Header menu link for other important links
Boosting Decision Trees for Prediction of Market Trends
Published in Medwell Publications
Volume: 13.0
Issue: 3.0
Pages: 552.0 - 556.0
Usage of social sites like Facebook, Twitter is increasing rapidly. People are using these sites for getting feedback about any product or service. Social data is the best data which business analyst can use for getting analysis results. From social data the investor can predict in which products the users are more interested in or what changes the users want in service. The social data analysis will definitely increase the sale or profit gained by the investor. The use of machine learning algorithms for analysing market data will add more knowledge into the knowledge of investor. In this study, we have proposed a method for analysing market data collected from social sites. We have shown the behaviour of different machine learning algorithms against market data. It is found that AdaBoost algorithm with one level decision trees perform best against market data. We have used AdaBoost to boost the performance of decision trees and proved with results. Different phases of social media data mining are also explained in detail.
About the journal
JournalJournal of Engineering and Applied Sciences
PublisherMedwell Publications
Open AccessNo