Published November 1998
| Published
Journal Article
Open
Financial markets: very noisy information processing
Abstract
We report new results about the impact of noise on information processing with application to financial markets. These results quantify the tradeoff between the amount of data and the noise level in the data. They also provide estimates for the performance of a learning system in terms of the noise level. We use these results to derive a method for detecting the change in market volatility from period to period. We successfully apply these results to the four major foreign exchange (FX) markets. The results hold for linear as well as nonlinear learning models and algorithms and for different noise models.
Additional Information
© 1998 IEEE. Reprinted with permission. Manuscript received November 1, 1997; revised April 17, 1998. This work was supported in part by the Center for Neuromorphic Systems Engineering (a National Science Foundation supported Engineering Research Center) under National Science Foundation Cooperative Agreement EEC 9402726. The authors would like to thank A. Atiya, J. Sill, Z. Cataltepe, and X. Song for their helpful comments.Attached Files
Published - MAGprocieee98.pdf
Files
MAGprocieee98.pdf
Files
(441.0 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:e912beff8ca24dd740bee842998dbb08
|
441.0 kB | Preview Download |
Additional details
- Eprint ID
- 1642
- Resolver ID
- CaltechAUTHORS:MAGprocieee98
- Center for Neuromorphic Systems Engineering, Caltech
- NSF
- EEC-9402726
- Created
-
2006-02-08Created from EPrint's datestamp field
- Updated
-
2021-11-08Created from EPrint's last_modified field