Abstract
The authors study the problem of how news summarization can help stock price prediction, proposing a generic stock price prediction framework to enable the use of different external signals to predict stock prices. Experiments were conducted on five years of Hong Kong Stock Exchange data, with news reported by Finet; evaluations were performed at individual stock, sector index, and market index levels. The authors' results show that prediction based on news article summarization can effectively outperform prediction based on full-length articles on both validation and independent testing sets.
| Original language | English |
|---|---|
| Pages (from-to) | 26-34 |
| Number of pages | 9 |
| Journal | IEEE Intelligent Systems |
| Volume | 30 |
| Issue number | 3 |
| Early online date | 12 Jan 2015 |
| DOIs | |
| Publication status | Published - May 2015 |
| Externally published | Yes |
Funding
The work described in this article was substantially supported by a grant from the Research Grants Council of the Hong Kong Special Administrative Region, China (UGC/FDS11/E06/14) and an Applied Research Grant by City University of Hong Kong (Project No. 9667095). The work was also partially supported by the National Natural Science Foundation of China under Grant No 61272110.
Keywords
- intelligent systems
- news summarization
- predictive analytics
- Predictive models
- stock prediction