FOX-TSA hybrid algorithm: Advancing for superior predictive accuracy in tourism-driven multi-layer perceptron models

Nature-inspired optimization models have received a great deal of interest due to the performance of these algorithms in solving resourceful and authentic problems. However, achieving high predictive accuracy in machine learning models for specialized domains, such as the tourism industry, remains challenging. Predictive modelling in tourism is vital for improving decision-making, including forecasting visitor behaviours and enhancing customer experiences. As the volume and complexity of tourism data increase, there is a need for optimization methods that enhance model training while effectively handling intricate datasets. This study proposes a hybrid FOX-TSA algorithm to optimize the MLP model. The hybrid algorithm synergises the Fox Optimization Algorithm's exploration capabilities with the Tree-Seed Algorithm's exploitation strengths. Using a tourism dataset with user preferences and ratings, the performance of the anticipated algorithm is compared with standalone FOX, TSA, PSO, and GWO algorithms. Results indicate that the hybrid FOX-TSA achieves superior predictive accuracy (94.64%), faster convergence speed (reducing iterations by 25%), and improved F1-score (94.63%) on the test dataset. These findings underline the potential of the hybrid FOX-TSA algorithm to advance predictive modelling in the tourism sector and other domains requiring complex data handling.