The Community for Technology Leaders
2016 International Conference on Big Data and Smart Computing (BigComp) (2016)
Hong Kong, China
Jan. 18, 2016 to Jan. 20, 2016
ISSN: 2375-9356
ISBN: 978-1-4673-8795-8
pp: 85-92
Victor W. Chu , School of Computer Sc & Eng., University of New South Wales, Sydney, Australia
Fang Chen , ATP Laboratory, National ICT Australia, Sydney, Australia
Raymond K. Wong , University of New South Wales and National ICT Australia, Sydney, Australia
Ivan Ho , Novel Approach Limited, Hong Kong
Joe Lee , Novel Approach Limited, Hong Kong
While time-series analysis techniques are commonly used in financial forecasting, a key source of market volatility is omitted from these models. Financial news is known to be making persuasive impact to the markets. Without considering these additional signals, only sub-optimal predictions can be made. This paper proposes a supervised topic learning approach to improve portfolio return. It is achieved by considering market-sentiment linked topics retrieved from financial news. Using this approach, we successfully improve the prediction accuracy of a proprietary trade recommendation platform. Different from traditional sentiment analysis and unsupervised topic modeling methods, topics specific to different sentiment levels are identified by our proposed model to quantify market conditions. The topics are learned from historical market performances and commentaries instead of using subjective interpretation of sentiments from human expressions. By capturing the knowledge specific to respective industries and markets, an impressive double-digit improvement in portfolio return is obtained as shown in our experiments.
Numerical models, Predictive models, Australia, Analytical models, Portfolios, Sentiment analysis, Resource management

V. W. Chu, Fang Chen, R. K. Wong, Ivan Ho and Joe Lee, "Enhancing portfolio return based on market-sentiment linked topics," 2016 International Conference on Big Data and Smart Computing (BigComp)(BIGCOMP), Hong Kong, China, 2016, pp. 85-92.
85 ms
(Ver 3.3 (11022016))