Optimizing Inventory Management
The Optimization Edge
A Blog for Business Executives and Advanced Analytics Practitioners
Technologies: Data Science, Big Data, Optimization, Machine Learning, Artificial Intelligence, Predictive Analytics, Forecasting
Applications: Operations, Supply Chain, Finance, Health Care, Workforce, Sales and Marketing
In 2016 I conducted a survey at the INFORMS Analytics conference in Orlando on the organization of analytics groups, and on the potential impact of current trends in the analytics landscape. ORMS Today included the summary of the results and the editor Peter Horner, added the title, “O.R. and Data Science: a Complicated Relationship,” which encapsulates a longstanding challenge that is not going away.
Advanced analytics practitioners and business executives are always striving to understand the nature of the problems facing them, so they can hire and manage talent and develop the best solutions. Seems straightforward enough, but technologies, methodologies and terminologies are evolving.
The same professional can have a job title that includes either Operations Research (O.R.), Analytics, or Data Science. Conversely, these labels at times represent three very different communities.
The Jan de Wit Company, www.jandewit.com.br, is a wholesale producer of bulb flowers in Brazil. In 2000, when the company began to consider optimization to help its production planning, it had 18,745 square meters of greenhouses, 1,032 square meters of cold-storage rooms, a team of approximately 30 employees and US$80 million in annual sales.
Princeton Consultants performs a Quality Assurance service that helps clients understand if best practices are used in the deployment of their predictive analytics or optimization models. Based on years of experience deploying advanced analytics in operational systems that run 24/7, our analysis often uncovers areas for improvement by suggesting new modeling and algorithmic approaches. Practitioner executives gain an understanding of how well their team uses industry best practices. Business sponsors gain more confidence in the solutions provided by their teams of analytics practitioners, and those practitioners improve their skills for future projects.
“For an MBA student, it’s very important to understand how you will encounter a problem in the real world,” says Arnie Greenland, a professor at the University of Maryland’s Robert H. Smith School of Business.
“You have to excel at more than the technical side of optimization to succeed in business—you have to understand the human side and change management,” he says. “Often, the hardest part is getting the client to understand the value of a solution and use the results properly.”
Professor Greenland uses my book, The Optimization Edge: Reinventing Decision Making to Maximize All Your Company’s Assets (McGraw Hill), to present realistic experiences in applied optimization, challenges to implement solutions, and tips to overcome them.
Over a year ago, I discovered a wonderful article by Hadley Wickham introducing the concept of "Tidy Data." Here is a complete reference:
Here is a true story about a visit to a major asset operations planning center. Our host executives had told us about their smart system and how, through optimization, it executed the planning and scheduling. They took us on a tour of the facility and pointed out the team of specialists.
For the INFORMS oral histories initiative that spotlights giants of operations research, I recently had the great pleasure to interview Egon Balas, who has led two lives, both of which are extraordinary success stories. In the first, he came of age in Romania prior to World War II and joined the underground communist movement to resist the growth of Nazism. This led to a “terrible obstacle course,” to use his phrase, consisting of humiliation, torture, and prison. He pursued a career in economics and wrote a book suggesting that some Keynesian ideas could be applied to a Socialist economy. The book branded him as a heretic and caused him to lose his job at a Romanian research institute. By reading on his own, he taught himself linear programming and became adept.
QuadGraphics, www.qg.com, an NYSE company, is the second largest print and integrated media solutions provider in North America. The firm’s leaders have consistently emphasized improving performance through innovation and, as evidence of that commitment, they invited us several years ago to look for optimization opportunities at their organization.
First, they showed us the printing presses, their most valuable asset. When our team looked at the presses, we literally could find nothing to help them with—mainly because all the jobs were designed to fit exactly on those presses, to not waste paper, to be efficient as possible.
However, we were happy to find was there was another area where we could help: the binding lines.
I’ve often heard stories from my operations research colleagues about fantastic results obtained from advanced analytics models they have built, but the models were never used in the business. Typically, the lack of acceptance of their models was due to a lack of understanding of what would be required for successful integration of those models into normal business operations.
What they missed was the need for applying organizational change management principles in order to gain broader acceptance of advanced analytics techniques that are used for decision support. I collaborated with longtime colleagues Zahir Balaporia of Schneider (now at FICO), Karl Kempf of Intel, John Milne of Clarkson University (formerly at IBM), and Rahul Saxena of Cobot Systems (formerly of Cisco)—who have decades of experience in the development and deployment of analytic methods for improved decision making—on a paper about this topic. Following is an adaptation of our paper and the related presentation I have given at INFORMS events.