Predicting crypto-currencies using sparse non-Gaussian state space models

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14560%2F18%3A00101268" target="_blank" >RIV/00216224:14560/18:00101268 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1002/for.2524" target="_blank" >http://dx.doi.org/10.1002/for.2524</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1002/for.2524" target="_blank" >10.1002/for.2524</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Predicting crypto-currencies using sparse non-Gaussian state space models

Popis výsledku v původním jazyce

In this paper we forecast daily returns of crypto-currencies using a wide variety of different econometric models. To capture salient features commonly observed in financial time series like rapid changes in the conditional variance, non-normality of the measurement errors and sharply increasing trends, we develop a time-varying parameter VAR with t-distributed measurement errors and stochastic volatility. To control for overparametrization, we rely on the Bayesian literature on shrinkage priors, which enables us to shrink coefficients associated with irrelevant predictors and/or perform model specification in a flexible manner. Using around one year of daily data, we perform a real-time forecasting exercise and investigate whether any of the proposed models is able to outperform the naive random walk benchmark. To assess the economic relevance of the forecasting gains produced by the proposed models we, moreover, run a simple trading exercise.

Název v anglickém jazyce

Predicting crypto-currencies using sparse non-Gaussian state space models

Popis výsledku anglicky

In this paper we forecast daily returns of crypto-currencies using a wide variety of different econometric models. To capture salient features commonly observed in financial time series like rapid changes in the conditional variance, non-normality of the measurement errors and sharply increasing trends, we develop a time-varying parameter VAR with t-distributed measurement errors and stochastic volatility. To control for overparametrization, we rely on the Bayesian literature on shrinkage priors, which enables us to shrink coefficients associated with irrelevant predictors and/or perform model specification in a flexible manner. Using around one year of daily data, we perform a real-time forecasting exercise and investigate whether any of the proposed models is able to outperform the naive random walk benchmark. To assess the economic relevance of the forecasting gains produced by the proposed models we, moreover, run a simple trading exercise.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

50202 - Applied Economics, Econometrics

Projekt

<a href="/cs/project/GA17-14263S" target="_blank" >GA17-14263S: Dynamické průměrování předpovědí makroekonomických modelů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2018

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

JOURNAL OF FORECASTING

ISSN

0277-6693

e-ISSN

—

Svazek periodika

37

Číslo periodika v rámci svazku

6

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

14

Strana od-do

627-640

Kód UT WoS článku

000441000600001

EID výsledku v databázi Scopus

2-s2.0-85045251359