A Novel Approach towards Database Exploration using Collaborative Filtering

Recommender systems play an important role in today’s applications which need to satisfy diverse user needs. Recommendation systems are widely used in web applications, e.g. online book shop, movie recommendation etc. It also plays an important role in the field of database systems, where users retrieve interesting information from database by submitting SQL queries. In this case such a system suggests potentially useful queries to the user. In this paper we have presented a system which follows collaborative filtering technique. We have converted the queries submitted by user into general form which is suitable for further calculations. Our system maintains sessions of users. Session is nothing but sequence of queries submitted by the user. We first determines the past session which is similar to current user session, and subsequently use queries in that session to give recommendations.