Awards Hall

Edelman Award Ceremony

Recognizing Distinction in Applications of Analytics, Operations Research, and the Management Sciences

The Franz Edelman Award, emphasizing beneficial impact; INFORMS Prize, emphasizing long-term, multi-project success; Daniel H. Wagner Prize, emphasizing innovative methods and clear exposition; and the UPS George D. Smith Prize, emphasizing effective academic preparation, will be awarded at this elegant presentation. Admission to the award ceremony is included in your registration fee. The ceremony begins at 5:30pm.

Since 1972, INFORMS and the OR/MS and analytics community has celebrated and honored the very best in applied work in business or government with the annual Franz Edelman Award Competition. 2021 marks the 50th anniversary of this outstanding and rigorous competition. Since 2006, we have marked this special occasion with the Edelman Award Ceremony, an evening filled with fun, excitement, and pride for the entire community. The 2021 Award Ceremony, scheduled for Tuesday, April 13, promises to have hundreds of international analytics professionals and business leaders in attendance.

Thank You to Our Sponsors

Edelman Executive Level

INFORMS Prize

This prize is awarded annually to the company that effectively integrates analytics into organizational decision-making, and has repeatedly applied ORMS principles in pioneering, novel and lasting ways. The 2021 prize winner, Amazon, will describe their innovative O.R. work in the INFORMS Prizes and Special Sessions Track on Wednesday, April 14 at 11am EDT. The 2021 winner will be recognized at the Edelman Awards Ceremony on Tuesday, April 13.

View the 2021 INFORMS Prize Reprise Session

Previous winners include: Booz Allen Hamilton, B.N.S.F. Railways, Disney, U.S. Air Force, GM, Chevron, Memorial Sloan-Kettering Cancer Center, Sasol, Jeppesen, Intel, General Electric Global Research Center, Schneider National, Air Products and Chemicals, Procter & Gamble, UPS and other leading companies.

Learn more about the INFORMS Prize here.

UPS George D. Smith Prize

The George D. Smith Prize is aimed at strengthening ties between academia and industry by rewarding institutions of higher education for effective and innovative preparation of students to be good practitioners of operations research. The Prize is generously underwritten by UPS. Awarded for the first time in 2012, past winners are Carnegie Mellon University, H. John Heinz III College, Sauder School of Business, University of British Columbia – Center for Operations Excellence, MIT Leaders for Global Operations, Naval Postgraduate School, and Tauber Institute for Global Operations at University of Michigan.

The 2021 Competitors are:

Mili Mehrotra

Vishal Sachdev

Sridhar Seshadri

Ramanath Subramanyam

Gedas Adomavicius

Ravi Bapna

Alok Gupta

De Liu

Ellen Trader

Ann Campbell

Nanette Chapa

Lindsey Peters

Zach Veigulis

The teams will present their work to the judges on Friday, April 9. Videos of the competition will be found in the video on-demand library on the virtual meeting platform.

The Smith Prize winner will be announced at the Edelman Awards Ceremony on Tuesday, April 13. The 2021 winner will give their presentation on Wednesday, April 14 in the INFORMS Prizes & Special Sessions Track.

View the 2021 UPS George D. Smith Prize Reprise Session

Learn more about the UPS George D. Smith Prize here.

Return to top

Daniel H. Wagner Prize for Excellence in Operations Research

The Daniel H. Wagner competition is held each fall at the INFORMS Annual Meeting. The 2020 Wagner Prize Reprise will take place on Monday, April 12 in the INFORMS Prizes & Special Sessions Track.

The 2020 Wagner winning submission was authored by:

Saurabh Bansal

Genaro J. Gutierrez

Mahesh Nagarajan

Distribution Estimation and Efficient Optimization for Portfolio Management in Agribusiness: Analytical Developments and Benefits

We worked with an agribusiness firm to develop new mathematical algorithms to manage the firm’s annual $1 Billion portfolio of more than 200 seeds offered to farmers in the continental U.S. The algorithms included, (i) optimization-development to deduce probability distributions for production yields for new products when managers provide partial information for the distributions, and (ii) a decomposition based development to optimize the production plan for the firm’s portfolio with more than 600 uncertainties. The algorithms have yielded substantial monetary savings and intangible benefits.

View the 2020 Wagner Prize Reprise Session

This prize emphasizes the quality and coherence of the analysis used in practice. Dr. Wagner strove for strong mathematics applied to practical problems, supported by clear and intelligible writing. The Wagner Prize recognizes those principles by emphasizing good writing, strong analytical content and verifiable practice successes. The competition is held and the winner is announced at the INFORMS Annual Meeting in the fall.

Past awardees include practitioners and researchers from Lehigh University and the Pennsylvania Department of Corrections, The Forestry Research Institute of Sweden, CDC, Ford, U.S. Coast Guard, Intel, IBM T. J. Watson Research, Schneider National, Boston University, University of Florida, and others.

Learn more about the Daniel H. Wagner Prize here.

Return to top

Consider applying for the 2021 Wagner Prize competition!

Submission deadline
May 2, 2021

Learn more about the Wagner Prize application process here.

Innovative Applications in Analytics Award (IAAA)

Sponsored by INFORMS Analytics Society, Kinaxis, and Adelphi University

The IAAA Finalists will present on Tuesday, April 13 in the INFORMS Prizes & Special Sessions Track. The winner will be announced at the closing plenary session on Wednesday, April 14.

The purpose this award is to recognize the creative and unique application of a combination of analytical techniques in a new area. The prize promotes the awareness and value of the creative combination of analytics techniques in unusual applications to provide insights and business value. The Analytics Section leadership would like to cordially thank all the members of the judging committee for their hard work in selecting these finalists.

Learn more about the Innovative Applications in Analytics Award here.

Finalist Teams and Abstracts:

Operations Research Improves Biomanufacturing Efficiency at MSD Animal Health

Abstract

Biomanufacturing methods use living organisms (i.e., viruses and bacteria) to generate active ingredients, and this leads to challenges that are different to those incurred by other industries. For example, biomanufacturers often deal with high levels of uncertainty and batch-to-batch variability in production yield, lead times, and costs. Bio-safety requirements impose constraints, such as a no-wait requirement throughout the production process. In addition, biomanufacturing operations are cost and labor intensive, and involve high risks of failure. To address these challenges, a multidisciplinary team of researchers collaborated over three years to develop a portfolio of optimization models and decision support tools. These tools were aimed at improving biomanufacturing efficiency using a variety of operations research methodologies, including stochastic optimization, Bayesian design of experiments, and simulation-optimization. The developed models link the underlying biology and chemistry of biomanufacturing processes with financial trade-offs and business risks. The research has been conducted in close collaboration with Merck Sharp & Dohme Animal Health (MSD AH) in Boxmeer, the Netherlands. Industry implementation at MSD AH had a significant impact with up to 50% increase in batch yield and an additional revenue of 50 million euro per year.

Team

Tugce Martagan, Eindhoven University of Technology
Bram van Ravenstein, MSD Animal Health
Oscar Repping and Marc Baaijens, MSD Animal Health

Tuesday, April 13 at 1:45pm EDT

View the MSD Animal Health Competition Session

Personalized Recommender System Design for an Online B2B Platform

Abstract

We collaborated with IndiaMart, the largest online B2B platform in India, to design and implement a personalized recommender system for participant firms. In this problem, buyers place requests for quotation (RFQs) to the platform, and the objective of the platform is to match the RFQs with suitable sellers with the highest likelihood of acceptance. The core of our algorithm involves predictive and prescriptive analytics to first learn sellers’ preferences from their historical behavior using an attribute-based logit model and feature engineering, and then to determine the display order of RFQs on the sellers’ webpages. Our algorithm is novel in two respects: (1) new closeness metrics to learn sellers’ evolving preferences from high-dimensional and sparse data; (2) methods to counter the problem of class imbalance using a new resampling strategy we propose, which we call Panel Data Augmentation Technique (PDATE). We implemented our algorithm in a controlled field experiment at IndiaMart since January 2020, resulting in a significant improvement in the acceptance of recommended RFQs from the top of the webpage. The improvement is consistent and sustained over time including during the pandemic. After a pilot test with 21 sellers, the company has now adopted the algorithm for 2,000 sellers in a gradual expansion to a larger scale.

Team

Vishal Gaur, Cornell University
Xiaoyan Liu, Cornell University
Gaurang Manchanda, IndiaMART

Tuesday, April 13 at 2:25pm EDT

View the IndiaMART Competition Session

Using Machine Learning to Improve Public Reporting on U.S. Government Contracts

Abstract

The U.S. Government procures more than $500 billion annually in goods and services on public contracts, which it classifies using a hierarchical product and service taxonomy. Classification serves several purposes including transparency in the use of taxpayer funding, reporting, tracing and segmenting government expenditures, budgeting and forecasting. Government acquisition personnel have historically performed these classifications manually, resulting in a process that is time-consuming, error-prone and that limits visibility into government purchases. We improve classification by leveraging natural language processing and machine learning techniques to generate a descriptive manual and a predictive classifier. Using 4 million historical data records on governmental purchases, we fit a machine learning classifier and demonstrate (a) superior performance when explicitly modeling the hierarchical structure of information domains through the use of top-down strategies; and (b) the effectiveness of character-level convolutional neural networks when textual inputs are terse and contain irregularities such as abnormal character combinations and misspellings, common in government contracts. Our machine learning models are embedded in multiple software applications, including a web application we developed, used by government personnel and other contracting professionals. Our innovative approach demonstrates a significant potential for sharply reducing the time spent by public officials in categorizing procurement transactions.

Team

William A. Muir, U.S. Air Force Installation Contracting Center
Roger H. Westermeyer, U.S. Air Force Installation Contracting Center
Daniel Reich, Naval Postgraduate School

Tuesday, April 13 at 3:05pm EDT

View the U.S. Government Contracts Competition Session

Data-driven COVID-19 Vaccine Development for Janssen

Abstract

The COVID-19 pandemic has spurred extensive research in vaccine development. However, Phase III vaccine trials’ success highly depends on future COVID-19 incidence rates at trial sites. To accurately predict these rates, we created DELPHI, a novel policy-driven and machine-learning powered epidemiological model. DELPHI has been the centerpiece of site selection for Ad26.COV2-S, the leading vaccine candidate from Janssen.

Team

Dimitris Bertsimas, Massachusetts Institute of Technology
Michael Lingzhi Li, Massachusetts Institute of Technology
Omar Skali Lami, Massachusetts Institute of Technology
Hamza Tazi Bouardi, Massachusetts Institute of Technology
Ali Haddad-Sisakht, Dynamic Ideas LLC
Jennings Xu, Janssen Pharmaceuticals
Jose Zamalloa, Janssen Pharmaceuticals
Amir Hashemi, Janssen Pharmaceuticals
Ankit Lodha, Janssen Pharmaceuticals
Yuqi Shang, Janssen Pharmaceuticals
Kris Standish, Janssen Pharmaceuticals
Shi-hua Yu, Janssen Pharmaceuticals
Levon Demirdjian, Janssen Pharmaceuticals
Xiaoying Wu, Janssen Pharmaceuticals
Sid Jain, Janssen Pharmaceuticals
Najat Khan, Janssen Pharmaceuticals

Tuesday, April 13 at 3:45pm EDT

View the Janssen Competition Session

Predictive Analytics for Detection of Metastatic Cancer

Abstract

We used data-analytics approaches to develop, calibrate, and validate predictive models, to help urologists in a large statewide collaborative make prostate cancer staging decisions on the basis of individual patient risk factors. These models were used to design guidelines that optimally weigh the benefits and harms of radiological imaging for detection of metastatic prostate cancer. The Michigan Urological Surgery Improvement Collaborative (MUSIC), a statewide medical collaborative comprising more than 90% of urologists in the state of Michigan, 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%. A subsequent follow-up study a year after implementation confirmed the substantial reduction in imaging without any statistically significant change in prostate cancer detection. The major reduction in imaging was estimated to save more than $260, 000 per year. More importantly, the reduced imaging is associated with reduced anxiety and harm to patients resulting from false positive outcomes that can lead to other more invasive procedures, and the increased access to imaging for patients with other diseases and conditions warranting imaging.

Team

Selin Merdan, University of Michigan
Christine Barnett, University of Michigan
David Miller, University of Michigan
James Montie, University of Michigan
Brian Denton, University of Michigan

Tuesday, April 13 at 4:25pm EDT

View the University of Michigan Competition Session

Using Analytics to Understand and Improve Provider Accessibility for a State Medicaid Agency

Abstract

Geographical Information Science (GIS) methods play a critical role in determining the equity and capacity of health services for populations. Findings from GIS analyses are especially important for health administrative personnel and other stakeholders tasked with facilitating the provision of health services for underserved populations such as Medicaid beneficiaries. Many government agencies such as state Medicaid agencies, however, experience challenges in recruiting and retaining staff with GIS skill sets. Therefore, key employee turnover can serve as a detriment to the analytic operations of a government organization. Given this consideration, streamlining empirical GIS workflows for subject matter experts and citizen data scientists have promise in promoting 1) labor cost-efficiencies at health organizations, as well as 2) strategies to ameliorate health among beneficiaries. The purpose of this case report discussion is to highlight the development and application of a GIS tool designed to automate several GIS methods of high interest to the Alabama Medicaid Agency, which is the primary insurer for over one million Alabamians each year. Moreover, this tool includes some modeling techniques rarely integrated in Medicaid agencies’ assessment of physical access. This discussion also highlights some successes, challenges, and early-stage implementation of prescriptive analytics within the described geodesign project.

Team

Dwight Lewis Jr., University of Alabama
Jason Parton, University of Alabama
Matthew Hudnall, University of Alabama
Nick Freeman, University of Alabama
Irem Sengul Orgut, University of Alabama
Xin Yang, University of Alabama
Thomas English, University of Alabama
James Cochran, University of Alabama
Steven Samsel, University of Alabama
Ryan Tramp, University of Alabama

Tuesday, April 13 at 5pm EDT

View the University of Alabama Competition Session

Return to top

Syngenta Crop Challenge in Analytics

Brought to you by INFORMS Analytics Society
Powered by IdeaConnection

The population of Earth is growing daily and our world is running out of land needed to produce food. Meanwhile, the crops farmers plant face escalating challenges due to increasingly variable growing conditions and climate change.

Today, the agriculture industry works to maximize the amount of food we gain from crops by breeding plants with the strongest, highest-yielding genetics. Plant breeding is complex, and data analytics can help scientists at research and development organizations like Syngenta make advances in seed product development

Syngenta has proven that data-driven strategies can help our industry accelerate innovation and breed better seeds that require fewer resources and are adaptable to more diverse environments. Developing models that can predict the performance of potential corn products can help scientists more accurately select seeds that increase the productivity of the crops farmers plant – and will help address the growing global food demand.

Teams will put their analytics skills to the test for a chance to win up to $5,000.

The finalists will present on Monday, April 12. The winner will be announced at the closing plenary session on Wednesday, April 14.

Learn more about the Syngenta Crop Challenge here.

Finalist Teams:

Optimal Schedules for Corn Planting and Storage

Abstract

Corn (or maize) is, together with rice and wheat, accounting for 94% of all cereal consumption, making it one of the most consumed cereals in the world. The breeding of seeds with desirable traits is spurring the development of new, emerging technologies, which in turn creates the need to increase the efficiency of harvesting and storage operations. In the present report, we address the problem posed by the Syngenta Challenge, which is focused on corn planting, harvesting and storage. The problem consists on determining an optimal planting schedule, first, considering a pre-defined storage capacity for two sites, and second, where this capacity must also be specified. We propose a two-step methodology to produce an optimal schedule that ensures that ensures that the harvested corn can be stored in the available facilities. In the first step, we made a forecast of accumulated GDUs using historical data to estimate the available GDUs for 2020 and 2021 and produced tables of required number of days to maturity of the plants. In the second step, these
tables were fed to an optimization model. Additionally, we introduce a stochastic model to add robustness to the solution. Our solution represents an schedule and suggests warehouse capacities and strategies for robust operations.

Team

Reena Kapoor, CSIRO Data61
Rodolfo García-Flores, CSIRO Data61

Monday, April 12 at 10am EDT

View the Optimal Schedules for Corn Planting and Storage Competition Session

Optimizing Crop Planting Schedule Considering Planting Window & Harvesting Capacity

Abstract

Crop planting schemes are sensitive to dynamic weather conditions and harvesting capacity. In this study, a mathematical model has been developed to address the planting and harvesting decision making, considering the crop growth as well as resources available. In this context, we developed a two-phase methodology. In the first step, a GDU prediction model was developed utilizing historical climate data. The proposed 1D-CNN model can predict GDU with an RRMSE of 7% to 8% depending on the training data set. These predicted GDUs were then used in the second step, where an optimization model was developed to provide weekly harvest quantity. The objective of the decision-making model was to achieve even allocation within a minimum number of weeks with both fixed and variable site capacity. The model was implemented for two different geographic locations under two different capacity scenarios. The model was able to provide an optimal planting schedule respecting planting date and site capacity. This planting schedule will direct the harvesting to be completed within 51 weeks and 52 weeks respectively for the first site and the second site. This will help to reduce the labor cost and overcapacity in the harvesting phase. The model has also demonstrated its robustness by performing well under multiple scenarios and for multiple locations.

Team

Saiara Samira Sajid, Iowa State University
Guiping Hu, Iowa State University

Monday, April 12 at 10:30am EDT

View the Optimizing Crop Planting Schedule Considering Planting Window & Harvesting Capacity Competition Session

A Multiobjective, Soft Constraint Solution to the 2021 Syngenta Crop Challenge

Abstract

In response to the 2021 Syngenta Crop Challenge in Analytics, this article describes a solution that uses elements from data science and optimization to produce a planting schedule that attempts to minimize the median and maximum absolute deviation from capacity, as well as the number of nonzero harvest weeks, while respecting planting windows and weekly harvest capacities. In one scenario, capacities for two sites are specified. For the other scenario, capacities must be suggested. We used a Long Short-Term Memory model to predict GDUs for 2020 and 2021, based on historical data. Then we used a genetic algorithm to produce a Pareto front of solutions. Building upon the initial basic model, we optimized a new set of objectives that imposed soft capacity constraints. This yielded improved results, and led us to a strategy whereby we suggested capacities for the second scenario.

Team

Mingshi Cui, Miami University
Kunting Qi, Miami University
Julia Loncala, Miami University
Byran Smucker, Miami University

Monday, April 12 at 11am EDT

View the A Multiobjective, Soft Constraint Solution to the 2021 Syngenta Crop Challenge Competition Session

Scheduling Planting Time Through Developing an Optimization Model and Analysis of Time Series Growing Degree Units

Abstract

Producing higher-quality crops within shortened breeding cycles ensure global food availability and security, but this improvement intensifies logistical and productivity challenges for seed industries in the year-round breeding process due to the storage limitations. In the 2021 Syngenta crop challenge in analytics, Syngenta raised the problem to design an optimization model for the planting time scheduling in the 2020 year-round breeding process so that there is a consistent harvest quantity each week. They released a dataset that contained 2569 seed populations with their planting windows, required growing degree units for harvesting, and their harvest quantities at two sites. To address this challenge, we developed a new framework that consists of a weather time series model and an optimization model to schedule the planting time. Our computational experiment found that the proposed times-series structure achieved a relative root-meansquared error (RRMSE) of 7% for the five test years (2015-2019), outperforming other state-of-the-art time-series models such as convolutional neural networks (CNN) and deep fully connected neural network (DNN). The proposed optimization models also scheduled the seed population’s planting time at the fewest number of weeks with a more consistent weekly harvest quantity. Using the proposed optimization models can decrease the required capacity by 69% at site 0 and up to 51% at site 1 compared to the original planting time.

Team

Javad Ansarifar, Iowa State University
Faezeh Akhavizadegan, Iowa State University
Lizhi Wang, Iowa State University

Monday, April 12 at 11:30am EDT

View the Scheduling Planting Time Through Developing an Optimization Model and Analysis of Time Series Growing Degree Units Competition Session

Return to top

Edelman Award Ceremony

Recognizing Distinction in Applications of Analytics, Operations Research, and the Management Sciences

Thank You to Our Sponsors

2021 Awards & Competitions

INFORMS Prize

UPS George D. Smith Prize

Mili Mehrotra

Vishal Sachdev

Sridhar Seshadri

Ramanath Subramanyam

Gedas Adomavicius

Ravi Bapna

Alok Gupta

De Liu

Ellen Trader

Ann Campbell

Nanette Chapa

Lindsey Peters

Zach Veigulis

Daniel H. Wagner Prize for Excellence in Operations Research

Saurabh Bansal

Genaro J. Gutierrez

Mahesh Nagarajan

Distribution Estimation and Efficient Optimization for Portfolio Management in Agribusiness: Analytical Developments and Benefits

Innovative Applications in Analytics Award (IAAA)

Finalist Teams and Abstracts:

Syngenta Crop Challenge in Analytics

Finalist Teams:

Get the Latest Updates