Abstract
This study links stock prices of publicly traded companies with online financial news to predict direction of stock price change. Previous work shows this to be an extremely challenging problem. We develop a very high-dimensional representation for news about companies that encodes lexical, syntactic and frame semantic information in graphs. Use of a graph kernel to efficiently compare subgraphs for machine learning provides a uniform feature engineering framework that integrates semantic frames in document representation. Evaluated on a news web archive against two benchmarks, only our approach beats the majority class baseline, and with statistically significant results.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings of the 28th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2015 |
| Editors | William Eberle, Ingrid Russell |
| Publisher | AAAI press |
| Pages | 237-240 |
| Number of pages | 4 |
| ISBN (Electronic) | 9781577357308 |
| State | Published - 2015 |
| Event | 28th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2015 - Hollywood, United States Duration: May 18 2015 → May 20 2015 |
Publication series
| Name | Proceedings of the 28th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2015 |
|---|
Other
| Other | 28th International Florida Artificial Intelligence Research Society Conference, FLAIRS 2015 |
|---|---|
| Country/Territory | United States |
| City | Hollywood |
| Period | 5/18/15 → 5/20/15 |
All Science Journal Classification (ASJC) codes
- Artificial Intelligence