Document Type

Project

Lead Author Type

CIS Masters Student

Advisors

Dr. Yonglei Tao, taoy@gvsu.edu

Embargo Period

5-8-2015

Abstract

Vacations play a vital role in our lives. Taking a good vacation can help our physical health; helps maintaining good family relations, improves mental health and reduces the chance of burnouts. However, most vacation recommender systems available are complicated and confusing and usually rely on explicit user ratings to recommend .travel packages. However, user ratings for travel data are sparse, therein reducing their effectiveness in recommending travel packages. I propose to develop a system aimed at exploiting a travel data set and creating travel package recommendations based on the user’s interests and the spatial-temporal correlations that exist within sets of locations, seasons and attractions. Further, I will assess relationships between travel users so than common users can be arranged into travel groups or the people who wants to travel as a group with their family or friends can also be arranged into travel groups. This personalized vacation package recommendation based on the traditional models, which follow a recommendation strategy and has the ability to combine many possible constraints that exist in the real-world scenarios.

This data mining approach uses collaborative filtering method and performs much better than the traditional systems. It can be used both by the travel agencies and the travel groups at low maintenance and cost. The Graphical user interface is designed for both novice and expert users. This project has been developed using NetBeans with java and MySQL. I choose NetBeans because it is free, open-source, cross-platform IDE with built-in-support for Java programming language. This package system can be considered as an experimental prototype, we can see that the proposed recommendation approach works very well for predicting the user travel preferences by exploiting the unique characteristics of vacation package data.

Download

Share

COinS