Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

A personalized hotel recommendation system for online booking based on multiple criteria decision analysis

Pratikakis Emmanouil

Full record


URI: http://purl.tuc.gr/dl/dias/CEA8EEEB-F065-4D72-94A1-84E5DC5525BA
Year 2017
Type of Item Diploma Work
License
Details
Bibliographic Citation Emmanouil Pratikakis, "A personalized hotel recommendation system for online booking based on multiple criteria decision analysis", Diploma Work, School of Production Engineering and Management, Technical University of Crete, Chania, Greece, 2017 https://doi.org/10.26233/heallink.tuc.70374
Appears in Collections

Summary

The explosive growth of the Internet has increased the volume and complexity of available information, fact that can make decision-making inefficient. Recommendation or Recommender systems are software tools and techniques intended to help users in decision-making processes by suggesting products or services of potential interest. In this thesis a personalized recommender system is developed considering user preferences. Initially the theoretical framework of the recommendation problem is analyzed and current methodologies and approaches are reviewed. Then a methodological framework based on Multiple Criteria Decision Analysis is proposed. Specifically an aggregation-disaggregation approach is used for user modeling prior to the application of a collaborative filtering algorithm based on multi-criteria ratings. Finally in order to evaluate the system’s performance it was applied in the online hotel booking recommendations domain using a data set of hotel reviews from trip-advisor website.

Available Files

Services

Statistics