Correction to: Prediction accuracy improvement for Bitcoin market prices based on symmetric volatility information using artificial neural network approach

Othman, Anwar Hasan Abdullah; Kassim, Salina; Rosman, Romzie; Redzuan, Nur Harena

doi:10.1057/s41272-020-00240-8

Cited by 5 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In 2020, Othman et al (2020) have introduced a BTC currency's symmetric volatility structure for price future trend prediction using four input attributes "open price (OP), high price (HP), low price (LP), and close price (CP)". Based on the ANN algorithm, this used the Rapid-Miner program.…”

Section: Literature Review 21 Related Workmentioning

confidence: 99%

“…Table 1 summarizes the characteristics and problems of these projects. Only works with little amounts of data (Othman et al, 2020). The prediction accuracy is modest, and it is only useful for data with a low frequency (Chen et al, 2020a).…”

Section: Problem Statementmentioning

confidence: 99%

“…At such an exponential rate, the world's economy and financial infrastructures are now becoming digitized. As per the recent projection, "the digital economy would be worth 25% (23 trillion USD) in 2025, comprising of both tangible and intangible digital assets" (Othman et al, 2020). The bitcoin (BTC) market blew up the previous decade.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A two level ensemble classification approach to forecast bitcoin prices

Kundra

Sharma²,

Nancy³

et al. 2022

View full text Add to dashboard Cite

PurposeBitcoin has indeed been universally acknowledged as an investment asset in recent decades, after the boom-and-bust of cryptocurrency values. Because of its extreme volatility, it requires accurate forecasts to build economic decisions. Although prior research has utilized machine learning to improve Bitcoin price prediction accuracy, few have looked into the plausibility of using multiple modeling approaches on datasets containing varying data types and volumetric attributes. Thus, this paper aims to propose a bitcoin price prediction model.Design/methodology/approachIn this research work, a bitcoin price prediction model is introduced by following three major phases: Data collection, feature extraction and price prediction. Initially, the collected Bitcoin time-series data will be preprocessed and the original features will be extracted. To make this work good-fit with a high level of accuracy, we have been extracting the second order technical indicator based features like average true range (ATR), modified-exponential moving average (M-EMA), relative strength index and rate of change and proposed decomposed inter-day difference. Subsequently, these extracted features along with the original features will be subjected to prediction phase, where the prediction of bitcoin price value is attained precisely from the constructed two-level ensemble classifier. The two-level ensemble classifier will be the amalgamation of two fabulous classifiers: optimized convolutional neural network (CNN) and bidirectional long/short-term memory (BiLSTM). To cope up with the volatility characteristics of bitcoin prices, it is planned to fine-tune the weight parameter of CNN by a new hybrid optimization model. The proposed hybrid optimization model referred as black widow updated rain optimization (BWURO) model will be conceptual blended of rain optimization algorithm and black widow optimization algorithm.FindingsThe proposed work is compared over the existing models in terms of convergence, MAE, MAPE, MARE, MSE, MSPE, MRSE, Root Mean Square Error (RMSE), RMSPE and RMSRE, respectively. These evaluations have been conducted for both algorithmic performance as well as classifier performance. At LP = 50, the MAE of the proposed work is 0.023372, which is 59.8%, 72.2%, 62.14% and 64.08% better than BWURO + Bi-LSTM, CNN + BWURO, NN + BWURO and SVM + BWURO, respectively.Originality/valueIn this research work, a new modified EMA feature is extracted, which makes the bitcoin price prediction more efficient. In this research work, a two-level ensemble classifier is constructed in the price prediction phase by blending the Bi-LSTM and optimized CNN, respectively. To deal with the volatility of bitcoin values, a novel hybrid optimization model is used to fine-tune the weight parameter of CNN.

show abstract

Section: Literature Review 21 Related Workmentioning

confidence: 99%

Section: Problem Statementmentioning

confidence: 99%

See 1 more Smart Citation

A two level ensemble classification approach to forecast bitcoin prices

Kundra

Sharma²,

Nancy³

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Artificial neural network is a non-linear, selforganizing and adaptive system, which includes a number of units. It has a research hotspot that has emerged in the field of artificial intelligence since the 1980s, trying to simulate the way neural networks process and remember information and design a new machine with human brain-style information processing capabilities [27,28].…”

Section: Basic Principlesmentioning

confidence: 99%

Application of Artificial Neural Networks for Chemical Industry Safety Production: A Review

Liu

2022

JERR

View full text Add to dashboard Cite

Chemical industry as a national pillar industry, safety management is particularly important; Safety assessment is the use of relevant technologies to assess the risks in the production process of a company. The key is the selection of evaluation methods and means, which can directly influence the effect of the evaluation. However, since the object of chemical safety production evaluation is influenced by many factors, it is concerned with a non-linear relationship between cause and effect. Artificial neural network can make use of the threshold value between neuron nodes and the connection weight value between nodes based on artificial function to carry out non-linear mapping input and output in advance, which has obvious advantages in dealing with non-linear complex problems.

show abstract

“…On the one hand, if the number of hidden layers and/or hidden neurons is too high, there is a risk of overfitting; on the other hand, if their number is too small, it will cause inappropriateness. Generally, the best ANN algorithm configuration can be defined by comparing the average RMSEs of the test set during cross-validation or sensitivity testing [42].…”

Section: Algorithmic Structure Of a Typical Artificial Neural Network (Ann)mentioning

confidence: 99%

Research Progress in the Application of Artificial Neural Networks in Catalyst Optimization

Liu

Zhou

2021

AJOCS

View full text Add to dashboard Cite

The catalyst can speed up the chemical reaction and increase the selectivity of the target product, playing an important role in the chemical industry. By improving the performance of the catalyst, the economic benefits can be greatly improved. Artificial Neural Network (ANN), as one of the most popular machine learning algorithms, has parallel processing and self-learning capabilities as well as good fault tolerance, and has been widely used in various fields. By optimizing the catalyst through ANN, time and resource consumption can be greatly reduced, and greater economic benefits can be obtained. This article reviews how CNN technology can help people solve highly complex problems and accelerate progress in the catalytic world.

show abstract

Correction to: Prediction accuracy improvement for Bitcoin market prices based on symmetric volatility information using artificial neural network approach

Cited by 5 publications

References 0 publications

A two level ensemble classification approach to forecast bitcoin prices

A two level ensemble classification approach to forecast bitcoin prices

Application of Artificial Neural Networks for Chemical Industry Safety Production: A Review

Research Progress in the Application of Artificial Neural Networks in Catalyst Optimization

Contact Info

Product

Resources

About