An invitation to portfolio decision analysis

Portfolio Decision Analysis (PDA) – the application of decision analysis to the problem of selecting a subset or portfolio from a large set of alternatives – accounts for a significant share, perhaps the greater part, of decision analysis consulting. By construction, PDA has a sound theoretical and methodological basis, and its ability to contribute to better resource allocations decisions has been demonstrated in numerous applications. This book pulls together some of the rich and diverse efforts as a starting point for treating PDA as a promising and distinct area of study and application. In this introductory chapter, we first describe what we mean by Portfolio Decision Analysis. We then sketch the historical development of some key ideas, outline the contributions contained in the chapters and, finally, offer personal perspectives on future work in this sub-field of decision analysis that merits growing attention. 1.1 What is Portfolio Decision Analysis? Practically all organizations and individuals have goals that they seek to attain by allocating resources to actions that consume resources. Industrial firms, for example, undertake research and development projects (R&D), expecting that these projects allow them to introduce new products that generate growing profits. Municipalities allocate public funds to initiatives that deliver social and educational services to their citizens. Regulatory bodies attempt to mitigate harmful consequences of human activity by imposing alternative policy measures which contribute to objectives such as safety and sustainability. Even many individual decisions can be viewed analogously. For instance, university students need to consider what academic courses and recreational pursuits to engage in, recognizing that time is a limited resource when aspiring to complete one’s studies successfully and on schedule while having a rewarding social life. Decision problems such as these are seemingly different. Yet from a methodological point of view, they share so many similarities that it is instructive to consider them together. Indeed, all the above examples involve one or several decision makers who are faced with alternative courses of action which, if implemented, consume resources and enable consequences. The availability of resources is typically limited by constraints while the desirability of consequences depends on preferences concerning the attainment of multiple objectives. Furthermore, the decision may affect several stakeholders who are impacted by the decision even if they are not responsible it. There can be uncertainties as well: for instance, at the time of decision making, it may be impossible to determine what consequences the actions will lead to or how much resources they will consume. These, in short, are the key concepts that characterize decision contexts where the aim is to select a subset consisting of several actions with the aim of contributing to the realization of consequences that are aligned with the decision maker’s preferences. They are also key parts of the following definition of Portfolio Decision Analysis: By Portfolio Decision Analysis (PDA) we mean a body of theory, methods, and practice which seeks to help decision makers make informed multiple selections from a discrete set of alternatives through mathematical modeling that accounts for relevant constraints, preferences, and uncertainties. A few introductory observations about this definition are in order. To begin with, theory can be viewed as the foundation of PDA in that as it postulates axioms that characterize rational decision making and enable the development of functional representations for modeling such decisions. Methods build on theory by providing practicable approaches that are compatible with these axioms and help implement decision processes that seek to contribute to improved decision quality (see Keisler, Chapter 2). Practice consists of applications where these methods are deployed to address real decision problems that involve decision makers and possibly even other stakeholders (see, e.g., Salo and Hämäläinen, 2010). Thus, applications build on decision models that capture the salient problem characteristics, integrate relevant factual and subjective information, and synthesize this information into recommendations about what subset of alternatives (or portfolio)