ABSTRACT
The tourism-based recommender system focuses on tourism characteristics and unused resources with customer needs. The intelligent recommender system comprises three layers such as a data source layer, an intermediate layer and an application layer. Collaborative filtering predicts unknown outcomes by creating a user-item matrix that consists of user’s product preferences or interests. Accuracy metrics are used to evaluate the accuracy of any type of filtering-based recommendation system by contrasting the predicted ratings directly with the actual user rating. Geographical information system is a system which is used to capture, store, manipulate and analyze the spatial or geographic data. Different machine learning algorithms like Bayesian, decision tree, matrix factorization, nearest-neighbor, deep learning neural network and clustering are used for prediction of different tourist places according to users preferences. Clustering method makes a number of user clusters to produce recommendations for active users.
