search query: @indexterm PREDICTION THEORY / total: 137
reference: 7 / 137
Author: | Azzouzi, M. Nabney, I. T. |
Title: | Dynamic local models for segmentation and prediction of financial time series |
Journal: | European Journal of Finance
2001 : DEC, VOL. 7:4, p. 289-311 |
Index terms: | DYNAMIC MODELS SEGMENTATION PREDICTION THEORY FINANCE |
Language: | eng |
Abstract: | In the analysis and prediction of many real-world time series, the assumption of stationarity is not valid. A special form of non-stationarity, where the underlying generator switches between (approximately) stationary regimes, seems particularly appropriate for financial markets. The authors introduce a new model which combines a dynamic switching (controlled by a hidden Markov model) and a non-linear dynamical system. The authors show how to train this hybrid model in a maximum likelihood approach and evaluate its performance on both synthetic and financial data. The paper provides a substantial list of references on this subject. |
SCIMA