Today's business environment involves design decisions with significant uncertainty. To succeed, decision-makers should replace deterministic methods with a risk-based approach that accounts for the decision maker‘s risk tolerance. In many problems, it is impractical to collect data because rare or one-time events are involved. Therefore, we need a

Today's business environment involves design decisions with significant uncertainty. To succeed, decision-makers should replace deterministic methods with a risk-based approach that accounts for the decision maker’s risk tolerance. In many problems, it is impractical to collect data because rare or one-time events are involved. Therefore, we need a methodology to model uncertainty and make choices when we have limited information. This methodology must use all available information and rely only on assumptions that are supported by evidence. This book explains theories and tools to represent uncertainty using both data and expert judgment. It teaches the reader how to make design or business decisions when there is limited information with these tools. Readers will learn a structured, risk-based approach, which is based on common sense principles, for design and business decisions. These decisions are consistent with the decision-maker’s risk attitude. The book is exceptionally suited as educational material because it uses everyday language and real-life examples to elucidate concepts. It demonstrates how these concepts touch our lives through many practical examples, questions and exercises. These are designed to help students learn that first they should understand a problem and then establish a strategy for solving it, instead of using trial-and-error approaches. This volume is intended for undergraduate and graduate courses in mechanical, civil, industrial, aerospace, and ocean engineering and for researchers and professionals in these disciplines. It will also benefit managers and students in business administration who want to make good decisions with limited information.

An introduction to decision making under uncertainty from a computational perspective, covering both theory and applications ranging from speech recognition to airborne collision avoidance. Many important problems involve decision making under uncertainty—that is, choosing actions based on often imperfect observations, with unknown outcomes. Designers of automated decision support systems must take into account the various sources of uncertainty while balancing the multiple objectives of the system. This book provides an introduction to the challenges of decision making under uncertainty from a computational perspective. It presents both the theory behind decision making models and algorithms and a collection of example applications that range from speech recognition to aircraft collision avoidance. Focusing on two methods for designing decision agents, planning and reinforcement learning, the book covers probabilistic models, introducing Bayesian networks as a graphical model that captures probabilistic relationships between variables; utility theory as a framework for understanding optimal decision making under uncertainty; Markov decision processes as a method for modeling sequential problems; model uncertainty; state uncertainty; and cooperative decision making involving multiple interacting agents. A series of applications shows how the theoretical concepts can be applied to systems for attribute-based person search, speech applications, collision avoidance, and unmanned aircraft persistent surveillance. Decision Making Under Uncertainty unifies research from different communities using consistent notation, and is accessible to students and researchers across engineering disciplines who have some prior exposure to probability theory and calculus. It can be used as a text for advanced undergraduate and graduate students in fields including computer science, aerospace and electrical engineering, and management science. It will also be a valuable professional reference for researchers in a variety of disciplines.

Uncertainty is a fundamental characteristic of weather, seasonal climate, and hydrological prediction, and no forecast is complete without a description of its uncertainty. Effective communication of uncertainty helps people better understand the likelihood of a particular event and improves their ability to make decisions based on the forecast. Nonetheless, for decades, users of these forecasts have been conditioned to receive incomplete information about uncertainty. They have become used to single-valued (deterministic) forecasts (e.g., "the high temperature will be 70 degrees Farenheit 9 days from now") and applied their own experience in determining how much confidence to place in the forecast. Most forecast products from the public and private sectors, including those from the National Oceanographic and Atmospheric Administration's National Weather Service, continue this deterministic legacy. Fortunately, the National Weather Service and others in the prediction community have recognized the need to view uncertainty as a fundamental part of forecasts. By partnering with other segments of the community to understand user needs, generate relevant and rich informational products, and utilize effective communication vehicles, the National Weather Service can take a leading role in the transition to widespread, effective incorporation of uncertainty information into predictions. "Completing the Forecast" makes recommendations to the National Weather Service and the broader prediction community on how to make this transition.

This open access book focuses on both the theory and practice associated with the tools and approaches for decisionmaking in the face of deep uncertainty. It explores approaches and tools supporting the design of strategic plans under deep uncertainty, and their testing in the real world, including barriers and enablers for their use in practice. The book broadens traditional approaches and tools to include the analysis of actors and networks related to the problem at hand. It also shows how lessons learned in the application process can be used to improve the approaches and tools used in the design process. The book offers guidance in identifying and applying appropriate approaches and tools to design plans, as well as advice on implementing these plans in the real world. For decisionmakers and practitioners, the book includes realistic examples and practical guidelines that should help them understand what decisionmaking under deep uncertainty is and how it may be of assistance to them. Decision Making under Deep Uncertainty: From Theory to Practice is divided into four parts. Part I presents five approaches for designing strategic plans under deep uncertainty: Robust Decision Making, Dynamic Adaptive Planning, Dynamic Adaptive Policy Pathways, Info-Gap Decision Theory, and Engineering Options Analysis. Each approach is worked out in terms of its theoretical foundations, methodological steps to follow when using the approach, latest methodological insights, and challenges for improvement. In Part II, applications of each of these approaches are presented. Based on recent case studies, the practical implications of applying each approach are discussed in depth. Part III focuses on using the approaches and tools in real-world contexts, based on insights from real-world cases. Part IV contains conclusions and a synthesis of the lessons that can be drawn for designing, applying, and implementing strategic plans under deep uncertainty, as well as recommendations for future work. The publication of this book has been funded by the Radboud University, the RAND Corporation, Delft University of Technology, and Deltares.

Publisher Description

Model development decisions are an important feature of engineering design. The quality of simulation models often dictates the quality of design decisions, seeing as models guide decision makers (DM) in choosing design decisions. A quality model accurately represents the modeled system and is helpful for exploring what-if scenarios, optimizing design parameters, estimating design performance, and predicting the effect of design changes. However, obtaining a quality model comes at a cost in terms of model development--in experimentation, labor, model development time, and simulation time. Thus, DMs must make appropriate trade-offs when considering model development decisions. :The primary challenge in model development is making decisions under significant uncertainty. This thesis addresses model development in the conceptual design phase where uncertainty levels are high. In the conceptual design phase, there are many information constraints which may include an incomplete requirements list, unclear design goals, and/or undefined resource constrains. During the embodiment design phase, the overall objective of the design is more clearly defined, and model development decisions can be made with respect to an overall objective function. For example, the objective may be to maximize profit, where the profit is a known function of the model output. In the conceptual design phase, this level of clarity is not always present, so the DM must make decisions under significant model uncertainty and objective uncertainty. In this thesis, conjoint analysis is employed to solicit the preferences of the decision maker for various model attributes, and the preferences are used to formulate a quasi-objective function during the conceptual design phase--where the overall design goals are vague. Epistemic uncertainty (i.e., imprecision) in model attributes is represented as intervals and propagated through the proposed model development framework. :The model development framework is used to evaluate the best course of action (i.e., model development decision) for a real-world packaging design problem. The optimization of medical product packaging is assessed via mass spring damper models which predict contact forces experienced during shipping and handling. Novel testing techniques are employed to gather information from drop tests, and preliminary models are developed based on limited information. Imprecision in preliminary test results are quantified, and multiple model options are considered. Ultimately, this thesis presents a model development framework in which decision makers have systematic guidance for choosing optimal model development decisions.