A New Genre of Recommender Systems Based on Modern Paradigms of Data Filtering

In this era of web, we have a huge amount of information overload over internet. To extract useful information, filtering is required. Search engines help to solve this problem to some extent but they do not provide personalization of data. Hence, there is a need of recommendation engine. With the help of recommender software the preferences of user for a particular product can be foreseen. Recommender systems help in pinpointing the required information thereby deescalating unwanted information. Collaborative filtering is the most efficient approach to create recommendations so that the identified choices of a user's group can be used to envisage the preferences for other users which are not yet known to them. Through this paper we endeavor to present a thorough survey of collaborative filtering methods that can help in future for further research in this field and thereby propose a solution to enhance the precision and recall measures of recommendations.