Recommender System (RS) is a personalized information filtering technique used to provide personalized recommendations of products or services to the users. The goal of the RS is to obtain ratings for items(such as music, books, or movies) from the users and based on the result, the system will predict ratings for each item and suggests interesting items to the users. Collaborative filtering technique is widely used recommendation algorithm that predicts item ratings by considering the users with similar preferences (i. e. , "neighbors") who liked in the past. Recommending the highly rated items can improve the accuracy but it does not provide more diverse recommendations. The previous works was modeled using optimization algorithms for recommending bundled items. i. e. , set of items in packages but does not provide more efficient recommendations. In the proposed system, a ranking algorithm along with collaborative filtering technique is used to provide different set of composite package of items to improve both the accuracy and diversity. The empirical evaluation of this proposed technique will be implemented based on real-world datasets to providedifferent set of composite packages to all theusers.

1. <ul style="text-align: justify;"> Data replication has to reduce data file transfer time, bandwidth consumption and maintain the consistency between the data and replica nodes. The centralized replication that reduces the total data file access delay and caching algorithm is used for any replica server is easily joining and leaving from the main server. An Integrated File Replication and Consistency Maintenance mechanism algorithm is used to achieve high efficiency in data replication and consistency maintenance at a low cost. Each replica server determines data replication and update polling by dynamically adapting to time varying file query and file update rates. Poll reduction process is to avoid unnecessary updates.

[1] Zhang And Hurley (2008) "avoiding Monotony: Improving The Diversity Of Recommendation Lists" Proceedings Of The 2008 Acm Conference On Recommender Systems Pp. 123-130. [2] Park Joo And Tuzhilin (2008) "the Long Tail Of Recommender Systems And How To Leverage It" Proceedings Of The 2008 Acm Conference On Recommender Systems Pp. 11-18. [3] Khabbaz Xie And Laks (2011) "toprecs: Pushing The Envelope On Recommender Systems" Data Engineering Pp. 61. [4] Nguyen And Tho (2009) "web Based Recommender Systems And Rating Prediction". [5]xie Laks And T. wood (2012) "composite Recommendations: From Items To Packages" Frontiers Of Computer Science Pp. 264-277. [6] Sarwar And Badrul Et Al (2001) "item-based Collaborative Filtering Recommendation Algorithms" Proceedings Of The 10th International Conference On World Wide Web Acm Pp. 285-295. [7] Adomavicius. G And Y. Kwon (2012) "improving Aggregate Recommendation Diversity Using Ranking-based Techniques" Ieee Transactions On Knowledge And Data Engineering Vol. 24 Pp. 896-911. [8] Schafer . j Et Al. (2007) "collaborative Filtering Recommender Systems" The Adaptive Web Acm Pp. 291-324. [9] Su M. Khoshgoftaar And Russell Greiner (2008) "imputed Neighborhood Based Collaborative Filtering" Web Intelligence And Intelligent Agent Technology Wi-iat'08. Ieee/wic/acm International Conference On Vol. 1. [10] Anderson Chris And Manishahiralall (2011) "recommender Systems For E-shops". [11] Adomavicius And Y. Kwon. (2009) "toward More Diverse Recommendations: Item Re-ranking Methods For Recommender Systems" Workshop On Information Technologies And Systems. [12] Adomavicius And Kwon (2007) "new Recommendation Techniques For Multi Criteria Rating Systems" Intelligent Systems Pp. 48-55.