Machine Learning-Based Timeseries Analysis for Cryptocurrency Price Prediction: A Systematic Review and Research

A, Siva Kumar; PV, Gopirajan; Jackson, Beulah

doi:10.1109/icnwc57852.2023.10127439

Cited by 3 publications

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On this basis Long Short-Term Memory (LSTM) networks have proven effective for capturing the complexities of cryptocurrency price fluctuations with Kumar et al [15] assessing Long Short-Term Memory (LSTM) networks for predicting prices, while empha-sizing the model's ability to adjust to the cryptocurrency price fluctuations. The authors employed numerous market data features such as high, low, open, close, and market cap values.…”

Section: Literature Reviewmentioning

confidence: 99%

Enhancing Bitcoin Price Volatility Estimator Predictions: A Four-Step Methodological Approach Utilizing Elastic Net Regression

Zournatzidou,

Mallidis,

Farazakis

et al. 2024

Mathematics

View full text Add to dashboard Cite

This paper provides a computationally efficient and novel four-step methodological approach for predicting volatility estimators derived from bitcoin prices. In the first step, open, high, low, and close bitcoin prices are transformed into volatility estimators using Brownian motion assumptions and logarithmic transformations. The second step determines the optimal number of time-series lags required for converting the series into an autoregressive model. This selection process utilizes random forest regression, evaluating the importance of each lag using the Mean Decrease in Impurity (MDI) criterion and optimizing the number of lags considering an 85% cumulative importance threshold. The third step of the developed methodological approach fits the Elastic Net Regression (ENR) to the volatility estimator’s dataset, while the final fourth step assesses the predictive accuracy of ENR, compared to decision tree (DTR), random forest (RFR), and support vector regression (SVR). The results reveal that the ENR prevails in its predictive accuracy for open and close prices, as these prices may be linear and less susceptible to sudden, non-linear shifts typically seen during trading hours. On the other hand, SVR prevails for high and low prices as these prices often experience spikes and drops driven by transient news and intra-day market sentiments, forming complex patterns that do not align well with linear modelling.

show abstract

Section: Literature Reviewmentioning

confidence: 99%