Research on Optimization Decision-Making Model Based on Genetic Algorithm

In the face of challenges posed by resource constraints and environmental changes, optimizing decision-making models has become crucial for enhancing system efficiency and resilience. This paper develops a multi-objective optimization model that integrates dynamic variables and multidimensional constraints to improve the efficiency of solving for global optima. By employing mixed-integer linear programming, genetic algorithms, and simulated annealing, we propose a profit-risk balance model under multi-variable correlations. Sensitivity analysis shows that the model is highly sensitive to key variables such as price, yield, and cost. Results indicate that dynamic adjustments and multi-strategy combinations provide significant optimization in complex environments, offering scientific algorithmic support for intertemporal resource allocation.