Media-aware quantitative trading based on public Web information

• Published in: Decision Support Systems Vol. 61; pp. 93 - 105
• Main Authors: Li, Qing, Wang, Tiejun, Gong, Qixu, Chen, Yuanzhu, Lin, Zhangxi, Song, Sa-kwang
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01-05-2014; Elsevier; Elsevier Sequoia S.A
• Subjects: Applied sciences; Artificial intelligence; Computer science; control theory; systems; Data processing. List processing. Character string processing; Emotions; Exact sciences and technology; Investment policy; Investors; Memory organisation. Data processing; Operational research and scientific management; Operational research. Management science; Portfolio theory; Rates of return; Securities trading; Sentiment analysis; Social networks; Software; Speech and sound recognition and synthesis. Linguistics; Stock market; Studies; Trading strategy; Web information; Sentiment analysis; Stock market; Web information; Trading strategy; Finance; Social network; Emotion emotionality; Financial market; Market survey; Mean square error; Mood; Behavioral analysis; Stock exchange; World wide web; Public information; Internet; Public opinion; Impulse; Stock markets; Investment
• ISSN: 0167-9236; 1873-5797
• DOI: 10.1016/j.dss.2014.01.013

Recent studies in behavioral finance discover that emotional impulses of stock investors affect stock prices. The challenge lies in how to quantify such sentiment to predict stock market movements. In this article, we propose a media-aware quantitative trading strategy utilizing sentiment information of Web media. This is achieved by capturing public mood from interactive behaviors of investors in social media and studying the impact of firm-specific news sentiment on stocks along with such public mood. Our experiments on the CSI 100 stocks during a three-month period show that a predictive performance in closeness to the actual future stock price is 0.612 in terms of root mean squared error, the same direction of price movement as the future price is 55.08%, and a simulation trading return is up to 166.11%.
•Extract finance-oriented sentiment words from the Web automatically.•Study the combined effect of Web news and social media on stock markets.•The amplification of social media on Web news affects stock movements.