Novel Recommendation System for E-Commerce Tourism Platform

The traditional collaborative filtering-based recommendation algorithm is improved in terms of offline consumer clustering and consumer weighting. Insights into the structure of the e-commerce tourism platform are provided to offer consumers customized search and recommendation services. The rapid growth of tourism e-commerce has highlighted the need of developing customized recommendation systems for China's e-commerce tourism platform. A clustering-based customized e-commerce tourism recommendation system is proposed, which can quickly and accurately generate a list of tourism information of interest to users while consumers are accessing the e-commerce tourism platform. In addition, the generated list will be recommended to users, reducing consumers' time consumption and search costs, improving transaction rates of the e-commerce tourism platform.