Prescriptive Analytics for Data-driven Capacity Management

Motivated by the real-world problem of a logistics company, this paper proposes a novel distribution-free prescriptive analytics approach—termed kernelized empirical risk minimization (kernelized ERM)—to solve a complex two-stage capacity planning problem with multivariate demand and vector-valued capacity decisions and compares this approach both theoretically and numerically with an extension of the well-known sample average approximation (SAA) approach termed weighted SAA. Both approaches use integrated machine learning algorithms to prescribe capacities directly from historical demand and numerous features (covariates) without having to make assumptions about the underlying multivariate demand distribution. We provide extensive analytical insights into both approaches. Most important, we prove the universal approximation property for the kernelized ERM approach when using a universal (data-independent) kernel and show how out-of-sample guarantees can be derived for various kernels. We demonstrate the applicability of both approaches to a real-world planning problem and evaluate their performance relative to traditional parametric approaches that first estimate a multivariate demand distribution and then solve a stochastic optimization problem and a nonparametric approach (SAA). Our results suggest that the two prescriptive analytics approaches can result in substantial performance improvements of up to 58% compared with traditional approaches. Additional numerical analyses shed light on the behavior and performance drivers of the various approaches and demonstrate that in our case, the prescriptive approaches are much more robust to variations of exogenous cost parameters than traditional approaches. This paper was accepted by J. George Shanthikumar, Management Science Special Section on Data-Driven Prescriptive Analytics.

Operations management research: an update for the 1990s

Contributors

Contributors

The operations management research agenda: An update

PurposeThus far, no study collects evidence from practitioners directly to investigate the characteristics of operations management (OM) research that appears to have impacts on OM practice, nor do we know how practitioners evaluate the managerial relevance of OM research. This paper aims to answer two interesting and important questions: how do practitioners judge the managerial relevance of OM research; and whether practitioners' criteria on managerial relevance can help OM researchers improve the relevance?Design/methodology/approachA panel of senior executives was asked to read the top 10 most downloaded papers from theJournal of Operations Managementand fill the designed questionnaire. Following Cronbach's cumulative theory‐building process through which progress is made by successively testing the efficacy of the measures, this research examined the diverse disciplines, consolidated relevant findings, and integrated them into a tractable, meaningful research framework.FindingsThis paper reveals that practitioners evaluate our OM research by three criteria: whether academic research is applicable or implementable (solution oriented), whether academic research provides novel insights or new perspectives to management (eye opening), and whether academic research helps practitioners recognize their situations (accessibility).Originality/valueWhile the awareness of managerial relevance in OM research has been growing, few systematic, quantitative‐oriented empirical studies of practitioners' attitude toward academic OM research exist in current literature. This paper directly explores practitioners' opinions on managerial relevance through quantitative analysis and identified several possible dimensions to pursue managerial relevance in OM research.

International operations management and operations management research: a comparative analysis

Design decisions for integrating Prescriptive Analytics Use Cases into Smart Factories

A couple of years ago, one of us was a co-author on a paper presenting the results of a nice little operations management (OM) research study. Although narrowly focused, it came to some important conclusions and insights regarding an important concept in our field, but we were at a loss about where to try to publish it. It wasn’t a massive study with multiple confounded variables that had to be teased out using sophisticated statistical techniques, nor did it present impressive, earth-shaking conclusions, so it seemed obvious that it wasn’t suitable for the top journals in our field. Nor, some editors informed us, was it appropriate for the engineering or math or management oriented, journals where OM researchers sometimes publish their work. It seemed we had run out of alternatives. Whereas the field of Finance has 46 or more journals that have the words Finance or Financial in their title, and somewhat the same is probably true for Marketing, Economics, and Management, in OM, there are only about five journals with the words Operations Management somewhere in their title. It thus seemed clear that there was a tremendous need, and opportunity, for additional journals in our field. Moreover, since the demise of the Production & Inventory Management Journal published by APICS (formerly, the American Production and Inventory Control Society) and the Notes section of the Journal of Operations Management, there has been no place for academic scholars to read about and publish small but high-quality OM research studies. Between just these two publications themselves, that means about 70 short OM research papers are not being published each year, or are perhaps being published but in less preferred or less appropriate journals. And since that time, the field has grown in both size and stature, while the pressure for publishing continues to increase. As a result, we decided to take matters into our own hands and initiate an OM journal dedicated to smaller, focused papers that held particular promise of advancing practice, since OM is basically an applied field. The journal would not compete with existing A-level journals in the field but would instead aspire to publish shorter, more sharply focused work that exhibited solid methodological rigor. The journal would entertain all OM topics and all forms of research: survey, math modeling, case, field, qualitative, simulation, ethnography, hermeneutics, metaanalyses, and other such reputable methodologies. However, total manuscript length would be limited to 20 pages (including figures and tables) and the turnaround time would be fast, with a target maximum of 8 weeks. We Oper Manag Res (2008) 1:1–5 DOI 10.1007/s12063-008-0009-8

Improving Patient Flow in Emergency Departments with OR Techniques: A Literature Overview

This article surveys a new generation of analytical tools for capacity planning and management, especially in high-tech industries such as semiconductors, electronics and bio-techs. The objectives of the article are to (1) identify fundamental theory driving current research in capacity management, (2) review emerging models in operations research, game theory, and economics that address strategic, tactical and operational decision models for high-tech capacity management, and (3) take an in-depth look at capacity-optimization models developed in the specific context of semiconductor manufacturing. The goal of this survey is to go beyond typical production-planning and capacity-management literature and to examine research that can potentially broaden capacity-planning research. For instance, we explore the role of option theory and real options in modeling capacity decisions. We not only examine capacity-planning problems from the perspective of a particular firm, but also the interaction of capacity investment among supply chain partners. Not only are these issues increasingly important in the fast-changing high-tech environment, they draw on new tools from different disciplines and pose significant intellectual challenges. We also examine papers that represent the multifaceted nature of high-tech capacity planning, integrating capacity decisions with issues related to contracting, coordination, sourcing, and capacity configurations.

Operations Management Research was started to promote research that advances both the theory and practice of operations management (Meredith and McMullen 2008). In this guest editorial, we discuss how operations management (OM) researchers could more systematically engage in the exploration of technological opportunity. In this respect, operations management research is an activity shaped by technological invention and innovation in use. Whereas OM researchers currently are still mainly interested in the performance of OM processes and practices adopted by large populations (e.g. of firms or customers), they should also attend to early adopters trying out new technology as well as those combining and configuring existing technologies in new ways. Expanding attention from studying how established practice transforms operational contexts in terms of efficiency and reliability to the development of innovative practice requires an integrative methodological approach for OM research. We outline such an integrative approach, based on a science-for-design approach. To systematically link practice and science, five methodological steps for the systematic formulation of research agendas and the development and testing of design principles are proposed. As such, we provide a framework that effectively connects practice and the scientific knowledge base in developing field-tested and grounded OM knowledge.

Demand response (DR) is a cost-effective and environmentally friendly approach for mitigating the uncertainties in renewable energy integration by taking advantage of the flexibility of customers' demands. However, existing DR programs suffer from either low participation due to strict commitment requirements or not being reliable in voluntary programs. In addition, the capacity planning for energy storage/reserves is traditionally done separately from the demand response program design, which incurs inefficiencies. Moreover, customers often face high uncertainties in their costs in providing demand response, which is not well studied in literature. This paper first models the problem of joint capacity planning and demand response program design by a stochastic optimization problem, which incorporates the uncertainties from renewable energy generation, customer power demands, as well as the customers' costs in providing DR. We propose online DR control policies based on the optimal structures of the offline solution. A distributed algorithm is then developed for implementing the control policies without efficiency loss. We further offer enhanced policy design by allowing flexibilities into the commitment level. We perform real world trace based numerical simulations. Results demonstrate that the proposed algorithms can achieve near optimal social costs, and significant social cost savings compared to baseline methods.

International audience

A queueing Network approach for capacity planning and patient Scheduling: A case study for the COVID-19 vaccination process in Colombia