LAUSR

Performance profiling and testing is one of the interesting topics in the big data management and Cloud Computing. In testing, we use test cases composed to different type of queries to evaluate the performance aspects of the information retrieval system for large scale information collection. This test scenarioperforms the evaluation ofretrieval accuracy for all kind of ambiguity and non factoid queries with result set as Training data. This stands difficult to evaluate the retrieval method in order to schedule or optimize the Recommendation and prediction technique of the IR method to the Real time queries. The Queries is considered as requirement specification which has to supply to search engine or web information provider applications for information or web page retrieval. In this paper, we propose a novel technique named as “Test Retrieval Framework“a performance profiling and testing of the web search engines on the information retrieved towards non factoid queries. In this technique, we apply expectation maximization algorithm as an iterative method to find maximum likelihood estimate.We discuss on the important aspects in this work based on Recommendation models integrating domain and web usage, Query optimization for navigational and Transactional queries, Query Result records.The Experimental results demonstrates the proposed technique outperforms of state of arts approaches in terms of set based measures like Precision, Recall and F measure and rank based measures like Mean Average Precision and Cumulative Gain.