Developed High Scale Bagging Algorithm for E-Tourism Advising System

Abstract

Filtering huge amounts of data is a very critical issue with the explosion of data over the web and cloud storage. A need to classify and sort these data is linked to that issue to facilitate data management and database building for various applications. Machine learning techniques are the most suitable to deal with such big data.

One of the applications that can be implemented in machine learning is a tourist advising system that harvests data from tourism sites and aggregates different types of data about them (humidity, temperature, distance from user’s country, etc…) and classifies them. These data should be updated constantly, since the system provides real-time decision based on real-time data, where they are used later on by a bagging system to provide the user with suggested tourism sites with percentage to how suitable these sites according to the preferences submitted in addition to some other criteria.