Improving stock market prediction by integrating both market news and stock prices

Authors:
Xiaodong Li;Chao Wang;Jiawei Dong;Feng Wang;Xiaotie Deng;Shanfeng Zhu
Affiliations:
Department of Computer Science, City University of Hong Kong, Hong Kong;Fudan University, Shanghai, China;Fudan University, Shanghai, China;Wuhan University, Wuhan, China;Department of Computer Science, City University of Hong Kong, Hong Kong and Department of Computer Science, University of Liverpool, Liverpool, UK;Fudan University, Shanghai, China
Venue:
DEXA'11 Proceedings of the 22nd international conference on Database and expert systems applications - Volume Part II
Year:
2011

Citing 10
Cited 1

News Sensitive Stock Trend Prediction

PAKDD '02 Proceedings of the 6th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining
Thumbs up?: sentiment classification using machine learning techniques

EMNLP '02 Proceedings of the ACL-02 conference on Empirical methods in natural language processing - Volume 10
Determining the sentiment of opinions

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Segmentation of Plane Curves

IEEE Transactions on Computers
Integrating Multiple Data Sources for Stock Prediction

WISE '08 Proceedings of the 9th international conference on Web Information Systems Engineering
Opinion Mining and Sentiment Analysis

Foundations and Trends in Information Retrieval
Textual analysis of stock market prediction using breaking financial news: The AZFin text system

ACM Transactions on Information Systems (TOIS)
A quantitative stock prediction system based on financial news

Information Processing and Management: an International Journal
The SHOGUN Machine Learning Toolbox

The Journal of Machine Learning Research
Support vector machine with adaptive parameters in financial time series forecasting

IEEE Transactions on Neural Networks

Evaluating and understanding text-based stock price prediction models

Information Processing and Management: an International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Stock market is an important and active part of nowadays financial markets. Addressing the question as to how to model financial information from two sources, we focus on improving the accuracy of a computer aided prediction by combining information hidden in market news and stock prices in this study. Using the multi-kernel learning technique, a system is presented that makes predictions for the Hong Kong stock market by incorporating those two information sources. Experiments were conducted and the results have shown that in both cross validation and independent testing, our system has achieved better directional accuracy than those by the baseline system that is based on single one information source, as well as by the system that integrates information sources in a simple way.