Knowledge Discovery on Cryptocurrency Exchange Rate Prediction Using Machine Learning Pipelines

The popularity of cryptocurrency in recent years has gained a lot of attention among researchers and in academic working areas. The uncontrollable and untraceable nature of cryptocurrency offers a lot of attractions to the people in this domain. The nature of the financial market is non-linear and d...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Sensors (Basel, Switzerland) Jg. 22; H. 5; S. 1740
Hauptverfasser: Shahbazi, Zeinab, Byun, Yung-Cheol
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Switzerland MDPI AG 23.02.2022
MDPI
Schlagworte:
Algorithms
Artificial intelligence
Blockchain
Crypto-currencies
cryptocurrency
Data Mining
Deep learning
Digital currencies
exchange rate prediction
Feature selection
Financial markets
Foreign exchange rates
Germany
Humans
Inflation (Finance)
Information management
Knowledge Discovery
Literature reviews
Machine Learning
Market positioning
Neural networks
Peer to peer computing
Volatility
XGBoost
Germany
cryptocurrency
exchange rate prediction
blockchain
XGBoost
ISSN:1424-8220, 1424-8220
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The popularity of cryptocurrency in recent years has gained a lot of attention among researchers and in academic working areas. The uncontrollable and untraceable nature of cryptocurrency offers a lot of attractions to the people in this domain. The nature of the financial market is non-linear and disordered, which makes the prediction of exchange rates a challenging and difficult task. Predicting the price of cryptocurrency is based on the previous price inflations in research. Various machine learning algorithms have been applied to predict the digital coins’ exchange rate, but in this study, we present the exchange rate of cryptocurrency based on applying the machine learning XGBoost algorithm and blockchain framework for the security and transparency of the proposed system. In this system, data mining techniques are applied for qualified data analysis. The applied machine learning algorithm is XGBoost, which performs the highest prediction output, after accuracy measurement performance. The prediction process is designed by using various filters and coefficient weights. The cross-validation method was applied for the phase of training to improve the performance of the system.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1424-8220
1424-8220
DOI:10.3390/s22051740