RARE: right algorithm for the right errand; a multi-model machine learning-based approach for tourism routes and...

Area of Science:

• Computer Science
• Artificial Intelligence
• Tourism Informatics

Background:

• Tourism is a major economic driver, increasing the need for efficient travel planning.
• Personalized recommendations are in high demand, but traditional methods are insufficient.
• Dynamic, AI-driven solutions are needed to adapt to the evolving tourism landscape.

Purpose of the Study:

• To develop a novel tourism recommendation system using multiple machine learning algorithms.
• To provide personalized tourist spot and route recommendations dynamically.
• To enhance the efficiency and user experience of travel planning.

Main Methods:

• A 2D grid model represents the tourist map with interconnected nodes.
• Long Short-Term Memory (LSTM) predicts spot relevance.
• Support Vector Machine (SVM) classifies spot names.
• Depth First Search (DFS) generates optimal routes.
• K-means clustering assigns cluster leaders (CLs) for zone management.

Main Results:

• The system provides optimized travel routes based on simple textual queries.
• Experimental evaluation on an augmented travel dataset demonstrates effectiveness.
• The model successfully enhances tourism planning and user satisfaction.

Conclusions:

• The proposed machine learning framework offers a dynamic and adaptive solution for tourism recommendations.
• This approach has the potential to significantly advance intelligent tourism systems.
• Personalized, optimized routes improve the overall tourist experience.