Introduction to the ITED Special Section Cases Based on Real-World Projects from the INFORMS Journal on Applied Analytics

We could not be more excited to be writing this introduction to the INFORMS Transactions on Education (ITED) special section on Cases Based on Real-World Projects from the INFORMS Journal on Applied Analytics (IJAA)! There are a few reasons. First, as former Editors in Chief (EiCs) of IJAA and ITED, it is a pleasure seeing the real-world projects that have appeared in IJAA brought to the classroom.

When we were both EiCs, we saw an opportunity to combine the missions of our respective journals in a special section. IJAA, formerly known as Interfaces, prides itself on publishing applied work in analytics that has had success in practice. ITED prides itself on finding novel ways to teach analytics. These cases cover both spectrums, bringing real-world, unpublished applications into the classroom in a digestible case study format for the classroom, truly bridging the gap between academia and practice.

There are many cases in ITED that are based on real-world applications, but in this case, the students may reference in IJAA the actual implementation either while or after working on the case to solidify their knowledge and demonstrate the powerful nature of the techniques they are learning.

“Teaching integer programming by scheduling the Belgian soccer league” by Goossens and Beliën (2023) is based on Goossens and Spieksma (2009). It describes two approaches for teaching integer programming starting from a real-life case on scheduling the Belgian soccer league: hands-on exercises and an interactive lecture that focuses more on current research challenges.

“Bayer new drug development decision making” by Stonebraker (2023) is based on Stonebraker (2002). It uses a structured decision analysis process in deciding whether to develop a new drug to treat blood clots in legs. After a role-playing exercise in which the instructor acts as the subject matter expert and decision maker, the students, acting as consultants, build a decision tree and probabilistic assessment of whether to take the drug to market. The case builds both analytical skills and consulting skills for the student.

The three cases by Michael Gorman in this section all feature work published in IJAA that utilizes multiple analytical techniques: predictive statistics, optimization, simulation, and stochastic optimization. In each case, the instructor can pick and choose the portions of the case to cover. Despite the breadth of the areas of coverage, all of the cases find an opportunity to combine these methods in a useful way, developing deeper understanding of the problem and the possible solutions. The full case is covered in three to five segments, envisioned by the author as weeks. In each case, an emphasis is given to the quality of the communication of solutions that are described as well as the quality of the solutions.

The papers cover a variety of fields of application and are described.

For railways, the work on Louisiana branch lines by Gorman (2023) is based on Gorman (2001). This case estimates demand curves, conducts nonlinear optimization on prices based on those estimates, evaluates profit risk of those optimal prices given demand uncertainty, and finally, conducts a stochastic optimization, reoptimizing profits under various demand conditions.

For print manufacturing, the work on blending statistics, optimization, and simulation in a multiphase case (named Junko’s Print Shop) by Gorman (2023) is based on Ahire et al. (2007). This case estimates press operating costs and times for various job sizes, minimizes job assignment costs for a set of jobs in a mixed integer program, and finally, evaluates cost and feasibility risks given operating characteristic uncertainty.

For inventory management, the work on the Swirltubs after-market part inventory and repair service case by Gorman (2023) is based on Gorman and Ahire (2006). This case estimates part need based on probabilistic demand, uses a heuristic (in place of a binary integer problem, which is also an option) to make part stocking decisions, estimates service risk based on the optimal stocking plan, and conducts stochastic optimization to evaluate how much the stocking plan varies under different part demand scenarios.

We are pleased with the outcome and hope the reader will find usefulness and value in these cases.