Go home now Header Background Image
Search
Submission Procedure
share: |
 
Follow us
 
 
 
 
Volume 25 / Issue 10

available in:   PDF (875 kB) PS (2 MB)
 
get:  
Similar Docs BibTeX   Write a comment
  
get:  
Links into Future
 
DOI:   10.3217/jucs-025-10-1353

 

An Intelligent Data Analytics based Model Driven Recommendation System

Bushra Ramzan (The Islamia University of Bahawalpur, Pakistan)

Imran Sarwar Bajwa (The Islamia University of Bahawalpur, Pakistan)

Rafaqut Kazmi (The Islamia University of Bahawalpur, Pakistan)

Shabana Ramzan (The Islamia University of Bahawalpur, Pakistan)

Abstract: The recommendation systems are getting important due to their significance in decision making, social and economic impact on customers and getting detailed information relevant to a required product or a service. A challenge in getting true recommendations in terms of relevance is the heterogenous nature of data (likes, ratings, reviews, etc.) that a recommendation engine has to cope with. This paper presents an intelligent approach to handle heterogeneous and large-sized data of user reviews and generate true recommendations for the future customers. The proposed approach makes use of Apache Cassandra to efficiently store data (such as customer reviews, feedback of hotel customers) having context properties such as awareness and knowledge of the tourists, personal preferences (such as ratings, likes, etc.) and location of the users. This system consists of three main components: the web front-end, the data storage and the recommendation engine to gain recommendations efficiently. The recommendation engine is relying on Euclidean distance and Collaborative Filtering (CF) to measure similarities in users' review or items' features. Our hotel recommender approach has bifold contribution as it has ability to handle heterogeneous data with the help of big data platform and it also provides accurate and true recommendations.

Keywords: big data, customer satisfaction, e-commerce, hotel recommender

Categories: K.8.0, J.7, K.3.0, K.3.1