TY - GEN
T1 - Maintaining prior distributions across evolving eigenspaces
T2 - 11th IEEE International Conference on Machine Learning and Applications, ICMLA 2012
AU - Keane, Kevin R.
AU - Corso, Jason J.
PY - 2012
Y1 - 2012
N2 - Temporal evolution in the generative distribution of nonstationary sequential data is challenging to model. This paper presents a method for retaining the information in prior distributions of matrix variate dynamic linear models (MVDLMs) as the eigenspace of sequential data evolves. The method starts by constructing sliding windows ' matrices composed of a fixed number of columns containing the most recent point-in-time multivariate observation vectors. Characteristic time series, the right singular vectors, are extracted from a window using singular value decomposition (SVD). Then, a sequence of matrices capturing the rotation and scaling of the eigenspace is specified as a function of adjacent windows characteristic time series. The method is tested on observations derived from daily US stock prices spanning 25 years. The results indicate that models constructed using sliding window SVD and MVDLMs, as extended in this paper, are resistant to over-fitting and perform well when used in portfolio construction applications.
AB - Temporal evolution in the generative distribution of nonstationary sequential data is challenging to model. This paper presents a method for retaining the information in prior distributions of matrix variate dynamic linear models (MVDLMs) as the eigenspace of sequential data evolves. The method starts by constructing sliding windows ' matrices composed of a fixed number of columns containing the most recent point-in-time multivariate observation vectors. Characteristic time series, the right singular vectors, are extracted from a window using singular value decomposition (SVD). Then, a sequence of matrices capturing the rotation and scaling of the eigenspace is specified as a function of adjacent windows characteristic time series. The method is tested on observations derived from daily US stock prices spanning 25 years. The results indicate that models constructed using sliding window SVD and MVDLMs, as extended in this paper, are resistant to over-fitting and perform well when used in portfolio construction applications.
KW - Online regression methods
KW - applications of dynamic online incremental learning
KW - unsupervised methods
UR - http://www.scopus.com/inward/record.url?scp=84873599723&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84873599723&partnerID=8YFLogxK
U2 - 10.1109/ICMLA.2012.202
DO - 10.1109/ICMLA.2012.202
M3 - Conference contribution
AN - SCOPUS:84873599723
SN - 9780769549132
T3 - Proceedings - 2012 11th International Conference on Machine Learning and Applications, ICMLA 2012
SP - 422
EP - 427
BT - Proceedings - 2012 11th International Conference on Machine Learning and Applications, ICMLA 2012
Y2 - 12 December 2012 through 15 December 2012
ER -