بهینه سازی پروژه "تحقیق و توسعه" اوراق بهادار تحت عدم قطعیت درون زا

Project portfolio management deals with the dynamic selection of research and development (R&D) projects and determination of resource allocations to these projects over a planning period. Given the uncertainties and resource limitations over the planning period, the objective is to maximize the expected total discounted return or the expectation of some other function for all projects over a long time horizon. We develop a detailed formal description of this problem and the corresponding decision process, and then model it as a multistage stochastic integer program with endogenous uncertainty. Accounting for this endogeneity, we propose an efficient solution approach for the resulting model, which involves the development of a formulation technique that is amenable to scenario decomposition. The proposed solution algorithm also includes an application of the sample average approximation method, where the sample problems are solved through Lagrangian relaxation and a new lower bounding heuristic. The performance of the overall solution procedure is demonstrated using several implementations of the proposed approach.

Project portfolio management, as defined in this paper, refers to selecting and allocating resources to research and development (R&D) projects to design, test and improve a technology, or the process of building a technology. Project portfolio management is an essential part of the operational planning process for most private and public organizations. Such organizations typically have several potential R&D projects with different performance characteristics that they can choose to invest in using available resources. The primary characteristics of technology projects, which include parameters such as the required resource levels, i.e. the total expenditure necessary to create returns, as well as the projected returns themselves, are typically unknown at the time of investment. However, some information, in particular on the uncertainty in the estimates of these characteristics, is mostly available. Given these uncertainties and resource limitations over a planning horizon, the project portfolio management problem becomes one of selecting R&D projects and determining optimal resource allocations for the current planning period such that the expected total discounted return or the expectation of some other function over a long time horizon is maximized.

We have presented a detailed and comprehensive description of the project portfolio optimization problem at a level not considered in any of the existing approaches. The corresponding decision making process was then modeled as a multistage stochastic programming problem with endogenous uncertainty in the stochastic parameters. An efficient formulation technique that enabled direct scenario decomposition for these types of problems was introduced and implemented using a tight lower bounding heuristic, which is also applicable to any other similarly structured problem. A two-stage approximation of the general model was also described, and the performance of the overall solution procedure was demonstrated using several implementations of the proposed approach.