Enterprise Project Risk Management and Optimization: Integrating Genetic Algorithms with Monte Carlo Simulation

This paper presents an innovative approach to enterprise project risk management and optimization that combines genetic algorithms with Monte Carlo simulation to address the complexity and uncertainty inherent in large construction projects. As the technical complexity and scope of projects continue to grow, traditional risk management methods are no longer adequate and more dynamic and adaptive solutions are needed. Our proposed model transitions from deterministic discrete optimization to stochastic discrete optimization by incorporating probabilistic constraints on project durations and costs and modeling them as random variables that follow a Beta distribution. This dual approach not only ensures high accuracy and stability of the solution but also improves computational efficiency by 14 times by dynamically allocating computational resources based on proximity to constraint thresholds. The Weka API simplifies data processing and model training, further improving the efficiency of the system. To validate the effectiveness of our proposed approach, we compared it against several benchmark models commonly used in project risk management, including the Critical Path Method (CPM), Linear Programming (LP) techniques, and Nonlinear Cost-Time Tradeoff Models.