A New Hybrid Cryptocurrency Returns Forecasting Method Based on Multiscale Decomposition and an Optimized Extreme Learning Machine Using the Sparrow Search Algorithm

Du, Xiaoxu; Tang, Zhenpeng; Wu, Junchuan; Chen, Kai‐Jie; Cai, Yi

doi:10.1109/access.2022.3179364

Cited by 8 publications

(6 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study claimed to achieved better accuracy, however, it is lacking with a thorough comparative study and considering prediction of other developing digital currencies. Bitcoin and Ethereum prices are forecasted using sparrow search algorithm optimized extreme learning machine in [25]. Unlike regular stock market, cryptocurrency can be traded any time rather than specific trading time and the continuous information can affect its price instantly [26].…”

Section: Related Studiesmentioning

confidence: 99%

See 1 more Smart Citation

An Elitist Artificial Electric Field Algorithm Based Random Vector Functional Link Network for Cryptocurrency Prices Forecasting

et al. 2023

View full text Add to dashboard Cite

Cryptocurrencies have carved out a significant presence in financial transactions during the past few years. Cryptocurrency market performs similarly to other financial markets with considerable nonlinearity and volatility and its prediction is a growing research area. It is challenging to capture the inherent uncertainties connected with cryptocurrency using the currently used conventional methodologies. The popularity of random vector functional link networks (RVFLN) is attributed to its simple structural layout, quick rate of learning, and enhanced generalization ability. It computes the output layer weights using non-iterative techniques like least square methods or iterative techniques like gradient methods, and assigns hidden neuron parameters at random. Random initialization of non-optimal hidden neuron settings, however, degrades the performance. Population-based metaheuristics are a superior option to random initialization for determining the ideal parameters and avoiding the problem of local optima stagnation. In the current article, an elitist artificial electric field algorithm (eAEFA) for training RVFLN is proposed. Here, eAEFA is utilized to create an ideal RVFLN by determining the weights and biases of the hidden layer connections. The elitism method is used by AEFA to maximize its strength. Here, the most suitable entities are directly inserted to create the population of the following generation. By predicting the closing values of six widely used cryptocurrencies, including Bitcoin, Litecoin, Ethereum, ZEC, XLM, and Ripple, one may determine how well the eAEFA+RVFLN model is performing. For comparison study, models including ARIMA, multi-layer perceptron (MLP), basic RVFLN, support vector regression (SVR), LSTM, GA trained RVFLN, and AEFA trained RVFLN are also constructed concurrently. In terms of performance and statistical significance testing, the suggested eAEFA+RVFLN findings outperform the comparator models. On an average, it achieves a MAPE (mean absolute percentage of error) value of 0.0573, R 2 (coefficient of determination) of 0.9589, POCID (prediction of change in direction) of 0.9676, RMSE (root mean squared error) of 0.0685, MAE (mean absolute error) of 0.0727 and an average rank of 1.346; as a result, it is possible to recommend it as a useful financial forecasting tool.INDEX TERMS Cryptocurrency, bitcoin, random vector functional link network, financial time series forecasting, artificial neural network, AEFA.The associate editor coordinating the review of this manuscript and approving it for publication was Chun-Wei Tsai .

show abstract

Section: Related Studiesmentioning

confidence: 99%

“…The bigger initial value of K 0 helps in better exploration in the search process and gradually decreases through iterations to regulate the accuracy. The resultant electrostatic force F d i acting on i th particle at time t can be calculated as in Eq (24) and the electric field is calculated as in Eq (25).…”

Section: F Basic Aefamentioning

confidence: 99%

An Elitist Artificial Electric Field Algorithm Based Random Vector Functional Link Network for Cryptocurrency Prices Forecasting

et al. 2023

View full text Add to dashboard Cite

show abstract

“…There are more than 10,000 cryptocurrencies at present, as stated on the yahoo finance website. The complexity of price fluctuations, multiple market elements, and uncertainties, including the political and economic environments and investor behavior, might have been to the unpredictability of their price changes [24]. Additionally, cryptocurrency trading practices and hours differ from those of financial markets because, unlike financial markets, which have set trading hours, decentralized cryptocurrencies can be traded around the clock every day of the week.…”

Section: Literature Reviewmentioning

confidence: 99%

Predicting Top Five Cryptocurrency Prices via Linear Structural Time Series (STS) Approach

2023

View full text Add to dashboard Cite

Predicting cryptocurrency prices are difficult due to dynamic data. At the same time, the hidden market behavior of trend and seasonal components in the history data is also critical as it provides an idea of what the price pattern will be in the future. Hence, this research proposes to identify and model the hidden pattern behavior in terms of component time series instead of removing it via the linear structural time series (STS) model approach. This study focuses on the top five cryptocurrencies relying on the highest market capitalization. From the results obtained, the top five cryptocurrencies have a different trend model, either deterministic or stochastic, which relies on the behavior of data. The five cryptocurrencies also show the crypto winter event, where the trend is downward after six months every year. The linear STS is the best model for predicting three cryptocurrencies’ prices for nonstationary and volatility data behavior. It can also handle the hidden component behavior and is easy to interpret. Since the linear STS model can indirectly retain the information of data, it will assist investors and traders in accurately predicting cryptocurrency prices.

show abstract

“…Compared with traditional neural networks, rapid learning and a simple model structure are advantages of ELM, but the initial parameters have a significant impact on the prediction outcomes (Du et al, 2022). In An et al (2021), Zhang et al (2022), the performance of the ELM prediction is optimized using sparrow search algorithm (SSA) to lower the uncertainty caused by the input weights and thresholds.…”

Section: Introductionmentioning

confidence: 99%

Ultra-short-term PV power prediction using optimal ELM and improved variational mode decomposition

Wang

Lin

2023

Front. Energy Res.

View full text Add to dashboard Cite

The development of photovoltaic (PV) power forecast technology that is accurate is of utmost importance for ensuring the reliability and cost-effective functioning of the power system. However, meteorological factors make solar energy have strong intermittent and random fluctuation characteristics, which brings challenges to photovoltaic power prediction. This work proposes, a new ultra-short-term PV power prediction technology using an improved sparrow search algorithm (ISSA) to optimize the key parameters of variational mode decomposition (VMD) and extreme learning machine (ELM). ISSA’s global search capability is enhanced by levy flight and logical chaotic mapping to search the optimal number of decomposition and penalty factor of VMD, and VMD adaptively decomposes PV power into sub-sequences with different center frequencies. Then ISSA is used to optimize the initial weight and threshold of ELM to improve the prediction performance of ELM, the optimized ELM predicts each subsequence and reconstructs the prediction results of each component to obtain the final result. Furthermore, isolated forest (IF) and Spearman correlation coefficient (SCC) are respectively used in the data preprocessing stage to eliminate outliers in the original data and determine appropriate input features. The prediction results using the actual data of solar power plants show that the proposed model can effectively mine the key information in the historical data to make more accurate predictions, and has good robustness to various weather conditions.

show abstract

A New Hybrid Cryptocurrency Returns Forecasting Method Based on Multiscale Decomposition and an Optimized Extreme Learning Machine Using the Sparrow Search Algorithm

Cited by 8 publications

References 50 publications

An Elitist Artificial Electric Field Algorithm Based Random Vector Functional Link Network for Cryptocurrency Prices Forecasting

An Elitist Artificial Electric Field Algorithm Based Random Vector Functional Link Network for Cryptocurrency Prices Forecasting

Predicting Top Five Cryptocurrency Prices via Linear Structural Time Series (STS) Approach

Ultra-short-term PV power prediction using optimal ELM and improved variational mode decomposition

Contact Info

Product

Resources

About