A Hybrid Approach to Improve Recommendation System in E-Tourism

Recommendation Systems help users search large amounts of digital contents and identify more effectively the items—products or services—that are likely to be more attractive or useful. As such, it can be characterized as tools that help people making decisions, i.e., make a choice across a vast set of alternatives. This research work has explored decision-making processes in the wide application domain of online services, specifically, hotel booking. This research work is a combination of collaborative filtering (Item-based) recommendation and knowledge-based recommendation system. In which collaborative filtering recommendation will work for user searching and knowledge-based recommendation will work as default recommendation system. In knowledge-based recommendation system it reads the user profile along with his activity of certain last time period as our main knowledge base where this work define the fact of user’s activity. Then this research work applies sorting and counting algorithm. Contextual data are temporarily stored in the knowledge base as the time user stay logged in. Each login will take an updated contextual database. In searching, using item-based k-nearest neighbor algorithm for prediction by collaborative filtering. This work proposed a new rating system which based on hotels performance.