Past Webinars

Advanced Analytics in the Land of Moore’s Law

Speaker: Karl G. Kempf, Intel

The Decision Engineering Group was founded at Intel Corporation in August 1987. For the first 20 years, we focused on manufacturing and supply chain problems, then in 2007  expanded our scope to include product design and development problems. I will briefly describe the major projects over this time. Then I will present a few of the basics of how the group is constituted – how we pick projects – our development process – interactions with our internal customers – and more. There will be ample time allotted for questions and answers.


    Watch the Advanced Analytics in the Land of Moore’s Law recording


    O.R. for Social Good Practical Implementations

    Speaker: Dr. Natalia Summerville, SAS Institute

    Natalia will provide overview of four Data4Good Optimization applications:

    • Medical Resource Optimization for Cleveland Clinic
    • Student Monitor Optimization for Boston Public Schools
    • Collection Site Optimization for Mothers Milk Bank
    • Back-to-School Optimization for Durham Public Schools

      Watch O.R. for Social Good Practical Implementations recording


      Driving Business Value at Ford through Analytics

      Speaker: Erica Klampfl, Ford Motor Company

      Ford Motor Company and the automotive industry have a long history of applying analytics to solve tough business problems. New technology, data sources and analytics methodology are unlocking business value and enabling Ford to address some of the most challenging problems facing the industry.  Erica will share her lessons learned from leading an analytics organization at Ford.

      Watch the Driving Business Value at Ford Analytics recording


      Deep Transformation with Smart Supply Chain Digitization

      Speaker: David Simchi-Levi, MIT

      The presentation is focused on a practical supply chain digitization strategy that includes three important components: a unified, single, view of demand; supply chain segmentation; and smart planning and execution, all of which are powered by Digitization, Analytics and Automation.

      Watch the Deep Transformation with Smart Supply Chain Digitization webinar recording


      Veritec Solutions Revolutionizes Self Storage Pricing Practices

      Speaker: Dr. Warren H. Lieberman, Veritec

      Using customer segmentation techniques in a new and innovative manner, we highlight an automated and dynamic capability known as Value Pricing. Without using purchase fences/restrictions, Value Pricing allows offering customers multiple rates for a product previously offered at a single price. By introducing the concept of “dynamic relative desirability,” Value Pricing enables greater revenue gains than the static inventory allocation approach used in some industries to differentiate inventory, such as the seat selection process for airlines, where certain types of seats are sold for premiums. We will show how Value Pricing is incorporated into the websites of several companies.

      The increased revenues made possible by these methods is a “game changer” for many self-storage companies. The President of one company has described it as the “next step in self storage evolving and growing.”

      Watch the Veritec Solutions Revolutionizes Self Storage Pricing Practices webinar recording


      Building and Sustaining Analytics at Chevron

      Speaker: Margery Connor, Chevron

      Chevron and the energy industry have a long history of applying analytics to solve tough business problems. See examples in this article. With the business challenges and the technologies to solve them growing dramatically over the past decade, building an analytics team of the appropriate size and skillset has been a moving target. Margery will share her lessons learned from leading the analytics organization at Chevron.

      Watch the Building and Sustaining Analytics at Chevron webinar recording


      Predictive Models for Optimizing Imaging Decisions for Detection of Metastatic Prostate Cancer

      Speaker: Dr. Brian Denton, University of Michigan

      We used data-analytics approaches to develop, calibrate, and validate predictive models, to help urologists in a large state-wide collaborative make prostate cancer staging decisions on the basis of individual patient risk factors. The models we developed predict the probability a patient who receives radiographic imaging will have metastatic cancer. The models were developed using observational data for patients diagnosed with prostate cancer. We experimented with a variety of machine learning methods and compared their performance at predicting outcomes of imaging. The models were validated using statistical methods based on bootstrapping and subsequent evaluation on out-of-sample data. These models were used to design guidelines that seek to optimally weigh the benefits and harms of radiological imaging for detection of metastatic prostate cancer. The Michigan Urological Surgery Improvement Collaborative, a state-wide medical collaborative, implemented these guidelines, which were predicted to reduce unnecessary imaging by more than 40% and limit the percentage of patients with missed metastatic disease to be less than 1%. The effects of the guidelines were measured post-implementation to confirm their impact on reducing unnecessary imaging across the state of Michigan.

      Co-authors:
      Selin Merdan, Christine Barnett
      Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, MI
      James E. Montie, David C. Miller
      Department of Urology, University of Michigan, Ann Arbor, MI,
      Michigan Urological Surgery Improvement Collaborative, Ann Arbor, MI

      Watch the Predictive Models for Optimizing Imaging Decisions for Detection of Metastatic Prostate Cancer webinar recording


      Model Serving and MLOps

      Speaker: Dr. Diego Klabjan, Northwestern University and Center for Deep Learning

      Advanced analytics, in particular deep learning and real-time decision making, is ready to take the next step to transition to production and operations where MLOps and DevOps become crucial. Model serving, one of the most important part of MlOps, possesses unique challenges not present in training. We will discuss differences and challenges, and common solution principles and frameworks. You will learn the concepts of drift detection, monitoring, and feature stores. IoT use cases will be discussed

      Watch the Model Serving and MLOps webinar recording


      Optimization: It’s Math and Psychology

      Speaker: Jack Levis, retired

      Turning data into a business advantage through optimization is the goal of most organizations. The ever growing availability of data, along with expanding computing power and tools, opens the door to businesses gaining competitive advantage through analytical processes and skill. But, there is much more to making an impact than just creating advanced algorithms.  Organizations change is also essential.

      Watch the Optimization: It’s Math and Psychology webinar recording


      Media Manipulation in the 2020 Elections: Implications for National Security

      Speaker: Douglas A. Samuelson, InfoLogix, Inc.

      Elections have become increasingly driven by images, memes and social media messaging rather than policy statements.  We review some prominent examples from US Presidential campaigns and discuss how confusing and disruptive messaging was used.  We note how these methods could also be used to disrupt defense and intelligence networks and draw some lessons learned about how to increase national security.

      Watch the Media Manipulation in the 2020 Elections: Implications for National Security webinar recording


      Analytics for Infectious Disease Control

      Speakers: Dr. Pinar Keskinocak, Georgia Institute of Technology and Dr. Julie Swann, NC State University

      There has been a lot of progress in medicine and science in understanding and preventing infectious diseases over time; however, these diseases still threaten human health. A variety of prevention or intervention measures may be available, and it is important to understand which combination of these measures would be most impactful, when and where, particularly under resource limitations.  In this presentation we will provide examples on how operations research and analytics methods can  be used in supporting public health interventions for infectious diseases.

      Watch the Analytics for Infectious Disease Control webinar recording


      Supply Chain Resilience Through Planning and Design

      Speakers: Zahir Balaporia, CAP, FICO Xpress Optimization and Duncan Klett, Kinaxis, Inc.

      The COVID pandemic demonstrated, yet again, the importance of supply chains and their susceptibility to disruption.

      This webinar will cover processes and technology for measuring and improving resiliency, as well as mechanisms  that allow organizations to respond with confidence in re-planning and execution, enabling a resilient supply chain.

      Watch the Supply Chain Resilience Through Planning and Design webinar recording


      Inventory, Packages, Price Points and People: An Inside Look at Leading Technical People

      Speakers: Pallav Chhaochhria, Citi; Pooja Dewan, Otis Elevator; Mallory Freeman, UPS; Anne Robinson, Kinaxis

      How do the best geeks in the industry motivate and manage their technical teams? Hear from:

      • Pallav Chhaochhria, PhD
        Director of Pricing Algorithms at Citi
      • Pooja Dewan, PhD
        VP, Chief Data and Analytics Officer at Otis Elevator,
      • Mallory Freeman PhD
        Director of Data Science and Machine Learning at UPS
      • Anne Robinson, PhD
        Chief Strategy Officer at Kinaxis

      Watch the Inventory, Packages, Price Points and People: An Inside Look at Leading Technical People webinar recording 


      Blood, Sweat, and PPEs: Rescuing Perishable Product Supply Chains and Impacting Policy through Analytics

      Speaker: Anna Nagurney, University of Massachusetts Amherst and Supernetworks

      In this webinar, Dr. Nagurney will talk about how this pandemic is affecting perishable product supply chains and how analytics can be used to determine the steps for recovery.

      Watch the Blood, Sweat, and PPEs: Rescuing Perishable Product Supply Chains and Impacting Policy through Analytics webinar recording