International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395 -0056 Volume: 03 Issue: 09 | Sep-2016 www.irjet.net p-ISSN: 2395-0072 © 2016, IRJET | Impact Factor value: 4.45 | ISO 9001:2008 Certified Journal | Page 229 A comprehensive and heuristic approach for Personalized Web Search using Greedy Algorithm K.Saranya M. Phil Scholar, School of Computer Science Engineering and Applications, Bharathidasan University, Tiruchirappalli, Tamil Nadu, India, ksaranyakarunanithi.sk@gmail.com ---------------------------------------------------------------------***-------------------------------------------------------------- Abstract - Personalized web search (PWS) used for developing the quality of various search services on the Internet. Users might experience failure when search engines return unrelated results that do not meet their real intentions. Such irrelevance is largely due to the huge variety of users’ contexts and backgrounds, as well as the ambiguity of texts. However, evidences show that user’s private information during search has become known to publicly due to proliferation of PWS. We proposed a PWS framework so-called UPS that can adaptively generalize profiles by queries while respecting user specified privacy requirements. This project presents two greedy algorithms, namely Greedy DP and Greedy IL, for runtime generalization. It also provides an online prediction mechanism for determining whether personalizing a query is beneficial. Rough set theory, which has been used victoriously in solving problems in pattern recognition, machine learning, and data mining, centers around the idea that a set of individual objects may be approximated via a lower and upper bound. In order to obtain the profits that rough sets can provide for data mining and related tasks, efficient computation of these approximations is vital. Compared with the classic Set theory, Rough Set is a mathematical approach to describe imprecision, vagueness, and ambiguity in data analysis, and it was earliest invented. Key Words: Classifier Ensemble Selection, Rough Sets, Feature Selection, Harmony Search, Fuzzy- rough Sets. 1. INTRODUCTION Recommender systems can use data mining techniques in order to make recommendations using knowledge learnt from the action and attributes of users. The main aim of data mining is to discover new, interesting and useful knowledge or information using a variety of techniques such as prediction, classification, clustering, association rule mining and sequential pattern discovery. Currently, there is a rising interest in data mining and educational systems, making educational data mining a new and increasing research community. The data mining approach to personalization uses all the information about users/students which is available on the web site (in the web course) in order to learn user models and to make use of these models for personalization. These systems can use different recommendation techniques in order to recommend online learning actions or optimal browsing pathways to students, based on their preferences, knowledge and the browsing history of other students with identical characteristics. Large amounts of data are generated every day and the ability to analyses them is normally a challenge. Experts need efficient data mining methods to extract useful information and to perform the analysis of the data. This is the case of the Rough Sets Theory (RST); Pawlak introduced mathematical rough set theory in the bit previous ͳͻͺͲ‟s. The theory was based on the distinguishability of objects. Rough set theory affords systems designers with the ability to handle ambiguity. If a concept is „not definable‟ in a given information base, rough sets can „approximate‟ with honor to that knowledge. From a medical point of view, the attribute- value boundaries are generally vague. The rough set philosophy is established on the assumption that with every item of the universe of discourse we associate certain information (data, knowledge). For example, if objects are patients suffering from some disease, symptoms of the disease form information about patients. Objects characterized by the same information are indiscernible (similar) in sight of the available information about them. The in discernibility relation generated in this approach is the mathematical basis of rough set theory. This understanding of indiscernible is related to the concept of Gottfried Wilhelm Leibniz that objects are indiscernible if and only if all available functional take on them identical values ȋLeibniz‟s Law of )ndiscernible The Identity of Indiscernible). However, in the rough set approach indiscernible is defined relative to a given set of functional (attributes). A weak aspect of RST is the unavailability of free RST software, except for limited implementations. On the other hand, there is RST proprietary software. RST is an extension of the set theory and has the implicit feature of compressing the dataset. Such compression is due to the definition of sameness classes based on indiscernibility relations and to the elimination of redundant or