Refine
Has Fulltext
- yes (3)
Is part of the Bibliography
- yes (3)
Document Type
- Doctoral Thesis (3)
Language
- English (3)
Keywords
- Maschinelles Lernen (3) (remove)
Institute
EU-Project number / Contract (GA) number
This dissertation consists of three independent, self-contained research papers that investigate how state-of-the-art machine learning algorithms can be used in combination with operations management models to consider high dimensional data for improved planning decisions. More specifically, the thesis focuses on the question concerning how the underlying decision support models change structurally and how those changes affect the resulting decision quality.
Over the past years, the volume of globally stored data has experienced tremendous growth. Rising market penetration of sensor-equipped production machinery, advanced ways to track user behavior, and the ongoing use of social media lead to large amounts of data on production processes, user behavior, and interactions, as well as condition information about technical gear, all of which can provide valuable information to companies in planning their operations. In the past, two generic concepts have emerged to accomplish this. The first concept, separated estimation and optimization (SEO), uses data to forecast the central inputs (i.e., the demand) of a decision support model. The forecast and a distribution of forecast errors are then used in a subsequent stochastic optimization model to determine optimal decisions. In contrast to this sequential approach, the second generic concept, joint estimation-optimization (JEO), combines the forecasting and optimization step into a single optimization problem. Following this approach, powerful machine learning techniques are employed to approximate highly complex functional relationships and hence relate feature data directly to optimal decisions.
The first article, “Machine learning for inventory management: Analyzing two concepts to get from data to decisions”, chapter 2, examines performance differences between implementations of these concepts in a single-period Newsvendor setting. The paper first proposes a novel JEO implementation based on the random forest algorithm to learn optimal decision rules directly from a data set that contains historical sales and auxiliary data. Going forward, we analyze structural properties that lead to these performance differences. Our results show that the JEO implementation achieves significant cost improvements over the SEO approach. These differences are strongly driven by the decision problem’s cost structure and the amount and structure of the remaining forecast uncertainty.
The second article, “Prescriptive call center staffing”, chapter 3, applies the logic of integrating data analysis and optimization to a more complex problem class, an employee staffing problem in a call center. We introduce a novel approach to applying the JEO concept that augments historical call volume data with features like the day of the week, the beginning of the month, and national holiday periods. We employ a regression tree to learn the ex-post optimal staffing levels based on similarity structures in the data and then generalize these insights to determine future staffing levels. This approach, relying on only few modeling assumptions, significantly outperforms a state-of-the-art benchmark that uses considerably more model structure and assumptions.
The third article, “Data-driven sales force scheduling”, chapter 4, is motivated by the problem of how a company should allocate limited sales resources. We propose a novel approach based on the SEO concept that involves a machine learning model to predict the probability of winning a specific project. We develop a methodology that uses this prediction model to estimate the “uplift”, that is, the incremental value of an additional visit to a particular customer location. To account for the remaining uncertainty at the subsequent optimization stage, we adapt the decision support model in such a way that it can control for the level of trust in the predicted uplifts. This novel policy dominates both a benchmark that relies completely on the uplift information and a robust benchmark that optimizes the sum of potential profits while neglecting any uplift information.
The results of this thesis show that decision support models in operations management can be transformed fundamentally by considering additional data and benefit through better decision quality respectively lower mismatch costs. The way how machine learning algorithms can be integrated into these decision support models depends on the complexity and the context of the underlying decision problem. In summary, this dissertation provides an analysis based on three different, specific application scenarios that serve as a foundation for further analyses of employing machine learning for decision support in operations management.
Autonomous cars and artificial intelligence that beats humans in Jeopardy or Go are glamorous examples of the so-called Second Machine Age that involves the automation of cognitive tasks [Brynjolfsson and McAfee, 2014]. However, the larger impact in terms of increasing the efficiency of industry and the productivity of society might come from computers that improve or take over business decisions by using large amounts of available data. This impact may even exceed that of the First Machine Age, the industrial revolution that started with James Watt’s invention of an efficient steam engine in the late eighteenth century. Indeed, the prevalent phrase that calls data “the new oil” indicates the growing awareness of data’s importance. However, many companies, especially those in the manufacturing and traditional service industries, still struggle to increase productivity using the vast amounts of
data [for Economic Co-operation and Development, 2018].
One reason for this struggle is that companies stick with a traditional way of using data for decision support in operations management that is not well suited to automated decision-making. In traditional inventory and capacity management, some data – typically just historical demand data – is used to estimate a model that makes predictions about uncertain planning parameters, such as customer demand. The planner then has two tasks: to adjust the prediction with respect to additional information that was not part of the data but still might influence demand and to take the remaining uncertainty into account and determine a safety buffer based on the underage and overage costs. In the best case, the planner determines the safety buffer based on an optimization model that takes the costs and the distribution of historical forecast errors into account; however, these decisions are usually based on a planner’s experience and intuition, rather than on solid data analysis.
This two-step approach is referred to as separated estimation and optimization (SEO). With SEO, using more data and better models for making the predictions would improve only the first step, which would still improve decisions but would not automize (and, hence, revolutionize) decision-making. Using SEO is like using a stronger horse to pull the plow: one still has to walk behind.
The real potential for increasing productivity lies in moving from predictive to prescriptive approaches, that is, from the two-step SEO approach, which uses predictive models in the estimation step, to a prescriptive approach, which integrates the optimization problem with the estimation of a model that then provides a direct functional relationship between the data and the decision. Following Akcay et al. [2011], we refer to this integrated approach as joint estimation-optimization (JEO). JEO approaches prescribe decisions, so they can automate the decision-making process. Just as the steam engine replaced manual work, JEO approaches replace cognitive work.
The overarching objective of this dissertation is to analyze, develop, and evaluate new ways for how data can be used in making planning decisions in operations management to unlock the potential for increasing productivity. In doing so, the thesis comprises five self-contained research articles that forge the bridge from predictive to prescriptive approaches. While the first article focuses on how sensitive data like condition data from machinery can be used to make predictions of spare-parts demand, the remaining articles introduce, analyze, and discuss prescriptive approaches to inventory and capacity management.
All five articles consider approach that use machine learning and data in innovative ways to improve current approaches to solving inventory or capacity management problems. The articles show that, by moving from predictive to prescriptive approaches, we can improve data-driven operations management in two ways: by making decisions more accurate and by automating decision-making. Thus, this dissertation provides examples of how digitization and the Second Machine Age can change decision-making in companies to increase efficiency and productivity.
Digitization and artificial intelligence are radically changing virtually all areas across business and society. These developments are mainly driven by the technology of machine learning (ML), which is enabled by the coming together of large amounts of training data, statistical learning theory, and sufficient computational power. This technology forms the basis for the development of new approaches to solve classical planning problems of Operations Research (OR): prescriptive analytics approaches integrate ML prediction and OR optimization into a single prescription step, so they learn from historical observations of demand and a set of features (co-variates) and provide a model that directly prescribes future decisions. These novel approaches provide enormous potential to improve planning decisions, as first case reports showed, and, consequently, constitute a new field of research in Operations Management (OM).
First works in this new field of research have studied approaches to solving comparatively simple planning problems in the area of inventory management. However, common OM planning problems often have a more complex structure, and many of these complex planning problems are within the domain of capacity planning. Therefore, this dissertation focuses on developing new prescriptive analytics approaches for complex capacity management problems. This dissertation consists of three independent articles that develop new prescriptive approaches and use these to solve realistic capacity planning problems.
The first article, “Prescriptive Analytics for Flexible Capacity Management”, develops two prescriptive analytics approaches, weighted sample average approximation (wSAA) and kernelized empirical risk minimization (kERM), to solve a complex two-stage capacity planning problem that has been studied extensively in the literature: a logistics service provider sorts daily incoming mail items on three service lines that must be staffed on a weekly basis. This article is the first to develop a kERM approach to solve a complex two-stage stochastic capacity planning problem with matrix-valued observations of demand and vector-valued decisions. The article develops out-of-sample performance guarantees for kERM and various kernels, and shows the universal approximation property when using a universal kernel. The results of the numerical study suggest that prescriptive analytics approaches may lead to significant improvements in performance compared to traditional two-step approaches or SAA and that their performance is more robust to variations in the exogenous cost parameters.
The second article, “Prescriptive Analytics for a Multi-Shift Staffing Problem”, uses prescriptive analytics approaches to solve the (queuing-type) multi-shift staffing problem (MSSP) of an aviation maintenance provider that receives customer requests of uncertain number and at uncertain arrival times throughout each day and plans staff capacity for two shifts. This planning problem is particularly complex because the order inflow and processing are modelled as a queuing system, and the demand in each day is non-stationary. The article addresses this complexity by deriving an approximation of the MSSP that enables the planning problem to be solved using wSAA, kERM, and a novel Optimization Prediction approach. A numerical evaluation shows that wSAA leads to the best performance in this particular case. The solution method developed in this article builds a foundation for solving queuing-type planning problems using prescriptive analytics approaches, so it bridges the “worlds” of queuing theory and prescriptive analytics.
The third article, “Explainable Subgradient Tree Boosting for Prescriptive Analytics in Operations Management” proposes a novel prescriptive analytics approach to solve the two capacity planning problems studied in the first and second articles that allows decision-makers to derive explanations for prescribed decisions: Subgradient Tree Boosting (STB). STB combines the machine learning method Gradient Boosting with SAA and relies on subgradients because the cost function of OR planning problems often cannot be differentiated. A comprehensive numerical analysis suggests that STB can lead to a prescription performance that is comparable to that of wSAA and kERM. The explainability of STB prescriptions is demonstrated by breaking exemplary decisions down into the impacts of individual features. The novel STB approach is an attractive choice not only because of its prescription performance, but also because of the explainability that helps decision-makers understand the causality behind the prescriptions.
The results presented in these three articles demonstrate that using prescriptive analytics approaches, such as wSAA, kERM, and STB, to solve complex planning problems can lead to significantly better decisions compared to traditional approaches that neglect feature data or rely on a parametric distribution estimation.