Robust Optimization of Forecast Combinations

25 Pages Posted: 18 Apr 2018 Last revised: 23 Jul 2018

See all articles by Thierry Post

Thierry Post

Graduate School of Business of Nazarbayev University

Selcuk Karabati

Koc University - College of Administrative Sciences and Economics

Stelios Arvanitis

Athens University of Economics and Business

Date Written: March 28, 2018

Abstract

A methodology is developed for constructing robust forecast combinations which improve upon a given benchmark specification for all symmetric and convex loss functions. The optimal forecast combination asymptotically almost surely dominates the benchmark and, in addition, minimizes the expected loss function, under standard regularity conditions. The optimum in a given sample can be found by solving a large Convex Optimization problem. An application to forecasting of changes of the S&P 500 Volatility Index shows that robust optimized combinations improve significantly upon the out-of-sample forecasting accuracy of simple averaging and unrestricted optimization.

Keywords: Forecasting, Robust Optimization, Stochastic Dominance, Convex Optimization

JEL Classification: C44, C54, C61

Suggested Citation

Post, Thierry and Karabati, Selcuk and Arvanitis, Stelios, Robust Optimization of Forecast Combinations (March 28, 2018). Available at SSRN: https://ssrn.com/abstract=3156302 or http://dx.doi.org/10.2139/ssrn.3156302

Thierry Post (Contact Author)

Graduate School of Business of Nazarbayev University ( email )

53 Kabanbay Batyra Avenue
Astana, 010000
Kazakhstan

Selcuk Karabati

Koc University - College of Administrative Sciences and Economics ( email )

Rumelifeneri Yolu
College of Administrative Sciences and Economics
Sariyer 34450, Istanbul
Turkey

Stelios Arvanitis

Athens University of Economics and Business ( email )

76 Patission Street
Athens, 104 34
GREECE

Here is the Coronavirus
related research on SSRN

Paper statistics

Downloads
73
Abstract Views
473
rank
356,793
PlumX Metrics