Introduction: 2021 Franz Edelman Award for Achievement in Advanced Analytics, Operations Research, and Management Science
Abstract
This special issue of the INFORMS Journal on Applied Analytics (formerly Interfaces) is devoted to the finalists of the 50th annual competition for the Franz Edelman Award for Achievement in Advanced Analytics, Operations Research, and Management Science, the profession’s most prestigious award for deployed work. As in previous years, the finalists this year cover a wide range of industries and functions.
It is an honor for us to serve as chair and special-issue editor, respectively, of the 50th annual international competition for the Franz Edelman Award for Achievement in Advanced Analytics, Operations Research, and Management Science. Because of the COVID-19 pandemic, the INFORMS Analytics Conference was held virtually in April 2021. On April 12, the finalists’ competition videos were shown. On April 13, the judges began their virtual deliberations in the morning; that evening, all finalists were celebrated, and the first-place winner was announced at the Edelman Award Ceremony.
In this special issue, six finalist teams describe how they applied operations research (OR) and advanced analytics to solve difficult decision problems. The problem domains include assigning robots, feeding the hungry, optimizing an entire supply chain, routing drivers, scheduling production and order pickups, and treating cancer patients. These entries highlight not only the high-impact models the proponents have created but also the remarkable and diverse ways these proponents have made advanced analytics modeling and analysis a part of strategic thinking and operational practice at their organizations. Three of the finalist teams are based primarily in China, one in Africa, one in Europe, and one in the United States. Four of the teams have authors from multiple countries.
About the Edelman Award Competition
The Franz Edelman Award competition is jointly sponsored by INFORMS and the INFORMS Section on Practice. The purpose of the competition is to bring forward and recognize outstanding examples of advanced analytics, OR, and management science (MS) practice. The award is named in honor of Franz Edelman, who established one of the earliest industrial analytics and OR/MS groups in North America at RCA. He worked at RCA for more than 30 years and is counted among the fathers of innovation in analytics and OR/MS.
The first-place and finalist awards are for implemented work that has had significant, verifiable, and measurable impact. The impact may be beneficial to the organization winning the award (e.g., by increasing its revenues) or to others (e.g., by reducing pollution). INFORMS presents trophies commemorating the finalist awards to the client organizations that used the finalists’ work and presents medals to the finalist authors. This year, the prize money totaled $15,000, with $10,000 going to the first-place winner. More important, the finalists have the honor and satisfaction of knowing their work has been recognized by their peers as the best in the profession. In addition to having their efforts described in this special issue of the INFORMS Journal on Applied Analytics, all finalists have their presentations available at https://www.informs.org/Resource-Center/Video-Library/Edelman-Competition-Videos. The Edelman finalist presentations are also available on the INFORMS YouTube channel: https://www.youtube.com/channel/UCCwr0VjkxPvbt9xNmKOHHFA.
The Process
The Edelman Award process begins with a call for entries in the summer prior to the scheduled competition date (in 2020 for this competition). The selection committee reviews all entrants and selects a set of semifinalists. Verifiers then work behind the scenes to validate the claims made by each semifinalist and to convey this information to the rest of the selection committee. Verification is performed by a mix of practice-oriented academics and full-time practitioners. The verifiers communicate directly with the entrant’s team, the users of the work, and client management. Support from client executives is important. Verification is a crucial element of the competition because it ensures that only the highest-achieving OR/MS and advanced analytics work makes it to the Edelman Award finals. All verifiers are provided with written guidelines and sample verification reports, and novice verifiers are paired with experienced verifiers.
The selection committee studies and discusses the verification reports to select six finalists. Coaches are assigned to each finalist team; these coaches help the finalists improve their papers and presentations for the competition. Typically, multiple iterations of paper and presentation drafts are required to clearly convey the work to a general INFORMS readership and audience within a limited number of pages and presentation lengths.
Judges study the papers, listen to the presentations, and then discuss the finalists’ accomplishments until they reach a decision on which finalist is most deserving of the Franz Edelman Award for Achievement in Advanced Analytics, Operations Research, and Management Science. Relevant factors include the overall impact and value of the application, the level of technical innovation, the difficulty of the obstacles surmounted, and the work's portability to other application contexts.
The Finalists and the Papers in This Issue
Here is a summary of the finalists listed in the sequence in which their papers appear in this special issue, beginning with the 2021 first-place team.
United Nations World Food Programme for UN World Food Programme: Toward Zero Hunger with Analytics
The United Nations World Food Programme (WFP) uses analytics to manage its operations in providing food assistance in over 80 countries. The WFP paper describes three of its analytics solutions: a supply chain dashboard that includes predictive analytics, mixed-integer programming for diet and supply chain planning optimization, and a data integration platform. Pareto-efficient curves are generated to help users understand trade-offs, such as how the cost per beneficiary varies as a function of the percentage of the nutritional or caloric requirements being met. During the past decade, WFP’s work has led to the creation of a supply chain planning unit and to savings of more than $150 million—enough to support two million food-insecure people for an entire year. WFP received the Nobel Peace Prize in 2020.
Alibaba for Alibaba Vehicle Routing Algorithms Enable Rapid Pick and Delivery
Alibaba developed an inner-sourced framework (i.e., software similar to open-sourced code but proprietary and intended for internal use) of solutions to a variety of vehicle routing problems, including order pickup and delivery, faced by its subsidiaries. Its core approaches use both an adaptive large neighborhood search and deep reinforcement learning (DRL). The adaptive large neighborhood search contains over 20 ruin and over 10 repair operators, making it applicable to many problems, whereas the DRL approach works better for many others. The work led to more than $50 million in annual financial savings while providing more reliable on-time delivery for customers.
JD.com for JD.com: Operations Research Algorithms Drive Intelligent Warehouse Robots to Work
JD.com built intelligent warehouses that use analytics to significantly improve the efficiency of its warehouses. It uses robotic automated guided vehicles (AGVs) to move racks of inventory to picking (and other) workstations. Every five seconds, a three-second process is run to determine the assignment of AGVs to racks to workstations. The dual objectives are to minimize AGV travel time and satisfy demand. It decomposes the problem into two subproblems with Lagrangian multipliers. One subproblem is a small integer program; it relaxes this problem into a linear program, adds cutting planes, and then rounds the results to the nearest integers. The other subproblem is equivalent to a linear program that is solved with the Hungarian algorithm. The construction of the intelligent warehouses has led to estimated annual savings of hundreds of millions of dollars.
Lenovo for Lenovo Schedules Laptop Manufacturing Using Deep Reinforcement Learning
Lenovo uses deep reinforcement learning to assign manufacturing orders to its 43 production lines (and to sequence their production) at its largest laptop manufacturing facility. Their implementation of multicriteria optimization allows schedulers to easily adjust the relative importance of production volume, changeover costs, and order fulfillment rates. A key innovation is a masking mechanism that enforces operational constraints to ensure that the machine-learning model avoids the exploration of infeasible solutions. The transformed process enabled a 20% reduction in the backlog of manufacturing orders and a 23% improvement in the order fulfillment rate. The resulting increase in revenue was about $1.9 billion in 2019 and $2.7 billion in 2020.
Memorial Sloan Kettering Cancer Center for Automated and Clinically Optimal Treatment Planning for Cancer Radiotherapy
Memorial Sloan Kettering Cancer Center developed an expedited constrained hierarchical optimization (ECHO) method to create patient-specific treatment plans to direct radiation beams that sterilize cancerous cells without excessive harm to nearby healthy cells. ECHO combines a preprocessing heuristic algorithm to approximate a nonconvex objective function and constraints, a pair of mixed-integer nonlinear programs solved using the interior point method, and a final solution step using Lagrange multipliers. The method rapidly provides consistent high-quality plans that have benefited over 4,000 patients to date, including those in severe pain and in urgent need of treatment, who were able to avoid surgery to control the progression of their disease.
OCP for Toward Global Food Security: Transforming OCP Through Analytics
Moroccan-based OCP is the world’s largest phosphate mining and processing company. In collaboration with Dynamic Ideas, a Massachusetts-based analytics consulting company, OCP developed a mixed-integer optimization model to optimize its entire sales and supply chain—from mining through processing to the port for global distribution. Many processing choices are available, including those involving trade-offs between product quality and production volume, substitutions (e.g., supplying acid or phosphate rock), the purchase of raw materials through standing contracts or spot markets, and decisions about the quantities to sell via contracts and via spot markets. The model has led to integrated decision making throughout the company, in contrast with the previous process in which decisions were made in organizational silos and based on local objectives. The work has contributed to an increase in earnings of over 20% (before interest, taxes, depreciation, and amortization) annually with a cumulative impact of over $2.3 billion from 2015 through 2020.
Conclusion
The Edelman finalists’ papers make this issue of the journal special for both practitioners and academics. Practitioners can benefit in at least four ways. First, they will find better ways of accomplishing their work using advanced analytics models in a diverse group of organizations in both the private and public sectors. Second, they will find better ways to advocate their ideas to others within their organizations by pointing out the impact of adopting analytics modeling. Third, they will learn how to bring about change in an organization to make OR-based modeling and analysis an integral part of its culture. Finally, they can be inspired to tackle challenging problems and make the modeling choices necessary for their effective solution and deployment.
Academics will find validation of the advanced methodology they teach and will be able to demonstrate what can be achieved with OR/MS and advanced analytics. Furthermore, these examples illustrate how model customization is often required to suit the problem context.
Selection committee members, verifiers, coaches, judges, and those supporting the award ceremony all deserve thanks for the effort they put into making the Franz Edelman Award competition a success—in spite of the disruptive pandemic.
We thank this year’s members of the selection committee: Carrie Beam (chair), Layek Abdel-Malek, Jeffrey Alden, Sudharshana Apte, Sharon Arroyo, Sudip Bhattacharjee, Ann Bixby, Paul Brooks, Aaron Burciaga, Pooja Dewan, Carol DeZwarte, Goutam Dutta, Gul Ege, Michael F. Gorman, Genetha Gray, Shailendra Jain, Burcu B. Keskin, Margarit Khachatryan, Don Kleinmuntz, Russell Labe, Tim Lowe, Polly Mitchell-Guthrie, Sven Müller, Chanel Murray, Ranganath Nuggehalli, Kamran Paynabar, Catherine Petersen, Patti Phillips, Sanjay Prasad, Michael Prokle, Mikael Rönnqvist, Cynthia Rudin, Harrison Schramm, Onur Seref, Zohar Strinka, Kendra Taylor, Rajesh Tyagi, Andrés Weintraub, and Xiaodi Zhu.
We thank the verifiers: Jeffrey Alden, Sudharshana Apte, Sudip Bhattacharjee, Ann Bixby, Aaron Burciaga, Carol DeZwarte, Goutam Dutta, Gul Ege, Shailendra Jain, Burcu B. Keskin, Margarit Khachatryan, Russell Labe, Chanel Murray, Catherine Petersen, Patti Phillips, Michael Prokle, Mikael Rönnqvist, Cynthia Rudin, Harrison Schramm, Zohar Strinka, Kendra Taylor, Rajesh Tyagi, and Xiaodi Zhu.
We thank the coaches: Jeffrey Alden, Aaron Burciaga, Goutam Dutta, Gul Ege, Chanel Murray, Sanjay Prasad, Michael Prokle, Mikael Rönnqvist, Kendra Taylor, Rajesh Tyagi, Andrés Weintraub, and Xiaodi Zhu.
We thank the judging panel: Carrie Beam (chair), Ann Bixby, Michael F. Gorman, Terry Harrison, Shailendra Jain, Tim Lowe, Aly Megahed, Harrison Schramm, and Kermit Threatte.
We thank the Edelman Award Ceremony Organizing Committee: Peter Bell (chair), Jeffrey Alden, Carrie Beam, Robert Dell, Pooja Dewan, Mary Helander, Erica Klampfl, and Russell Labe.
We thank the INFORMS staff members who helped with this year’s Edelman Award Ceremony: Christy Blevins, Ashley Kilgore, Mary Leszczynski, Max Liberatore-Resnick, Mary Magrogan, Olivia Schmitz, and Kara Tucker. We thank Dionne Aleman and Zahir Balaporia, who served as the award’s masters of ceremonies.
We thank the INFORMS staff who helped with many aspects of the process.
A final thanks from one of the authors (Milne), who is completing his 10th and final year as special issue editor of these Edelman finalist papers. I am grateful to the former editor-in-chief (EiC) of the journal, Srinivas Bollapragada, and the current EiC, Michael F. Gorman, for their guidance and allowing me to insist that the world’s best work in applied analytics be explained clearly enough that even I could understand as much of it as would fit within the page limits. Finally, my appreciation for the journal’s manuscript editor, Alice Mack, cannot be overstated. Having edited for the journal since 2006, Alice blends her knowledge of how an analytics success story should be conveyed with her judgment, brilliant editing, and meticulous attention to detail. Her talent and conscientious efforts have greatly improved the quality of these issues.
