Abstract:The creation of world of internet lead to many advancements in the technical as well as non-technical fields. Many thriving industries gained enormous advantages through the development of internet. Tourism is one among the flourishing industries of this era. Earlier the approach to visit a place is far beyond what is available today. Ranging from pamphlet to maps were made use to visit a place. Routing of places was done using maps and travel guides. Unlike before, the tourism industry has grown to great heights and handles the tours and travel without any manual intercession. The places are endorsed to users automatically using the recommendation system. Existing recommendation systems suffer from a problem of sparsity. Sparsity problem deals with inadequate data related to a user or any travel region. The proposed approach concentrate on eliminating this snag in the existing approach and generating a travel recommendation structure which focus on customized suggestions for users. The tags as well as geotags of images uploaded by the users on social sites like Flickr is made use in order to recommend the points of interest (POI) to the users. A hybrid approach with use of tags, geotags and the owner (author) of the image is proposed in this paper. User based collaborative filtering is used to create suggestions for the users. The benefits of the proposed approach is manifested by experimental analysis on a large cluster of data.