Scaled PCA: A new approach to dimension reduction

Scaled PCA: A new approach to dimension reduction

This paper proposes a novel supervised learning technique for forecasting: scaled principal component analysis (sPCA). The sPCA improves the traditional principal component analysis (PCA) by scaling each predictor with its predictive slope on the target to be forecasted. Unlike the PCA that maximize...

Full description

Saved in:
Bibliographic Details
Main Authors: HUANG, Dashan, JIANG, Fuwei, LI, Kunpeng, TONG, Guoshi, ZHOU, Guofu
Format: text
Language:English
Published: Institutional Knowledge at Singapore Management University 2022
Subjects:
Forecasting
PCA
Big Data
Dimension Reduction
Machine Learning
Management Sciences and Quantitative Methods
Online Access:https://ink.library.smu.edu.sg/lkcsb_research/6924
https://ink.library.smu.edu.sg/context/lkcsb_research/article/7923/viewcontent/SSRN_id3358911.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Singapore Management University
Language: English
Description
Summary:This paper proposes a novel supervised learning technique for forecasting: scaled principal component analysis (sPCA). The sPCA improves the traditional principal component analysis (PCA) by scaling each predictor with its predictive slope on the target to be forecasted. Unlike the PCA that maximizes the common variation of the predictors, the sPCA assigns more weight to those predictors with stronger forecasting power. In a general factor framework, we show that, under some appropriate conditions on data, the sPCA forecast beats the PCA forecast, and when these conditions break down, extensive simulations indicate that the sPCA still has a large chance to outperform the PCA. A real data example on macroeconomic forecasting shows that the sPCA has better performance in general.

Similar Items