A Machine Learning Predictive Model for an Intelligent Tourism Recommendation System

Recommendation systems are very important, and machine learning plays a bigger role in helping recommendation systems give users the best suggestions based on their interests. A recommendation system can be used for many things, like books, training courses, and hotels. There are a lot of different kinds of recommendation systems. Tourism is a major source of income for countries and areas. Many studies have been done on how to make tourist information more useful for tourists. There aren't enough studies on the list of things to do when people go on a trip. So, this study focuses on building a machine learning predictive model for an intelligent tourism recommendation system that can help tourists choose the best route for their trip. Naive Bayes, Decision Trees, and Linear Regression are machine learning algorithms that were adopted for this study. The "Tourism rating" dataset from Kaggle, containing 12 features, was used. The findings indicate that Linear Regression performed better at predicting than other algorithms, with less error and better prediction performance. The contribution of this paper lies in the provision of how to get to the right places for tourists, as well as the provision of various options available to tourists.