Journal of Advanced Computational Intelligence and Intelligent Informatics
Online ISSN : 1883-8014
Print ISSN : 1343-0130
ISSN-L : 1883-8014
Regular Papers
Stock Market Trend Prediction Based on Text Mining of Corporate Web and Time Series Data
Hoang T. P. ThanhPhayung Meesad
著者情報
ジャーナル 認証あり

2014 年 18 巻 1 号 p. 22-31

詳細
抄録

Predicting the behaviors of the stock markets are always an interesting topic for not only financial investors but also scholars and professionals from different fields, because successful prediction can help investors to yield significant profits. Previous researchers have shown the strong correlation between financial news and their impacts to the movements of stock prices. This paper proposes an approach of using time series analysis and text mining techniques to predict daily stock market trends. The research is conducted with the utilization of a database containing stock index prices and news articles collected from Vietnam websites over 3 years from 2010 to 2012. A robust feature selection and a strong machine learning algorithm are able to lift the forecasting accuracy. By combining Linear Support Vector Machine Weight and Support Vector Machine algorithm, this proposed approach can enhance the prediction accuracy significantly above those of related research approaches. The results show that data set represented by 42 features achieves the highest accuracy by using one-against-one Support Vector Machines (up to 75%) and one-against-one method outperforms one-against-all method in almost all case studies.

著者関連情報

この記事は最新の被引用情報を取得できません。

© 2014 Fuji Technology Press Ltd.
前の記事 次の記事
feedback
Top