Principal Component Analysis and Portfolio Optimization

28 Pages Posted: 10 Feb 2013 Last revised: 14 Feb 2013

See all articles by Ji Tan

Ji Tan

Pacific Life Insurance Company

Date Written: March 1, 2012

Abstract

Principle Component Analysis (PCA) is one of the common techniques used in Risk modeling, i.e. statistical factor models. When using PCA to estimate the covariance matrix, and applying it to portfolio optimization, we formally analyze its performance, and find positive results in terms of portfolio efficiency (Information Ratio) and transaction cost reduction. We also propose using PCA to manage beta against alpha, and show how to apply the idea within Black-Litterman framework. Finally, we invent the technique 'Mean-Reverting PCA' to improve the stability of conventional PCA analysis.

Keywords: principle component analysis, PCA, portfolio optimization, transaction cost, Black Litterman

JEL Classification: G11

Suggested Citation

Tan, Ji, Principal Component Analysis and Portfolio Optimization (March 1, 2012). Available at SSRN: https://ssrn.com/abstract=2213687 or http://dx.doi.org/10.2139/ssrn.2213687

Ji Tan (Contact Author)

Pacific Life Insurance Company ( email )

Newport Beach, CA
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
1,968
rank
6,765
Abstract Views
5,362
PlumX