An Efficient Personalized Hotel Recommendation System for Big Data Applications

B. Blesson Raja di, A.R. Arhun, Dr.A.V.K. Shanthi


Administration recommender frameworks have been indicated as important apparatuses
for  giving  proper  proposals  to  clients.  In  the  most  recent  decade,  the  measure  of  clients,
administrations  and  online  data  has  developed  quickly,  yielding  the  enormous  information
examination issue for administration recommender frameworks. Also the greater part of existing
administration  recommender  frameworks,  exhibit  the  same  appraisals  and  rankings  of
administrations  to  distinctive  clients  without  considering  various  clients'  inclination,  and  hence
neglects  to  meet  clients'  customized  necessities.  Consequently  we  approach  a  customized
administration proposal rundown for the most suitable administrations to clients, by proposing a
keyword-aware  suggestion  strategy  and  Natural  Language  Processing,  to  address  the  above
difficulties. Particularly, keywords are utilized  to demonstrate clients' inclination, and a client based
Collaborative Filtering calculation is received to create proper suggestions. To enhance its versatility
and productivity in vast information environment, it is actualized on Hadoop platform, a generally
embraced appropriated figuring stage utilizing the Map Reduce parallel transforming framework. At
long last, far reaching trials are directed on certifiable information datasets, and results exhibit that
personalized  search  technique  fundamentally  enhances  the  exactness  and  versatility  of
administration recommender frameworks over existing methodologies.
Key words: Recommender System, Preference, Keyword, Big Data, Map Reduce, Hadoop, Hotels.

Full Text:

PDF 56-65


Fay, Ch., Jeffrey, D., Sanjay, Gh., Wilson, C., Hsieh, Deborah, A. W.M.B., Tushar, Ch., Andrew, F., Robert, E.G. (2006).Bigtable: A Distributed Storage System for Structured Data.

Araujo, L., Pérez-Agüera., José, R. (2006). Enriching thesauri with hierarchical relationships by pattern matching in dictionaries. ,FinTAL - 5th International Conference on Natural Language Processing: 268-279.

Adomavicius, G., Kwon, Y. (2007). New Recommendation Techniques for Multicriteria Rating Systems, IEEE Intelligent Systems; 22(3): 48-55.

Kambatla, K., Pathak, A., Pucha, H. (2009). Towards Optimizing Hadoop Provisioning in the Cloud, Proc. Conf. Hot Topics in Cloud Computing HotCloud.

Ibrahim, S., Jin, H., Lu, L., Qi, L., Wu, S., Shi, X. (2009). Evaluating Map Reduce on virtual machines: The Hadoop case, Cloud Computing: 519–528.

Goldberg, D., Nichols, D., Brian, M.O., Douglas, T. (1992).Using collaborative filtering to weave an information Tapestry, Communications of the ACM; 35(12):61-71.

Kejiang, Y., Xiaohong, J., Yanzhang, H., Xiang, L., Haiming, Y., Peng, H. (2012). Hadoop: A Scalable Hadoop Virtual Cluster Platform for Map Reduce-Based Parallel Machine Learning with Performance Consideration.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

World of Researches Publication