Krill herd support vector regression and heterogeneous autoregressive leverage: evidence from forecasting and trading commodities

Stasinakis, C., Sermpinis, G., Psaradellis, I. and Verousis, T. (2016) Krill herd support vector regression and heterogeneous autoregressive leverage: evidence from forecasting and trading commodities. Quantitative Finance, 16(102), pp. 1901-1915. (doi:10.1080/14697688.2016.1211800)

[img] Text
122457.pdf - Accepted Version
Restricted to Repository staff only until 15 March 2018.

742kB

Abstract

In this study a Krill Herd - Support Vector Regression (KH-vSVR) model is introduced. The Krill Herd (KH) algorithm is a novel metaheuristic optimization technique inspired by the behaviour of krill herds. The KH optimizes the SVR parameters by balancing the search between local and global optima. The proposed model is applied to the task of forecasting and trading three commodity Exchange Traded Funds (ETFs) on a daily basis over the period 2012-2014. The inputs of the KH-vSVR models are selected through the Model Confidence Set (MCS) from a large pool of linear predictors. The KH-vSVR’s statistical and trading performance is benchmarked against traditionally adjusted SVR structures and the best linear predictor. In addition to a simple strategy, a time-varying leverage trading strategy is applied based on Heterogeneous Autoregressive (HAR) volatility estimations. It is shown that the KH-vSVR outperforms its counterparts in terms of statistical accuracy and trading efficiency, while the leverage strategy is found to be successful.

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Verousis, Dr Thanos and Stasinakis, Dr Charalampos and Sermpinis, Dr Georgios
Authors: Stasinakis, C., Sermpinis, G., Psaradellis, I., and Verousis, T.
College/School:College of Social Sciences > Adam Smith Business School > Accounting and Finance
College of Social Sciences > Adam Smith Business School > Economics
Journal Name:Quantitative Finance
Publisher:Taylor & Francis
ISSN:1469-7688
ISSN (Online):1469-7696
Published Online:14 September 2016

University Staff: Request a correction | Enlighten Editors: Update this record