Analyzing Swings in Bitcoin Returns: A Comparative Study of the LPPL and Sentiment-informed Random Forest Models

José Parra-Moyano; Daniel Partida; Moritz Gessl; Somnath Mazumdar

doi:10.1007/s42521-024-00110-7

Analyzing Swings in Bitcoin Returns: A Comparative Study of the LPPL and Sentiment-informed Random Forest Models

José Parra-Moyano^*, Daniel Partida, Moritz Gessl, Somnath Mazumdar

^*Corresponding author af dette arbejde

Institut for Digitalisering

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › peer review

Abstract

Forecasting Bitcoin’s returns continues to be a challenging endeavor for both scholars and practitioners. In this paper, we train a random forest model on a variety of features, with the aim of predicting pronounced changes in the returns of Bitcoin. The model that we present in this paper outperforms the baseline model with which we compare it: the LPPL model. Our results have implications for scholars studying financial prediction models, as well as for practitioners interested in Bitcoin investment.

Originalsprog	Engelsk
Tidsskrift	Digital Finance
Antal sider	13
ISSN	2524-6984
DOI	https://doi.org/10.1007/s42521-024-00110-7
Status	Udgivet - 1 maj 2024

Bibliografisk note

Epub ahead of print. Published online: 01 May 2024.

Emneord

Bitcoin
Cryptocurrencies
LPPL
Machine learning
Sentiment analysis

Adgang til dokumentet

10.1007/s42521-024-00110-7Licens: Ikke-specificeret

Handle.net

Persistent link

Citationsformater

@article{37010f51037743b584a3a3d4ae9f0aae,

title = "Analyzing Swings in Bitcoin Returns: A Comparative Study of the LPPL and Sentiment-informed Random Forest Models",

abstract = "Forecasting Bitcoin{\textquoteright}s returns continues to be a challenging endeavor for both scholars and practitioners. In this paper, we train a random forest model on a variety of features, with the aim of predicting pronounced changes in the returns of Bitcoin. The model that we present in this paper outperforms the baseline model with which we compare it: the LPPL model. Our results have implications for scholars studying financial prediction models, as well as for practitioners interested in Bitcoin investment.",

keywords = "Bitcoin, Cryptocurrencies, LPPL, Machine learning, Sentiment analysis, Bitcoin, Cryptocurrencies, LPPL, Machine learning, Sentiment analysis",

author = "Jos{\'e} Parra-Moyano and Daniel Partida and Moritz Gessl and Somnath Mazumdar",

note = "Epub ahead of print. Published online: 01 May 2024.",

year = "2024",

month = may,

day = "1",

doi = "10.1007/s42521-024-00110-7",

language = "English",

journal = "Digital Finance",

issn = "2524-6984",

publisher = "Springer",

}

TY - JOUR

T1 - Analyzing Swings in Bitcoin Returns

T2 - A Comparative Study of the LPPL and Sentiment-informed Random Forest Models

AU - Parra-Moyano, José

AU - Partida, Daniel

AU - Gessl, Moritz

AU - Mazumdar, Somnath

N1 - Epub ahead of print. Published online: 01 May 2024.

PY - 2024/5/1

Y1 - 2024/5/1

N2 - Forecasting Bitcoin’s returns continues to be a challenging endeavor for both scholars and practitioners. In this paper, we train a random forest model on a variety of features, with the aim of predicting pronounced changes in the returns of Bitcoin. The model that we present in this paper outperforms the baseline model with which we compare it: the LPPL model. Our results have implications for scholars studying financial prediction models, as well as for practitioners interested in Bitcoin investment.

AB - Forecasting Bitcoin’s returns continues to be a challenging endeavor for both scholars and practitioners. In this paper, we train a random forest model on a variety of features, with the aim of predicting pronounced changes in the returns of Bitcoin. The model that we present in this paper outperforms the baseline model with which we compare it: the LPPL model. Our results have implications for scholars studying financial prediction models, as well as for practitioners interested in Bitcoin investment.

KW - Bitcoin

KW - Cryptocurrencies

KW - LPPL

KW - Machine learning

KW - Sentiment analysis

KW - Bitcoin

KW - Cryptocurrencies

KW - LPPL

KW - Machine learning

KW - Sentiment analysis

U2 - 10.1007/s42521-024-00110-7

DO - 10.1007/s42521-024-00110-7

M3 - Journal article

SN - 2524-6984

JO - Digital Finance

JF - Digital Finance

ER -