Personalized Dynamic Recommendation System for Tourism Using Hybrid Approach in Web Mining
- Priyanka B. Tiwari
- Krunal J. Panchal
Web Data Mining, Data Acquisition, Data Pre-processing, Data Cleansing, Data Mart Development, Collaborative Filtering, Item-Based Filtering
Today’s rapid exponential growth in the use of internet has given boom to all areas having access to it. This has helped creating great opportunities and options for the businesses as well as customers. But this rapid growth has resulted complex situations for the customers to find the product and services they really want due to variation in prices and features. Also, providing accurate, valuable and personalized information for the customers, has become crucial for the businesses. Here, we have proposed a hybrid approach based on multi-dimensional user behaviour. It combines various techniques for recommendation and generates a flexible recommendation for both registered/unregistered users. For unregistered user it gives recommendation based on their past session whereas for registered users, it gives the result with the hybrid approach that considers the past history of the user itself as well as recent highly searched items by other users. This approach helps the users to get what is trending currently and they are unaware of. Evaluation of effectiveness is done using standard data set and by comparison with the existing system. For the research work, we have taken tourism domain as it is the most profitable and trending area now a days. The result shows that the personalized recommendation in a dynamic manner not only has direct impact on customer’s interest and gross-sale, but also increase the loyalty to/for the customer.
Priyanka B. Tiwari, Krunal J. Panchal. "Personalized Dynamic Recommendation System for Tourism Using Hybrid Approach in Web Mining".INTERNATIONAL JOURNAL OF ENGINEERING DEVELOPMENT AND RESEARCH ISSN:2321-9939, Vol.5, Issue 2, pp.609-615, URL :https://rjwave.org/ijedr/papers/IJEDR1702106.pdf
Volume 5 Issue 2
Pages. 609-615
