EM Algorithm and Stochastic Control in Economics

46 Pages Posted: 7 Nov 2016

See all articles by Steven Kou

Steven Kou

Boston University

Xianhua Peng

Peking University - HSBC School of Business

Xingbo Xu

Columbia University - Department of Industrial Engineering and Operations Research (IEOR)

Date Written: November 6, 2016

Abstract

Generalising the idea of the classical EM algorithm that is widely used for computing maximum likelihood estimates, we propose an EM-Control (EM-C) algorithm for solving multi-period finite time horizon stochastic control problems. The new algorithm sequentially updates the control policies in each time period using Monte Carlo simulation in a forward-backward manner; in other words, the algorithm goes forward in simulation and backward in optimization in each iteration. Similar to the EM algorithm, the EM-C algorithm has the monotonicity of performance improvement in each iteration, leading to good convergence properties. We demonstrate the effectiveness of the algorithm by solving stochastic control problems in the monopoly pricing of perishable assets and in the study of real business cycle.

Keywords: EM algorithm, stochastic control, recursive model, dynamic programming, monopoly pricing, real business cycle, numerical methods, stochastic approximation

JEL Classification: C44, C61, C63, D4, E3

Suggested Citation

Kou, Steven and Peng, Xianhua and Xu, Xingbo, EM Algorithm and Stochastic Control in Economics (November 6, 2016). Available at SSRN: https://ssrn.com/abstract=2865124 or http://dx.doi.org/10.2139/ssrn.2865124

Steven Kou

Boston University ( email )

595 Commonwealth Avenue
Boston, MA 02215
United States
6173583318 (Phone)

Xianhua Peng (Contact Author)

Peking University - HSBC School of Business ( email )

University Town
Shenzhen, 518055
China

Xingbo Xu

Columbia University - Department of Industrial Engineering and Operations Research (IEOR) ( email )

331 S.W. Mudd Building
500 West 120th Street
New York, NY 10027
United States

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

Paper statistics

Downloads
163
Abstract Views
992
Rank
329,180
PlumX Metrics