🤖 AI Summary
For the Capacitated Vehicle Routing Problem (CVRP), this paper proposes a feature-guided enhanced metaheuristic designed to jointly improve solution quality and population diversity while mitigating premature convergence. Methodologically, it introduces, for the first time, interpretable machine learning—specifically XGBoost augmented with SHAP values—to dynamically guide variable neighborhood search and a novel hybrid split-path-reconnection operator. A new operator is devised that balances local intensification with global structural exploration, integrated with an adaptive diversity preservation mechanism. Experimental evaluation on standard CVRP benchmark instances demonstrates that the algorithm achieves state-of-the-art performance: it attains new best-known solutions on multiple instances, and improvements are statistically significant.
📝 Abstract
We propose a metaheuristic algorithm enhanced with feature-based guidance that is designed to solve the Capacitated Vehicle Routing Problem (CVRP). To formulate the proposed guidance, we developed and explained a supervised Machine Learning (ML) model, that is used to formulate the guidance and control the diversity of the solution during the optimization process. We propose a metaheuristic algorithm combining neighborhood search and a novel mechanism of hybrid split and path relinking to implement the proposed guidance. The proposed guidance has proven to give a statistically significant improvement to the proposed metaheuristic algorithm when solving CVRP. Moreover, the proposed guided metaheuristic is also capable of producing competitive solutions among state-of-the-art metaheuristic algorithms.