Iterated and exponentially weighted moving principal component analysis
Statistical Finance
2021-08-31 v1
Abstract
The principal component analysis (PCA) is a staple statistical and unsupervised machine learning technique in finance. The application of PCA in a financial setting is associated with several technical difficulties, such as numerical instability and nonstationarity. We attempt to resolve them by proposing two new variants of PCA: an iterated principal component analysis (IPCA) and an exponentially weighted moving principal component analysis (EWMPCA). Both variants rely on the Ogita-Aishima iteration as a crucial step.
Cite
@article{arxiv.2108.13072,
title = {Iterated and exponentially weighted moving principal component analysis},
author = {Paul Bilokon and David Finkelstein},
journal= {arXiv preprint arXiv:2108.13072},
year = {2021}
}
Comments
9 pages, 5 figures