2019
DOI: 10.33111/nfmte.2019.065
|View full text |Cite
|
Sign up to set email alerts
|

Machine learning approach for forecasting cryptocurrencies time series

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
2
0
1

Year Published

2021
2021
2023
2023

Publication Types

Select...
4
1

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(3 citation statements)
references
References 0 publications
0
2
0
1
Order By: Relevance
“…Using paired-samples t-tests and Wilcoxon signed-rank tests, the study confirmed that stock prices can be predicted more effectively when sentiment scores are incorporated into the predictions. Vasyl Derbentsev [35] uses the Binary Autoregressive Tree model (BART), and Neural Networks (Multilayer Perceptron, MLP) and an ensemble of Classification and Regression Trees models (Random Forest, RF) to predict the price movements of Bitcoin, Ethereum, and Ripple. As a result, when measuring MAPE, the RF model showed the best results.…”
Section: Stock Market and Sentiment Analysismentioning
confidence: 99%
“…Using paired-samples t-tests and Wilcoxon signed-rank tests, the study confirmed that stock prices can be predicted more effectively when sentiment scores are incorporated into the predictions. Vasyl Derbentsev [35] uses the Binary Autoregressive Tree model (BART), and Neural Networks (Multilayer Perceptron, MLP) and an ensemble of Classification and Regression Trees models (Random Forest, RF) to predict the price movements of Bitcoin, Ethereum, and Ripple. As a result, when measuring MAPE, the RF model showed the best results.…”
Section: Stock Market and Sentiment Analysismentioning
confidence: 99%
“…The linear paradigm has been replaced by a nonlinear paradigm (Peters, 1994), which is based on the recognition of the fractal nature of the market and is actively developed for analysis and modeling, including in (Perepelitsa and Maksyshko, 2012) and (Maksyshko et al, 2020). This statement is based on such features of time series (TS) of indicators characterizing financial markets: the lack of independence of levels, the presence of long-term memory, and others (Derbentsev et al, 2019;. The use of statistical methods for their research and further forecasting (as the ultimate goal of the analysis) turns out to be inadequate.…”
Section: Related Workmentioning
confidence: 99%
“…Все частіше для розв'язання прикладних задач використовуються більш складні регресійні моделі та методи машинного навчання. Приклади використання можна побачити в роботах: [1] -прогнозування вартості легкових авто, [2] -прогнозування повеней, [3] -прогнозування потоків та рівнів води, [4] -прогнозування вартості криптовалют, в [5] використовуються для прогнозування цін на нерухомість. В роботі [6] представлено огляд та класифікацію моделей прогнозування.…”
Section: подовження рядів даних за значеннями показників схожих рядівunclassified