Application of Genetic Algorithm in Optimizing Path Selection in Tourism Route Planning

Abstract

Tourism route planning plays a pivotal role in shaping travel experiences, requiring efficient path selection strategies that cater to diverse preferences and operational constraints. In this study, we investigate the application of Genetic Algorithms (GAs) for optimizing path selection in tourism route planning, aiming to enhance solution quality, convergence speed, and user satisfaction. We formulate the tourism route planning problem as a multi-objective optimization task, considering objectives such as minimizing travel distance and maximizing tourist satisfaction while adhering to constraints such as time limitations and attraction accessibility. The GA iteratively evolves a population of candidate routes, employing genetic operators such as crossover and mutation to explore solution spaces and converge to near-optimal solutions. We present comprehensive statistical results demonstrating the superiority of GA-optimized routes over baseline algorithms and manual planning methods in terms of solution quality, convergence speed, and computational efficiency. Additionally, user feedback analysis highlights the practical relevance and user acceptance of GA-optimized routes, indicating high satisfaction with the proposed approach. Despite its promising results, we acknowledge certain limitations, including the simplification of the route planning problem and computational complexity of GAs, necessitating further research into hybrid optimization approaches and interdisciplinary collaborations. Overall, our study contributes to advancing the state-of-the-art in tourism route optimization, offering valuable insights for stakeholders in the tourism industry seeking to enhance travel experiences and destination competitiveness.