A Genetic Algorithm Simheuristic for Solving the Stochastic Project Portfolio Selection Problem with Portfolio Reliability Constraints

In response to the increasing complexity of modern products, dynamic markets, and intensified competition, project-based organizations are actively seeking methodologies to efficiently manage their expanding project portfolios. This paper analyzes the project portfolio selection problem in uncertain environments. Despite recent advances in the field, there is a pressing need for decision-making frameworks that blend optimization and simulation with realistic project information and portfolio constraints. Through an extensive literature review, we identify key variables critical for handling practical scenarios, such as project schedule interdependencies, duration estimations across various scenarios, baseline budget, risk registers, interproject correlations, and cost overrun correlation. To tackle the inherent stochasticity, we introduce a simheuristic algorithm that combines genetic optimization with Monte Carlo simulation. This strategy maximizes the expected value while adhering to project and portfolio constraints under a set portfolio budget reliability level. This approach provides decision-makers with a powerful tool for enhancing project selection processes, promoting upfront planning, improving risk management, and the achievement of strategic goals. The performance of this approach is validated against deterministic methodologies, such as employing a mixed-integer linear programming solver in stochastic environments, demonstrating its effectiveness and practical applicability.