Data-Guided Model Combination by Decomposition and Aggregation

Machine Learning, Vol. 63, No. 1, pp. 43-67

30 Pages Posted: 17 Jan 2011

See all articles by Mingyang Xu

Mingyang Xu

American International Group, Inc.

Michael Golay

affiliation not provided to SSRN

Date Written: November 5, 2005

Abstract

Model selection and model combination is a general problem in many areas. Especially, when we have several different candidate models and also have gathered a new data set, we want to construct a more accurate and precise model in order to help predict future events. In this paper, we propose a new data-guided model combination method by decomposition and aggregation. With the aid of influence diagrams, we analyze the dependence among candidate models and apply latent factors to characterize such dependence. After analyzing model structures in this framework, we derive an optimal composite model. Two widely used data analysis tools, namely, Principal Component Analysis (PCA) and Independent Component Analysis (ICA) are applied for the purpose of factor extraction from the class of candidate models. Once factors are ready, they are sorted and aggregated in order to produce composite models. During the course of factor aggregation, another important issue, namely factor selection, is also touched on. Finally, a numerical study shows how this method works and an application using physical data is also presented.

Keywords: Model Selection, Model Combination, Model Dependence, Model Structure, Model Decomposition, Principal Component Analysis, Independent Component Analysis, BIC, Cross-Validation

JEL Classification: C13, C14, C44, C51, C52, C61

Suggested Citation

Xu, Mingyang and Golay, Michael, Data-Guided Model Combination by Decomposition and Aggregation (November 5, 2005). Machine Learning, Vol. 63, No. 1, pp. 43-67, Available at SSRN: https://ssrn.com/abstract=1742035

Mingyang Xu (Contact Author)

American International Group, Inc. ( email )

80 Pine Street
New York, NY 10270
United States

Michael Golay

affiliation not provided to SSRN ( email )

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
41
Abstract Views
582
PlumX Metrics