Author: admin

The University of Toronto Operations Research Group (UTORG) is hosting a lunch talk by Professor Amir Ahmadi Javid. The talk is entitled “Entropic Value-at-Risk and Its Applications”. Lunch and coffee will be provided. Hope to see you there!

Who: Professor Amir Ahmadi Javid, Amirkabir University of Technology, Iran   When: Wednesday, August 22nd @ 12:00pm – 1:00pm Where: MB101

Bio-sketch: Amir Ahmadi Javid is an Associate Professor in the Department of Industrial Engineering at the Amirkabir University of Technology, Iran. His research areas include Risk Management and Financial Engineering, Location Analysis and Facility Planning, Quantitative Methods in Management, Sustainable Development and Corporate Social Responsibility, Supply Chain Management, and Service System Design and Management. He uses mathematical tools such as Stochastic Modeling and Optimization, Large-scale Optimization, Probability and Statistics, and Game Theory in his research. Personal Website: http://www.aut.ac.ir/official/main.asp?uid=ahmadi_javid Abstract:  The entropic value-at-risk (EVaR) is a new coherent risk measure, which is an upper bound for both the value-at-risk (VaR) and conditional value-at-risk (CVaR). There are many applications of EVaR, including in healthcare, finance, and portfolio optimization. In this talk we are going to introduce the concept of EVaR and its applications. Here is a paper on using EVaR for portfolio optimization by Professor Javid: https://arxiv.org/pdf/1708.05713.pdf

Hi everyone,

Please see below for the information about The Principal Cup: An OR/MS Analytics Challenge. The deadline is Aug 30th, 2018. In the registration form, you may indicate University of Toronto as your INFORMS student chapter.

The INFORMS student chapter at the University of Michigan and Principal Financial Group have come together to create The Principal Cup: An OR/MS Analytics Challenge – a data analytics challenge tailored to the skills of INFORMS student chapter members across the world. Each quality submission (up to 3) yields $300 to the submitting team’s INFORMS student chapter. Furthermore, finalists are eligible for:

·       a travel stipend to present their solution and approach at the Challenge Showcase event,
·       the opportunity to publish their work in a refereed journal, and
·       the top three teams win cash prizes (1st place: $4,000; 2nd place: $2,000; 3rd place: $1,000).

The Principal Cup Challenge Showcase event will be hosted by the University of Michigan in Ann Arbor, MI on September 28, 2018. In addition to the finalists’ presentations to the panel of judges, there will be a networking social event for all participants. The challenge will launch on July 15, 2018 and final submissions are due on August 30, 2018. To learn more about the challenge and register, visit: https://www.ideaconnection.com/principal-orms-challenge/.

I would strongly encourage your INFORMS student chapter to organize teams of your best students to prepare for this Analytics Challenge. In addition to showcasing your student talent, there is an opportunity to secure funding to support local chapter activities and cash prizes for the top 3 teams.

We are looking forward to your INFORMS Student Chapter participation! (Please note these can be multiple teams from your chapter.)

For any further information, please contact:
Lawrence M. Seiford
Goff Smith Co-Director of the Tauber Institute for Global Operations
The University of Michigan
1205 Beal Avenue, room 2731
Ann Arbor, MI 48109-2117   USA
Voice: (734) 764-9422
email: seiford@umich.edu

The University of Toronto Operations Research Group (UTORG) is hosting a lunch talk by Buser Say. The talk is entitled “Planning in Factored State and Action Spaces with Learned Binarized Neural Network Transition Models”.  Lunch and coffee will be provided.  Hope to see you there!

Who: Buser Say, Ph.D. candidate, University of Toronto   When: Wednesday, August 01st @ 12:00pm – 1:00pm Where: MB101

Bio-sketch: Buser is a Ph.D. candidate at University of Toronto under the supervision of Professor Scott Sanner, and a member of the Data-Driven Decision Making Lab (D3M). Previously, he has completed my BASc. in Industrial Engineering from University of Toronto (2014) with emphasis on Operations Research, and earned my MASc. from University of Toronto (2016) as a member of the Toronto Intelligent Decision Engineering Laboratory (TIDEL). His main research focus is in the application of Operations Research techniques and Deep Neural Networks to our Data-Driven Automated Hybrid Planning framework. Abstract:  In this paper, we leverage the efficiency of Binarized Neural Networks (BNNs) to learn complex state transition models of planning domains with discretized factored state and action spaces. In order to directly exploit this transition structure for planning, we present two novel compilations of the learned factored planning problem with BNNs based on reductions to Boolean Satisfiability (FDSAT-Plan) as well as Binary Linear Programming (FD-BLP-Plan). Experimentally, we show the effectiveness of learning complex transition models with BNNs, and test the runtime efficiency of both encodings on the learned factored planning problem. After this initial investigation, we present an incremental constraint generation algorithm based on generalized landmark constraints to improve the planning accuracy of our encodings. Finally, we show how to extend the best performing encoding (FD-BLP-Plan+) beyond goals to handle factored planning problems with rewards.

The CMU INFORMS Student Chapter is excited to announce the second annual YinzOR Student Conference and poster competition, held in Pittsburgh, PA on August 24-25. YinzOR, sponsored by EQT Corporation and the Tepper School of Business, is a single-track conference that brings together students studying OR, OM, MS, IE, CS, or related areas, to facilitate interaction and collaboration with peers. This year we are honored to have speakers from Carnegie Mellon University, University of Pittsburgh, Georgia Tech University, University of Pennsylvania, Lehigh University, University of Michigan Ann Arbor, Google, and EQT Corporation.

In addition to talks, we’re also hosting a poster competition open to all PhD students in related fields. The panel of judges for the poster session will consist of CMU faculty members. The top three poster presenters will win cash prizes: $500 first place, $300 second place, $200 third place.

If you are interested and willing to present a poster, please email us (at informs@andrew.cmu.edu or mneda@andrew.cmu.edu) a one paragraph abstract (no more than 150 words) by July 31. You will be informed of the results by August 7. We provide up to $50 reimbursement for poster printing expenses to the accepted presenters.

More details of the 2018 YinzOR conference can be found on our website, and attendance is open to all PhD students.

The University of Toronto Operations Research Group (UTORG) is hosting a lunch talk by Christian Silva. The talk is entitled “Simulation model to assess the impact of a centralized scheduling policy for imaging procedures in Ontario”. Lunch and coffee will be provided. Hope to see you there!

Who: Christian Silva, MASc, University of Toronto   When: Wednesday, July 18th @ 12:00pm – 1:00pm Where: MB101

Bio-sketch: Christian is a MASc student in his final year under the supervision of Prof. Michael Carter at the University of Toronto. His area of study is the application of Operations Research in Healthcare. His thesis is a discrete event simulation model to test a new policy to reduce the wait time for imaging procedures. During his master’s degree, he has been involved as TA in multiple courses related to Simulation, Operations Research, and Operations Management, which are the areas of his main interest. Before starting his graduate studies, he worked for 5 years in Logistics and Process Improvement for retail and airlines. Upon graduation, he will join a fintech company as Process Manager. Abstract:  Due to constrained capacity, wait times for imaging procedures in Ontario hospitals are frequently higher than the provincial target. A new approach that centrally schedules outpatients and assigns them between different locations is expected to be more efficient. Discrete event computer simulation was used to evaluate the impact of this approach by comparing individual hospital models versus a centralized model with imaging demand data from two Ontario hospitals. Results show that the proposed policy can lead to shorter wait times in the system. We also analyzed the different variables that drive better system performance. Final recommendations are given on the real-life application of this policy.