A multi-objective optimization approach for sustainable and personalized trip planning: A self-adaptive evolutionary algorithm with case study

In the modern tourism landscape, the fusion of sustainability and personalized travel plans marks a significant paradigm shift. This paper presents a novel multi-objective optimization approach for crafting sustainable and personalized tourist trip plans. The proposed model is designed to provide tailored recommendations to tourists, simultaneously minimizing total costs, environmental impacts, and maximizing individual preferences. These recommendations encompass choices such as hotel and resting place selection, daily sequence of attractions, precise visit schedules, and preferred modes of transportation. Addressing intricacies within an urban multimodal transport system, including factors like traffic lights, weather conditions, and distinct features of each transport mode, the model ensures that tourists can explore scenic spots within their available time windows. To tackle uncertainties in travel time, travel costs, and visit durations, a practical fuzzy optimization approach is employed. For efficient resolution of the multi-objective optimization model, a self-adaptive evolutionary algorithm based on Non-Dominated Sorting Genetic Algorithm II (SA-NSGAII) is developed. The effectiveness of the proposed solution method is verified through comparisons with Augmented epsilon-Constraint (AUGMECON) and NSGA-II methods, utilizing various benchmark examples. Employing real data from Montreal, an empirical case study is conducted to illustrate the application of the sustainable and personalized trip planning model. The analysis of the solution results demonstrates how this approach can assist tourists in achieving a harmonious balance between sustainability objectives and making well-informed decisions based on their individual preferences.