, Journal of the American Medical Informatics Association, Journal of Medical Internet Research). Joris is former chair of the Dutch Operations Research Society (NGB), and of INFORMS Healthcare conference 2017. He presently serves on the Graham Prize Selection Committee (AUPHA) and the program committee of EURO 2019.
Presently, Joris has the privilege to serve as founding faculty of the Prince Mohammad Bin Salman College for Business & Entrepreneursip, thus contributing to the transition the KSA is making towards a knowledge economy. He will also continue a special focus on the health & life sciences domain, and extend activities and network in this domain.