Machine Learning for Realised Volatility Forecasting

54 Pages Posted: 12 Oct 2020 Last revised: 10 Nov 2021

See all articles by Eghbal Rahimikia

Eghbal Rahimikia

University of Manchester - Alliance Manchester Business School

Ser-Huang Poon

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

Date Written: October 8, 2020

Abstract

This paper compares machine learning and HAR models for forecasting realised volatility of 23 NASDAQ stocks using 146 variables extracted from limit order book (LOBSTER) and stock-specific news (Dow Jones Newswires) from 27 July 2007 to 18 November 2016. We find simpler ML to outperform HARs on normal volatility days. With SHAP, an Explainable AI technique, we find simple mid prices at all limit order book levels and mean bid/ask prices drive RV forecasts for many stocks. An ML model with a larger number of units and complex idiosyncratic LOB variables are needed for forecasting volatility jumps.

Keywords: Realised Volatility Forecasting, Machine Learning, Long Short-Term Memory, Heterogeneous AutoRegressive models, Explainable AI, Limit Order Book Data, Dow Jones Newswires, 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

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
792
Abstract Views
1,792
rank
40,027
PlumX Metrics