Exploring the predictability of range-based volatility estimators using RNNs

We investigate the predictability of several range-based stock volatility estimators, and compare them to the standard close-to-close estimator which is most commonly acknowledged as the volatility. The patterns of volatility changes are analyzed using LSTM recurrent neural networks, which are a sta...

Full description

Saved in:
Bibliographic Details
Main Authors Petneházi, Gábor, Gáll, József
Format Journal Article
LanguageEnglish
Published 19.03.2018
Subjects
Quantitative Finance - Computational Finance
Quantitative Finance - Statistical Finance
Statistics - Machine Learning
Online AccessGet full text

Cover

More Information
Summary:We investigate the predictability of several range-based stock volatility estimators, and compare them to the standard close-to-close estimator which is most commonly acknowledged as the volatility. The patterns of volatility changes are analyzed using LSTM recurrent neural networks, which are a state of the art method of sequence learning. We implement the analysis on all current constituents of the Dow Jones Industrial Average index, and report averaged evaluation results. We find that changes in the values of range-based estimators are more predictable than that of the estimator using daily closing values only.
DOI:10.48550/arxiv.1803.07152