LASSO-based high-frequency return predictors for profitable Bitcoin investment
- 2 April 2021
- journal article
- research article
- Published by Taylor & Francis in Applied Economics Letters
- Vol. 29 (12) , 1079-1083
Abstract
This article explores the Bitcoin return predictability of variables constructed from one-minute high-frequency Bitcoin trading data. During the training period of 2012–2018, LASSO is used to pick out the most powerful predictors. We then use predictors selected by LASSO to predict the Bitcoin returns in the 2018–2019 test sample. An investment strategy based on the return predictions outperforms a simple buy-and-hold strategy and other strategies based on the prediction of Ordinary Least Squares and Neural Networks.Keywords
This publication has 13 references indexed in Scilit:
- A novel cryptocurrency price trend forecasting model based on LightGBMFinance Research Letters, 2020
- On the determinants of bitcoin returns: A LASSO approachFinance Research Letters, 2018
- Price manipulation in the Bitcoin ecosystemJournal of Monetary Economics, 2018
- Can volume predict Bitcoin returns and volatility? A quantiles-based approachEconomic Modelling, 2017
- On the hedge and safe haven properties of Bitcoin: Is it really more than a diversifier?Finance Research Letters, 2017
- Bitcoin as a Complement to Emerging Market CurrenciesEmerging Markets Finance and Trade, 2016
- What Are the Main Drivers of the Bitcoin Price? Evidence from Wavelet Coherence AnalysisPLOS ONE, 2015
- Statistics for High-Dimensional Data2011
- In-sample vs. out-of-sample tests of stock return predictability in the context of data miningJournal of Empirical Finance, 2006
- Macro variables and international stock return predictabilityInternational Journal of Forecasting, 2005