Collaborative filtering algorithms find useful patterns in rating and consumption data and exploit these patterns to guide users to good items. Many of the patterns in rating datasets reflect important real-world differences between the various users and items in the data; other patterns may be irrelevant or possibly undesirable for social or ethical reasons, particularly if they reflect undesired discrimination, such as gender or ethnic discrimination in publishing. In this work, we examine the response of collaborative filtering recommender algorithms to the distribution of their input data with respect to a dimension of social concern, namely content creator gender. Using publicly-available book ratings data, we measure the distribution of the genders of the authors of books in user rating profiles and recommendation lists produced from this data. We find that common collaborative filtering algorithms differ in the gender distribution of their recommendation lists, and in the relationship of that output distribution to user profile distribution.

A system for re-ordering the search results to provide to the user results of more relevance to him with the help of his profile. This concept is called Personalization. These profiles can be created by collecting data explicitly (which may be input directly by the user in the form of recommendation, comment or vote) as well as implicitly (based on the user's browsing patterns). This data can be monitored locally (at the client side) or at the server level or some hybrid approach can be adopted. The open recommendation system facilitates the degree to which personalization of results is needed by the user. The system design also includes measures to maintain the privacy and security of the users by encrypting their profile information to counter the threats to the same. The system has been designed as an open ended one and has a window for more ideas/ designs to be incorporated some of which have been mentioned in the future works.