Noisy Time Series Prediction using Symbolic Representation and Recurrent Neural Network Grammatical Inference
| dc.contributor.author | Lawrence, Steve | en_US |
| dc.contributor.author | Tsoi, Ah Chung | en_US |
| dc.contributor.author | Giles, C. Lee | en_US |
| dc.date.accessioned | 2004-05-31T22:38:46Z | |
| dc.date.available | 2004-05-31T22:38:46Z | |
| dc.date.created | 1996-04 | en_US |
| dc.date.issued | 1998-10-15 | en_US |
| dc.description.abstract | Financial forecasting is an example of a signal processing problem which is challenging due to small sample sizes, high noise, non-stationarity, and non-linearity. Neural networks have been very successful in a number of signal processing applications. We discuss fundamental limitations and inherent difficulties when using neural networks for the processing of high noise, small sample size signals. We introduce a new intelligent signal processing method which addresses the difficulties. The method uses conversion into a symbolic representation with a self-organizing map, and grammatical inference with recurrent neural networks. We apply the method to the prediction of daily foreign exchange rates, addressing difficulties with non-stationarity, overfitting, and unequal a priori class probabilities, and we find significant predictability in comprehensive experiments covering 5 different foreign exchange rates. The method correctly predicts the direction of change for the next day with an error rate of 47.1%. The error rate reduces to around 40% when rejecting examples where the system has low confidence in its prediction. The symbolic representation aids the extraction of symbolic knowledge from the recurrent neural networks in the form of deterministic finite state automata. These automata explain the operation of the system and are often relatively simple. Rules related to well known behavior such as trend following and mean reversal are extracted. Also cross-referenced as UMIACS-TR-96-27 | en_US |
| dc.format.extent | 952215 bytes | |
| dc.format.mimetype | application/postscript | |
| dc.identifier.uri | http://hdl.handle.net/1903/812 | |
| dc.language.iso | en_US | |
| dc.relation.isAvailableAt | Digital Repository at the University of Maryland | en_US |
| dc.relation.isAvailableAt | University of Maryland (College Park, Md.) | en_US |
| dc.relation.isAvailableAt | Tech Reports in Computer Science and Engineering | en_US |
| dc.relation.isAvailableAt | UMIACS Technical Reports | en_US |
| dc.relation.ispartofseries | UM Computer Science Department; CS-TR-3625 | en_US |
| dc.relation.ispartofseries | UMIACS; UMIACS-TR-96-27 | en_US |
| dc.title | Noisy Time Series Prediction using Symbolic Representation and Recurrent Neural Network Grammatical Inference | en_US |
| dc.type | Technical Report | en_US |