Machine learning predictive model for an intelligent tourism recommendation system

Abstract

Recommendation systems, powered by machine learning, are essential in offering personalized recommendations to consumers based on their preferences in different areas, including literature, educational programs, and lodging. In the field of recommendation systems, there are numerous techniques and strategies. Given that tourism plays a crucial role in driving the economies of regions and countries, there is an increasing desire to enhance the tourist experience by improving the way information is provided. Nevertheless, current research often fails to address the need for comprehensive manuals on activities and attractions while traveling.
This project aims to fill this gap by developing a machine learning predictive model for an intelligent tourist recommendation system. The system is designed to help travelers choose the best routes for their travels. This study uses machine learning algorithms such as Naive Bayes, Decision Trees, and Linear Regression to analyze the “Tourism rating” dataset obtained from Kaggle. The dataset consists of 12 significant features. The results indicate that Linear Regression surpasses other methods, exhibiting greater predictive accuracy and decreased error rates. The importance of this study lies in its ability to offer customized suggestions and a wide range of choices to travelers, thereby improving their travel experiences by directing them towards the most suitable destinations and activities.