A Framework for Selecting Action Portfolios with Incomplete and Action-Dependent Scenario Probabilities

Companies pursue their goals by selecting and implementing a combination or portfolio of actions that consume resources. The extent to which these actions help attain the companies’ objectives is often contingent on whether a given future scenario is realized. In this paper, we present a model-based framework for supporting the selection of a portfolio of actions that is robust across different scenarios while accounting for the impacts that the actions may have on the probabilities of these scenarios. For the purposes of this framework, we develop a new portfolio decision analytic model and algorithms to help generate recommendations for selecting actions, when (i) the actions’ scenario- and objective-specific impacts, as well as preferences between the objectives are incompletely specified, and (ii) information regarding scenario probabilities is incomplete and may depend on the selected actions. Finally, we provide a comprehensive report on the application of the framework in a high-impact case on supporting the strategy process at the payments unit of Nordea Bank Abp, the largest retail bank in the Nordic countries. Based on retrospective interviews with the participants in this strategy process, three kinds of impacts from the use of our framework could be identified: (i) actions related to implementing the decision recommendations and strengthening the required capabilities, (ii) information to help evaluate these decision recommendations as the future unfolded, and (iii) behavioral changes in terms of elevating the level of strategic discussions. This paper was accepted by Jack Soll, behavioral economics and decision analysis. Funding: This work was supported by Liikesivistysrahasto [Grant 16-9442]. Supplemental Material: The data files are available at https://doi.org/10.1287/mnsc.2024.05383 .