A Novel Cryptocurrency Prediction Method Using Optimum CNN

Naseer, Atif; Baro, Enrique Nava; Khan, Sultan Daud; Vila, Y.; Doyle, Jennifer

doi:10.32604/cmc.2022.020823

Cited by 12 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Its purpose is to extract unique characteristics from grouped on-chain inputs. Hasan et al [9] suggested an approach that was optimized by employing CNN, and by modifying the parameters, they were able to produce extremely accurate results. When it comes to the prediction of time-series data, neural networks provide superior performance compared to the most advanced machine learning algorithms.…”

Section: B Related Workmentioning

confidence: 99%

Bitcoin Price Prediction Using Hybrid LSTM-GRU Models

Hussein,

Abdulazeez

2024

ijcs

View full text Add to dashboard Cite

Cryptocurrency price prediction is a challenging task due to the inherent volatility and complexity of the market. In this research, we propose a hybrid Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural network model for predicting Bitcoin prices. The model is implemented using the TensorFlow and Keras libraries and is evaluated on historical Bitcoin price data obtained from Yahoo Finance. Our approach aims to leverage the strengths of both LSTM and GRU architectures to enhance the accuracy of price predictions. The results suggest that the proposed hybrid LSTM-GRU model holds promise for effectively capturing the complex dynamics of cryptocurrency markets, addressing the challenges associated with traditional time-series analysis techniques.

show abstract

Section: B Related Workmentioning

confidence: 99%

Bitcoin Price Prediction Using Hybrid LSTM-GRU Models

Hussein,

Abdulazeez

2024

ijcs

View full text Add to dashboard Cite

show abstract

“…Fig. 4 The hidden layer LSTM memory cell structure [24] D. Convolutional Neural Networks It is well known that this model has been used to recognize patterns and features in photos, videos, and audio signals and that it did so with surprisingly excellent results [28]. In this study, 1D CNN models presented in Fig 5, where the data and kernels are one-dimensional vectors, were taken into consideration.…”

Section: Long Short-term Memory (Lstm)mentioning

confidence: 99%

“…5 Basic Convolutional Neural Networks Architecture [15] In order to learn hierarchical representations of the input data, CNNs make use of a number of essential components [27]. Beginning with one or more convolutional layers, CNNs conduct convolution to extract local features by sliding filters or kernels over the input data [28]. After each convolutional layer, activation functions, often ReLUs (Rectified Linear Units), induce nonlinearity.…”

Section: Long Short-term Memory (Lstm)mentioning

confidence: 99%

Evaluation of Cryptocurrency Price Prediction Using LSTM and CNNs Models

Wen,

Ling

2023

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

Cryptocurrencies created by Nakamoto in 2009 have gained significant interest due to their potential for high returns. However, the cryptocurrency market's unpredictability makes it challenging to forecast prices accurately. To tackle this issue, a deep learning model has been developed that utilizes Long Short-Term Memory (LSTM) neural networks and Convolutional Neural Networks (CNNs) to predict cryptocurrency prices. LSTMs, a type of recurrent neural network, are well-suited for analyzing time series data and have been successful in various prediction applications. Additionally, CNNs, primarily used for image analysis tasks, can be employed to extract relevant patterns and characteristics from input data in Bitcoin price prediction applications. This study contributes to the existing related works on cryptocurrency price prediction by exploring various predictive models and techniques, which involve a machine learning model, deep learning model, time series analysis, and as well as a hybrid model that combines deep learning methods to predict cryptocurrency prices as well as enhance the accuracy and reliability of the price predictions. To ensure accurate predictions in this study, a trustworthy dataset from investing.com was sought. The dataset, sourced from investing.com, consists of 1826 time series data samples. The dataset covers the time frame from January 1, 2018, to December 31, 2022, providing data for a period of 5 years. Subsequently, pre-processing was conducted on the dataset to guarantee the quality of the input. As a result of absent values and concerns regarding the dataset's obsolescence, an alternative dataset was sourced to avoid these issues. The performance of the LSTM and CNN models was evaluated using root mean squared error (RMSE), mean squared error (MSE), mean absolute error (MAE) and R-squared (R2). It was observed that they outperformed each other to a certain degree in short-term forecasts compared to long-term predictions, where the R2Â values for LSTM range from 0.973 to 0.986, while for CNNs, they range from 0.972 to 0.988 for 1 day, 3 days and 7 days windows length. Nevertheless, the LSTM model demonstrated the most favorable performance with the lowest error rate. The RMSE values for the LSTM model ranged from 1203.97 to 1645.36, whereas the RMSE values for the CNNs model ranged from 1107.77 to 1670.93. As a result, the LSTM model exhibited a lower error rate in RMSE and achieved the highest accuracy in R2Â compared to the CNNs model. Considering these comparative outcomes, the LSTM model can be deemed as the most suitable model for this specific case

show abstract

“…Although individuals often Tweet favorably about cryptocurrencies as their values fall, Twitter attitude research believes forthcoming price levels will become favorable. As a result of their volatile nature in the current market, predicting cryptocurrency values is a difficult endeavor [31].…”

Section: Digital Promotion and Cryptocurrency Data Analysismentioning

confidence: 99%

Digital Marketing Enhancement of Cryptocurrency Websites through Customer Innovative Data Process

et al. 2022

View full text Add to dashboard Cite

Today, more than ever, the popularity of decentralized payment systems has risen, creating an outbreak of new cryptocurrencies hitting the market. Unique websites have been staged for each cryptocurrency, where information and means for mining cryptocurrencies are available daily. People visit those cryptocurrency websites either from desktop or mobile devices. Thus, the impulsion for appropriate promotion of cryptocurrency websites and customer factors affecting it rises. The above process increases cryptocurrency organizations’ website visibility, raising the need for customer relationships and satisfaction optimization concerning organizations’ supply chain strategy. Research data were collected from 10 well-known cryptocurrency websites, regarding mobile and desktop devices, in 180 days, regarding on-site web analytics. Therefore, a model consisting of three stages was applied. Starting phase of the model pertains to statistical and regression analysis of cryptocurrency web analytics, followed by Fuzzy Cognitive Mapping and Agent-Based Model deployment. Throughout this study, methods for promoting cryptocurrency websites can be deduced from assessing specific website metrics and device preferences. Research results indicate that web analytics give a clearer image of customer behavior in cryptocurrency websites and, therefore, provide opportunities for further website optimization through increased web traffic and digital reputation.

show abstract

A Novel Cryptocurrency Prediction Method Using Optimum CNN

Cited by 12 publications

References 26 publications

Bitcoin Price Prediction Using Hybrid LSTM-GRU Models

Bitcoin Price Prediction Using Hybrid LSTM-GRU Models

Evaluation of Cryptocurrency Price Prediction Using LSTM and CNNs Models

Digital Marketing Enhancement of Cryptocurrency Websites through Customer Innovative Data Process

Contact Info

Product

Resources

About