Machine Learning for Realised Volatility Forecasting

51 Pages Posted: 12 Oct 2020

See all articles by Eghbal Rahimikia

Eghbal Rahimikia

University of Manchester - Alliance Manchester Business School; University of Oxford - Oxford-Man Institute of Quantitative Finance

Ser-Huang Poon

Alliance Manchester Business School, University of Manchester; Alan Turing Institute

Date Written: October 8, 2020

Abstract

This paper examines, for the first time, the performance of machine learning models in realised volatility forecasting using big data sets such as LOBSTER limit order books and news stories from 'Dow Jones News Wires' for 28 NASDAQ stocks over a sample period of June 28, 2007, to November 17, 2016. We find strong evidence to support ML forecasting power dominating an extended CHAR and all other HAR-family of models using evaluation measures such as MSE, QLIKE, MDA and RC values. The LOB-ML has very strong forecasting power and adding News sentiment variables to the data set only improves the forecasting power marginally. However, the good forecasting performance of ML models is relevant only for normal volatility days (i.e. 90% of the out-of-sample period). Throughout the study, we find a persistent trade-off between normal vs jump day forecasting; one model serves well for normal days performs poorly for jump days, and vice versa.

Keywords: Realised Volatility Forecasting, Machine Learning, Long Short-Term Memory, Heterogeneous AutoRegressive (HAR) Models, Limit Order Book (LOB) Data, Dow Jones Corporate News, Big Data

JEL Classification: C22, C45, C51, C53, C55, C58

Suggested Citation

Rahimikia, Eghbal and Poon, Ser-Huang, Machine Learning for Realised Volatility Forecasting (October 8, 2020). Available at SSRN: https://ssrn.com/abstract=3707796 or http://dx.doi.org/10.2139/ssrn.3707796

Eghbal Rahimikia (Contact Author)

University of Manchester - Alliance Manchester Business School ( email )

Booth Street West
Manchester, M15 6PB
United Kingdom

HOME PAGE: http://www.rahimikia.com

University of Oxford - Oxford-Man Institute of Quantitative Finance ( email )

Eagle House
Walton Well Road
Oxford, Oxfordshire OX2 6ED
United Kingdom

Ser-Huang Poon

Alliance Manchester Business School, University of Manchester ( email )

Alliance Manchester Business School
Booth Street West
Manchester, Manchester M15 6PB
United Kingdom
+44 161 275 4031 (Phone)
+44 161 275 4023 (Fax)

HOME PAGE: http://www.manchester.ac.uk/research/Ser-huang.poon/

Alan Turing Institute ( email )

British Library, 96 Euston Road
London, NW12DB
United Kingdom

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
181
Abstract Views
731
rank
193,982
PlumX Metrics