Information-theoretic measures for nonlinear causality detection: application to social media sentiment and cryptocurrency prices

Information transfer between time series is calculated using the asymmetric information-theoretic measure known as transfer entropy. Geweke’s autoregressive formulation of Granger causality is used to compute linear transfer entropy, and Schreiber’s general, non-parametric, information-theoretic for...

Full description

Saved in:
Bibliographic Details
Main Authors: Z. Keskin, T. Aste
Format: Article
Language:English
Published: The Royal Society 2020-09-01
Series:Royal Society Open Science
Subjects:
Online Access:https://royalsocietypublishing.org/doi/10.1098/rsos.200863
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850201587854606336
author Z. Keskin
T. Aste
author_facet Z. Keskin
T. Aste
author_sort Z. Keskin
collection DOAJ
description Information transfer between time series is calculated using the asymmetric information-theoretic measure known as transfer entropy. Geweke’s autoregressive formulation of Granger causality is used to compute linear transfer entropy, and Schreiber’s general, non-parametric, information-theoretic formulation is used to quantify nonlinear transfer entropy. We first validate these measures against synthetic data. Then we apply these measures to detect statistical causality between social sentiment changes and cryptocurrency returns. We validate results by performing permutation tests by shuffling the time series, and calculate the Z-score. We also investigate different approaches for partitioning in non-parametric density estimation which can improve the significance. Using these techniques on sentiment and price data over a 48-month period to August 2018, for four major cryptocurrencies, namely bitcoin (BTC), ripple (XRP), litecoin (LTC) and ethereum (ETH), we detect significant information transfer, on hourly timescales, with greater net information transfer from sentiment to price for XRP and LTC, and instead from price to sentiment for BTC and ETH. We report the scale of nonlinear statistical causality to be an order of magnitude larger than the linear case.
format Article
id doaj-art-bd2e2e10f08c4dd595b042ff034a7fcf
institution OA Journals
issn 2054-5703
language English
publishDate 2020-09-01
publisher The Royal Society
record_format Article
series Royal Society Open Science
spelling doaj-art-bd2e2e10f08c4dd595b042ff034a7fcf2025-08-20T02:11:58ZengThe Royal SocietyRoyal Society Open Science2054-57032020-09-017910.1098/rsos.200863Information-theoretic measures for nonlinear causality detection: application to social media sentiment and cryptocurrency pricesZ. Keskin0T. Aste1Department of Computer Science & Centre for Blockchain Technologies, University College London, Gower Street, WC1E 6EA London, UKDepartment of Computer Science & Centre for Blockchain Technologies, University College London, Gower Street, WC1E 6EA London, UKInformation transfer between time series is calculated using the asymmetric information-theoretic measure known as transfer entropy. Geweke’s autoregressive formulation of Granger causality is used to compute linear transfer entropy, and Schreiber’s general, non-parametric, information-theoretic formulation is used to quantify nonlinear transfer entropy. We first validate these measures against synthetic data. Then we apply these measures to detect statistical causality between social sentiment changes and cryptocurrency returns. We validate results by performing permutation tests by shuffling the time series, and calculate the Z-score. We also investigate different approaches for partitioning in non-parametric density estimation which can improve the significance. Using these techniques on sentiment and price data over a 48-month period to August 2018, for four major cryptocurrencies, namely bitcoin (BTC), ripple (XRP), litecoin (LTC) and ethereum (ETH), we detect significant information transfer, on hourly timescales, with greater net information transfer from sentiment to price for XRP and LTC, and instead from price to sentiment for BTC and ETH. We report the scale of nonlinear statistical causality to be an order of magnitude larger than the linear case.https://royalsocietypublishing.org/doi/10.1098/rsos.200863Grangercausalitytransfer entropyinformation theorycryptocurrency
spellingShingle Z. Keskin
T. Aste
Information-theoretic measures for nonlinear causality detection: application to social media sentiment and cryptocurrency prices
Royal Society Open Science
Granger
causality
transfer entropy
information theory
cryptocurrency
title Information-theoretic measures for nonlinear causality detection: application to social media sentiment and cryptocurrency prices
title_full Information-theoretic measures for nonlinear causality detection: application to social media sentiment and cryptocurrency prices
title_fullStr Information-theoretic measures for nonlinear causality detection: application to social media sentiment and cryptocurrency prices
title_full_unstemmed Information-theoretic measures for nonlinear causality detection: application to social media sentiment and cryptocurrency prices
title_short Information-theoretic measures for nonlinear causality detection: application to social media sentiment and cryptocurrency prices
title_sort information theoretic measures for nonlinear causality detection application to social media sentiment and cryptocurrency prices
topic Granger
causality
transfer entropy
information theory
cryptocurrency
url https://royalsocietypublishing.org/doi/10.1098/rsos.200863
work_keys_str_mv AT zkeskin informationtheoreticmeasuresfornonlinearcausalitydetectionapplicationtosocialmediasentimentandcryptocurrencyprices
AT taste informationtheoreticmeasuresfornonlinearcausalitydetectionapplicationtosocialmediasentimentandcryptocurrencyprices