data

Article
Cryptocurrency Price Prediction with Convolutional Neural
Network and Stacked Gated Recurrent Unit
Chuen Yik Kang, Chin Poo Lee * and Kian Ming Lim

Faculty of Information Science and Technology, Multimedia University, Melaka 75450, Malaysia
* Correspondence: cplee@mmu.edu.my

Abstract: Virtual currencies have been declared as one of the financial assets that are widely rec-
ognized as exchange currencies. The cryptocurrency trades caught the attention of investors as
cryptocurrencies can be considered as highly profitable investments. To optimize the profit of the
cryptocurrency investments, accurate price prediction is essential. In view of the fact that the price
prediction is a time series task, a hybrid deep learning model is proposed to predict the future price
of the cryptocurrency. The hybrid model integrates a 1-dimensional convolutional neural network
and stacked gated recurrent unit (1DCNN-GRU). Given the cryptocurrency price data over the time,
the 1-dimensional convolutional neural network encodes the data into a high-level discriminative
representation. Subsequently, the stacked gated recurrent unit captures the long-range dependencies
of the representation. The proposed hybrid model was evaluated on three different cryptocurrency
datasets, namely Bitcoin, Ethereum, and Ripple. Experimental results demonstrated that the proposed
1DCNN-GRU model outperformed the existing methods with the lowest RMSE values of 43.933 on
the Bitcoin dataset, 3.511 on the Ethereum dataset, and 0.00128 on the Ripple dataset.

Keywords: cryptocurrency price prediction; price prediction; convolutional neural network; gated
recurrent unit; CNN; GRU; Bitcoin; Ethereum; Ripple
Citation: Kang, C.Y.; Lee, C.P.; Lim,
K.M. Cryptocurrency Price
Prediction with Convolutional
Neural Network and Stacked Gated 1. Introduction
Recurrent Unit. Data 2022, 7, 149. Cryptocurrencies serve as a peer-to-peer digital currency where every detailed transaction
https://doi.org/10.3390/ occurs in a secured way. The transactions are further stored in a block, known as Blockchain.
data7110149 The security features made cryptocurrency a popular and well-known trading platform for
Academic Editor: Francisco Guijarro
investors. Cryptocurrencies have been growing dramatically, gaining popularity and capitaliza-
tion. Bitcoin is the first decentralized cryptocurrency developed by Satoshi Nakamoto [1], and
Received: 19 June 2022 it has become the world’s most valuable cryptocurrency. With the vast transaction volume of
Accepted: 15 September 2022 cryptocurrencies, many types of currencies were introduced into the cryptography world. Some
Published: 31 October 2022
well-known cryptocurrencies are Ethereum and Ripple, among others.
Publisher’s Note: MDPI stays neutral This study focuses on cryptocurrency price prediction. The cryptocurrency price
with regard to jurisdictional claims in prediction is a time series problem that can be solved by using deep learning regres-
published maps and institutional affil- sion techniques. Although price prediction of cryptocurrency is challenging, developing
iations. cryptocurrency price prediction algorithms is worthwhile because it plays a vital role
for cryptocurrency traders. Inspired by the success of deep learning regression models
in a wide spectrum of applications, this paper proposes a hybrid regression model that
amalgamates a 1-dimensional convolutional neural network (1DCNN) and a stacked gated
Copyright: © 2022 by the authors. recurrent unit (GRU), into the 1DCNN-GRU model for cryptocurrency price prediction.
Licensee MDPI, Basel, Switzerland.
Three cryptocurrency historical price datasets are first collected from the cryptocurrency
This article is an open access article
exchange website. Subsequently, the datasets are subjected to some data pre-processing,
distributed under the terms and
including normalization and missing value removal before passing into the 1DCNN-GRU
conditions of the Creative Commons
model for representation learning and price prediction. The 1DCNN layer plays the role of
Attribution (CC BY) license (https://
extracting the salient features in the historical price data. The extracted features are then
creativecommons.org/licenses/by/
4.0/).
passed into the stacked GRU for temporal encoding where the long-range dependencies are

Data 2022, 7, 149. https://doi.org/10.3390/data7110149 https://www.mdpi.com/journal/data

Data 2022, 7, 149 2 of 13

captured. The temporal encoding is then leveraged for the cryptocurrency price prediction.
The predicted price is compared against the real price and the root mean square error is
computed. The main contributions of this paper are as follows.
• The cryptocurrency historical price data are acquired from the cryptocurrency exchange
website. As the daily or hourly interval data are susceptible to information loss, this
study leverages the one-minute interval data for more accurate price prediction.
• The feature scaling is performed on the cryptocurrency historical price data by nor-
malization. In addition, the data is further pre-processed to remove the missing values
that might affect model learning. The clean data are then partitioned into the training
set and testing set for model learning and price prediction.
• A hybrid 1DCNN-GRU model is proposed for representation learning and cryp-
tocurrency price prediction. The 1DCNN model encodes the prominent patterns in
the historical price data, hence producing discriminative features to represent the
historical price data. Thereafter, the stacked GRU model captures the long-range
dependencies in the features, thus alleviating the gradient vanishing problems.

2. Related Works
This section describes some existing works in cryptocurrency price prediction. There
are many deep learning models that are adopted for price prediction [2–14].
In early work, Sin et al. (2017) [15] proposed a forecasting algorithm that can be
applied to different financial, engineering, and medical tasks. The algorithm integrated an
artificial neural network (ANN) and a multilayer perceptron (MLP). From the experiments,
the incorporation of MLP into ANN increased the Bitcoin price prediction accuracy from
about 58% to 63%.
A deep learning algorithm, known as the Facebook Prophet for Bitcoin price prediction
was adopted by Yenidogan et al. (2018) [16]. A three-fold splitting technique was conducted
to provide optimum ratios for training, testing, and validation sets. The experimental results
showed that the PROPHET algorithm outperformed the ARIMA algorithm, in which
Prophet obtained a lower root mean square error (RMSE) of 652.18 compared to 817.01.
McNally et al. (2018) [17] leveraged several deep learning algorithms to predict the
price of Bitcoin. In the early process, functional patterns were extracted from the data
by feature engineering. The experimental results demonstrated that the long short-term
memory (LSTM) model achieved the highest accuracy of 52.78% while recurrent neural
networks (RNN) achieved the lowest accuracy of 5.45%.
Various regression techniques were presented by Phaladisailoed et al. (2018) [18]
to predict Bitcoin prices by using Keras libraries and scikit-learn. The dataset was taken
from Kaggle where it consists of one-minute interval data on the Bitcoin exchange website
Bitstamp. The best results showed that R-Square of 99.2% was obtained by the LSTM and
GRU models.
Jiang (2020) [19] proposed deep learning methods to forecast Bitcoin prices by gath-
ering and reorganizing data on the Bitcoin price per minute to hours. The dataset was
pre-processed, followed by mini-batch and min-max normalization before feeding it into
the regression models. The work proposed a few deep learning networks such as MLP,
RNN with the extension of LSTM, and GRU to predict future Bitcoin price. The experi-
mental results showed that the MLP model, with the involvement of two layers of GRU
achieved the best result, which had the minimal RMSE of 19.020.
Politis et al. (2021) [20] leveraged multiple deep learning models for predicting the
price of Ethereum. Feature selection was performed to reduce the dataset complexity and
anomalies. The ensemble model was implemented with the combination of LSTM, GRU
and/or temporal convolutional networks (TCN). In the daily forecast experimental result,
the ensemble model with LSTM, GRU, and Hybrid GRU-TCN had the best performance of
84.2% accuracy, whereas the LSTM-GRU model achieved the lowest RMSE of 8.6.
Another LSTM-GRU hybrid model was put forth by Tanwar et al. (2021) [21] for
cryptocurrency price prediction. The work considered Bitcoin as the parent currency
Data 2022, 7, 149 3 of 13

and captured the movement direction of Bitcoin price. Subsequently, the movement
direction was utilized to predict the price of Litecoin and Zcash with the inter-dependency
assumptions between Bitcoin-Litecoin and Bitcoin-Zcash. With a one-day window size,
the LSTM-GRU model recorded a mean squared error (MSE) of 0.02038 for Litecoin and
0.00461 for Zcash.
Livieris et al. (2021) [22] proposed a multiple-input cryptocurrency deep learning
model, also known as MICDL. The proposed approach utilized each cryptocurrency data as
input in a convolutional layer, followed by a pooling layer and an LSTM layer. The classical
structure of a deep learning neural network, such as a dense layer, batch normalization
layer, dropout layer, and output layer were leveraged. The proposed CNN with an LSTM
layer achieved 55.03% accuracy on the Bitcoin data, whereas accuracy of 51.51% was
obtained for Ethereum data and 49.61% for Ripple data.
Zhang et al. (2021) [23] presented a weighted and attentive memory convolutional
neural network (WAMC) for cryptocurrency price prediction. The model consists of a
GRU to establish the attentive memory for each input sequence, a channel-wise weighting
module to learn the interdependencies among several cryptocurrencies, and a CNN to
extract local temporal features of the historical price data. The proposed WAMC recorded
an RMSE of 9.70 for Ethereum and 1.37 for Bitcoin.
Jay et al. (2020) [24] devised stochastic neural networks for the price prediction of
Bitcoin, Ethereum, and Litecoin. The work considered three factors, namely cryptocurrency
exchange market statistics, blockchain data, and social sentiment as the neural networks’
input. In order to address the randomness in the factors, the stochastic layers were in-
corporated into the MLP and LSTM model. In comparison to the deterministic MLP and
LSTM, the stochastic neural networks (MLP and LSTM) showed an average improvement
of 4.84833% for Bitcoin, 4.15640% for Ethereum, and 4.74619% for Litecoin.
The price prediction of the same cryptocurrencies were performed by Sebastiao et al.
(2021) [25]. The authors devised a few machine learning models, including linear models,
random forest, and support vector machine to examine the predictability of the cryp-
tocurrencies. The experimental results showed that the best results were achieved by the
ensemble of linear models, random forest, and support vector machine on Ethereum prices,
which was at 63.33% of win rates of the strategies. In another way, linear models achieved
optimal RMSEs on forecasting Ethereum and Litecoin prices, which were only 6.85 and
8.14, whereas random forest achieved an RMSE of 5.77 on forecasting Bitcoin prices.
Saadah et al. (2020) [26] applied several machine learning and deep learning methods
for predicting the price of Bitcoin, Ethereum, and Ripple. The methods include k-nearest
neighbors, support vector machine, and LSTM. The experimental results demonstrated
that the LSTM achieved the optimal RMSE for all three cryptocurrencies, with RMSE of
928.62 on Bitcoin, 11.69 on Ethereum, and 0.16 on Ripple.
Derbentsev et al. (2020) [27] implemented machine learning approaches, namely
random forest and gradient boosting machine to forecast cryptocurrency prices. Three
cryptocurrencies were used, i.e., Bitcoin, Ethereum, and Ripple. The experiments showed
that gradient boosting machine is able to better forecast the price compared to random forest,
in which RMSE of 263.34 was obtained on Bitcoin, 5.02 on Ethereum, and 0.92 on Ripple.
The summary of the existing works is presented in Table 1. Many existing works
leveraged LSTM for price prediction, attributable to its gating mechanism that is able to
capture the sequential and temporal information in the data. However, there might be
noise or outliers in the raw historical price data; thus, this work first performs feature
extraction by using 1DCNN to capture the salient features and suppress the noise in the
data. Subsequently, GRU is leveraged to encode the long-range temporal information in the
features. The details of the proposed hybrid model with 1DCNN and GRU are discussed in
the next section.
Data 2022, 7, 149 4 of 13

Table 1. Summary of related works.

Paper Best Method Dataset Results (Metric)

Sin et al. (2017) [15] ANN + MLP Bitcoin 63% (Accuracy)
Yenidogan et al. (2018) [16] Facebook Prophet Bitcoin 652.18 (RMSE)
McNally et al. (2018) [17] LSTM Bitcoin 52.78% (Accuracy)
Phaladisailoed et al. (2018) [18] LSTM, GRU Bitcoin 99.2% (R-Square)
Jiang (2020) [19] MLP + GRU Bitcoin 19.020 (RMSE)
Politis et al. (2021) [20] LSTM-GRU Bitcoin 8.6 (RMSE)
Litecoin 0.02038 (MSE)
Tanwar et al. (2021) [21] LSTM-GRU
Zcash 0.00461 (MSE)
Bitcoin 55.03% (Accuracy)
Livieris et al. (2021) [22] CNN + LSTM Ethereum 51.51% (Accuracy)
Ripple 49.61% (Accuracy)
Ethereum 9.70 (RMSE)
Zhang et al. (2021) [23] WAMC
Bitcoin 1.37 (RMSE)
Jay et al. (2020) [24] Stochastic Neural Networks Bitcoin 4.84833% (Improvement)
Ethereum 4.15640% (Improvement)
Litecoin 4.74619% (Improvement)
Ethereum 6.85 (RMSE)
Linear Models
Sebastiao et al. (2021) [25] Litecoin 8.14 (RMSE)
Random Forest Bitcoin 5.77 (RMSE)
Bitcoin 928.62 (RMSE)
Saadah et al. (2020) [26] LSTM Ethereum 11.69 (RMSE)
Ripple 0.16 (RMSE)
Bitcoin 263.34 (RMSE)
Derbentsev et al. (2020) [27] Gradient Boosting Machine Ethereum 5.02 (RMSE)
Ripple 0.92 (RMSE)

3. Cryptocurrency Price Prediction with 1-Dimensional Convolutional Neural

Network and Stacked Gated Recurrent Unit (1DCNN-GRU)
This section details the proposed 1DCNN-GRU model for cryptocurrency price predic-
tion. The historical price data of three cryptocurrencies are first acquired, namely Bitcoin,
Ethereum, and Ripple. Subsequently, the collected data are pre-processed to clean missing
values. Thereafter, the cleaned data are fed into the hybrid 1DCNN-GRU model for model
learning and price prediction. Figure 1 illustrates the process flow of the cryptocurrency
price prediction.

Figure 1. The process flow of the cryptocurrency price prediction.

3.1. Data Acquisition

Three datasets were used for the cryptocurrency price prediction, namely Bitcoin,
Ethereum, and Ripple.
The Bitcoin historical data [28] were acquired from the Kaggle website. The provided
one-minute interval data range from 1 January 2012 until 31 March 2021, which contain
approximately 4.8 millions samples, including NaN values. Some columns in the data are
open, high, low, close (OHLC) price, volume, and the weighted price. All the timestamps
are in UNIX time. The NaN values indicate that no trade or activity happened at that time.
Figure 2 visualizes the Bitcoin closing price for the years 2012 to 2021.
The Ethereum historical data were collected from the Bitstamp exchange website.
The data comprise around 396,403 samples at one-minute intervals. The Ethereum closing
price of the year 2021 is shown in Figure 3.
Data 2022, 7, 149 5 of 13

Ripple is another widely known cryptocurrency, which has slightly lower values
compared to other cryptocurrencies. The Ripple historical data were also gathered from
the Bitstamp exchange website. The historical data consist of around 396,403 samples,
as displayed in Figure 4.

Figure 2. The historical price of Bitcoin (2012–2021).

Figure 3. The historical price of Ethereum (2021).

Figure 4. The historical price of Ripple (2021).

3.2. Data Pre-Processing

Some pre-processing steps are performed to clean the cryptocurrency historical data,
including feature selection, timestamp conversion, missing values removal, train-test split,
and min-max scaling normalization.
As each dataset consists of many features, this work only utilizes three features for
price prediction, namely timestamp, date, and closing price. Subsequently, timestamp
conversion is carried out where the timestamp in UNIX is converted into the YY:MM:DD
Data 2022, 7, 149 6 of 13

date format. The zeros and NaNs are filtered out by dropping the associated rows. To avoid
huge data losses and to provide more timely and detailed prediction, the samples are
taken at one-min intervals. Due to the inconsistency of historical data and high sampling
rates, the historical data of one week are used. With these settings, the number of samples
is 10,797 for Bitcoin and 10,834 for both Ethereum and Ripple. The samples are further
partitioned into six days for the training set and one day for the testing set. Apart from
that, the features are subjected to min-max scaling normalization that transforms each
feature into the range [0, 1]. The min-max scaling suppresses the effects of outliers while
preserving the relationships among the data values. The min-max scaling is computed as

x − min( x )
xnorm = . (1)
max( x ) − min( x )

3.3. 1-Dimensional Convolutional Neural Network and Gated Recurrent Unit

In this work, a hybrid model that integrates 1DCNN and GRU is proposed for cryp-
tocurrency price prediction. The architecture of the proposed 1DCNN-GRU model is
depicted in Figure 5. The proposed 1DCNN-GRU comprises a 1D convolutional layer and
two GRU layers with 256 units each.

Figure 5. The architecture of the proposed 1DCNN-GRU model.

The cryptocurrency historical price is a kind of time series data that captures the
closing price over the time. Using the raw price data as the input might introduce noise
and outliers, causing the regression model to learn on the insignificant data. Therefore,
a 1DCNN is leveraged to extract the prominent patterns from the historical price data.
In the 1-dimensional convolutional layer (Conv1D), the kernel slides along the temporal
axis and encodes the price data into representative features. The Conv1D layer in the
proposed model sets both kernel size and stride to 1; hence the convolution window will
read one time step at one time. The Conv1D layer consists of 256 output filters in the
convolution, thus producing 256-dimensional output space. The output of the Conv1D
layer is passed into the subsequent GRU layer.
Two GRU layers are leveraged to encode the long-term dependencies of the extracted
features. The ability of capturing long-term dependencies in GRU is attributable to the
gating mechanisms. There are two gates in the GRU, namely update gate and reset gate.
The update gate zt at time step t determines the information from the previous time steps
to be passed to the future, defined as
 
z t = σ W ( z ) x t + U ( z ) h t −1 , (2)

where the weights W (z) and U (z) are multiplied with the input xt and hidden states ht−1 ,
respectively. The results of the multiplication are summed and passed into a sigmoid
activation function to squash the values between 0 and 1.
The reset gate rt determines the past information to forget, where the computation is
defined as  
r t = σ W (r ) x t + U (r ) h t −1 , (3)
Data 2022, 7, 149 7 of 13

where the input xt and hidden states ht−1 are multiplied with their corresponding weights
W (r) and U (r) . The sum of the results is likewise fed into a sigmoid activation function to
limit the output to the range between 0 and 1.
A new memory content h0t is then leveraged to store past information, defined as

h0t = tanh(Wxt + rt Uht−1 ), (4)

where denotes the element-wise product. The new memory content is determined by
first multiplying the input xt and hidden states ht−1 with the corresponding weights W
and U. Thereafter, the element-wise product of the reset gate rt and Uht−1 is calculated.
The product operation diminishes the information from the previous time step when the
values of rt close to 0. Then, the sum of Wxt and rt Uht−1 is regulated by a tanh function
to keep the output within −1 and 1.
Following that, the final memory at the current time step ht that determines the
information to be passed to the next time step is calculated as

ht = zt h t −1 + (1 − z t ) h0t . (5)

Having zt values close to 1 will retain the majority of the previous information, whereas
zt values close to 0 will keep the most part of the current information.
Lastly, the output from the GRU layers is passed into a dense layer with one hidden
unit for price prediction. The layer-wise architecture of the proposed 1DCNN-GRU is
presented in Table 2.

Table 2. The layer-wise architecture of the proposed 1DCNN-GRU model.

Layer Configurations
Conv1D Layer filters = 256, kernel_size = 1, strides = 1
GRU Layer units = 256
GRU Layer units = 256
Dense Layer units = 1

4. Hyperparameter Tuning
A hyperparameter tuning by grid search is performed to determine the optimal
settings of the 1DCNN-GRU model. The hyperparameters that are involved in the hyper-
parameter tuning are optimizer, activation function, and batch size. The optimizers play
the role of optimizing the model learning process to ensure the model converges optimally.
In this work, four optimizers are considered, namely Adam, SGD, Adamax, and RMSProp.
The activation function is the function in the Conv1D layer and GRU layers that transforms
the input, enabling the model to learn and perform more complex tasks. Five activation
functions are explored, which are sigmoid, softmax, ReLU, tanh, and linear. The batch size
defines the number of samples that is used for error gradient computation in each model
weights update. The RMSE is adopted as the evaluation metric of the cryptocurrency price
prediction models. The RMSE is the square root of the average squared distance between
actual and predicted values, defined as
s
n
1
RMSE =
n ∑ (yi − ybi )2 , (6)
i =1

where n is the total number of predictions, y is the real price, and yb denotes the predicted
price. The optimal settings are set to the hyperparameter values with the lowest RMSE.
Table 3 shows the experimental results of different hyperparameter values on the
Bitcoin dataset. The lowest RMSE of 43.933 is obtained on the Bitcoin dataset when SGD
optimizer, sigmoid activation function, and batch size of 16 are used. The experimental
results on the Ethereum dataset are presented in Table 4. It is observed that the lowest RMSE
Data 2022, 7, 149 8 of 13

of 3.511 is achieved with the Adamax optimizer, softmax activation function, and batch size
of 32. As for the Ripple dataset, the lowest RMSE of 0.00128 is recorded when the Adam
optimizer, softmax activation function, and batch size of 32 are set, as shown in Table 5.
The experimental settings are given in Table 6.

Table 3. RMSE of 1DCNN-GRU with different hyperparameters on the Bitcoin dataset.

Hyperparameter Batch Size

Optimizer Activation 16 32 64 128
sigmoid 48.791 44.548 44.369 45.104
softmax 44.085 44.260 44.056 44.025
Adam relu 44.250 44.445 44.050 44.170
tanh 44.897 44.121 44.185 45.254
linear 44.013 44.221 44.517 44.094
sigmoid 43.933 43.962 43.987 43.961
softmax - - - -
SGD relu 44.045 44.395 44.211 44.167
tanh 44.029 44.029 44.015 44.003
linear 44.031 44.033 44.031 44.029
sigmoid 44.434 44.898 44.105 44.562
softmax 44.516 43.974 44.207 43.978
Adamax relu 44.162 44.145 44.120 44.750
tanh 44.147 44.843 44.527 44.074
linear 46.624 45.204 44.515 44.048
sigmoid 49.824 44.495 47.559 44.995
softmax 44.003 44.221 44.846 44.687
RMSprop relu 45.688 44.404 51.833 44.768
tanh 44.854 44.940 44.353 44.812
linear 44.620 44.131 44.108 44.182

Table 4. RMSE of 1DCNN-GRU with different hyperparameters on the Ethereum dataset.

Hyperparameter Batch Size

Optimizer Activation 16 32 64 128
sigmoid 3.807 3.617 3.556 3.576
softmax 3.521 3.518 3.524 3.515
Adam relu 3.583 3.528 3.669 3.518
tanh 3.729 3.529 3.579 3.556
linear 3.515 3.559 3.519 3.677
sigmoid 3.528 3.524 3.516 3.514
softmax - - - -
SGD relu 3.523 3.517 3.515 3.515
tanh 3.518 3.515 3.516 3.516
linear 3.515 3.515 3.516 3.515
sigmoid 4.245 3.516 3.709 3.519
softmax 3.526 3.511 3.515 3.514
Adamax relu 3.546 3.624 3.609 3.516
tanh 3.531 3.567 3.525 3.523
linear 3.513 3.520 3.557 3.534
sigmoid 4.362 3.565 3.591 3.586
softmax 3.517 3.580 3.717 3.592
RMSprop relu 3.636 3.630 3.515 3.534
tanh 3.630 3.820 3.822 3.529
linear 3.545 3.569 3.573 3.560
Data 2022, 7, 149 9 of 13

Table 5. RMSE of 1DCNN-GRU with different hyperparameters on the Ripple dataset.

Hyperparameter Batch Size

Optimizer Activation 16 32 64 128
sigmoid 0.00132 0.00129 0.00129 0.00132
softmax 0.00129 0.00128 0.00129 0.00129
Adam relu 0.00131 0.00129 0.00131 0.00129
tanh 0.00132 0.00129 0.00129 0.00129
linear 0.00129 0.00130 0.00129 0.00129
sigmoid 0.01189 0.00129 0.00129 0.00129
softmax - - - -
SGD relu 0.00129 0.00129 0.00129 0.00129
tanh 0.00129 0.00129 0.00129 0.00129
linear 0.00129 0.00129 0.00129 0.00129
sigmoid 0.00129 0.00133 0.00130 0.00129
softmax 0.00132 0.00130 0.00129 0.00129
Adamax relu 0.00133 0.00129 0.00129 0.00129
tanh 0.00129 0.00129 0.00129 0.00129
linear 0.00144 0.00129 0.00130 0.00129
sigmoid 0.00131 0.00130 0.00134 0.00145
softmax 0.00129 0.00129 0.00129 0. 00131
RMSprop relu 0.00134 0.00133 0.00129 0.00135
tanh 0.00130 0.00130 0.00129 0.00139
linear 0.00133 0.00131 0.00130 0.00134

Table 6. The experimental settings of the proposed 1DCNN-GRU model.

Dataset/Hyperparameter Configurations
Bitcoin optimizer = SGD, activation function = sigmoid, batch size = 16
Ethereum optimizer = Adamax, activation function = softmax, batch size = 32
Ripple optimizer = Adam, activation function = softmax, batch size = 32
Learning Rate 0.001
Training Epoch 150

5. Experimental Results and Analysis

In this section, the performance of the proposed 1DCNN-GRU model is compared
with the existing prediction models. All models are trained on the same one-minute interval
historical data.
Table 7 presents the comparison results of the methods on Bitcoin, Ethereum, and Rip-
ple datasets. In general, the RMSE of all methods on the Bitcoin dataset is the highest,
followed by the Ethereum dataset, and the Ripple dataset yields the lowest RMSE. This is
due to the difference in the price where higher prices tend to result in higher RMSE.
The experimental results show that the proposed 1DCNN-GRU outshines the methods
in comparison. The proposed 1DCNN-GRU model records an RMSE of 43.933 on the Bitcoin
dataset, 3.511 on the Ethereum dataset, and 0.00128 on the Ripple dataset. Compared
to the GRU model [19] alone, adding 1DCNN has reduced the RMSE on all datasets.
This is attributable to 1DCNN that is able to learn local relationships and encode the
cryptocurrency historical data into discriminative features. In doing so, the noise, outliers
and insignificant data in the input are suppressed.
Apart from that, the proposed 1DCNN-GRU also showed much improvement in
relation to the CNN-LSTM model [22]. The RMSE has reduced from 47.537 to 43.933
on the Bitcoin dataset, from 3.516 to 3.511 on the Ethereum dataset, and from 0.00135
to 0.00128 on the Ripple dataset. Both LSTM and GRU have their own strengths and
perform well in different applications in which they utilize gating mechanisms to retain the
historical information. In this application, the improvement corroborates the effectiveness
Data 2022, 7, 149 10 of 13

of stacked GRU in capturing the long-range dependencies of the features, thus alleviating
the vanishing gradient problems. The real and predicted prices of the Bitcoin, Ethereum,
and Ripple are illustrated in Figures 6–8, respectively.

Table 7. Experimental results on Bitcoin, Ethereum, and Ripple datasets.

Root Mean Square Error (RMSE)

Method
Bitcoin Ethereum Ripple
ARIMA [17] 43.954 3.516 0.00129
Simple RNN [17] 44.003 3.517 0.00129
Facebook Prophet 805.169 157.046 0.05733
GRU [19] 43.998 3.512 0.00129
LSTM [26] 45.687 3.636 0.00130
CNN-LSTM [22] 47.537 3.516 0.00135
Bidirectional LSTM [22] 332.886 43.414 0.01499
XGBoost [29] 1477.181 101.361 0.01652
1DCNN-GRU (Proposed) 43.933 3.511 0.00128

Figure 6. The price prediction by 1DCNN-GRU model on the Bitcoin dataset.

Figure 7. The price prediction by 1DCNN-GRU model on the Ethereum dataset.

Data 2022, 7, 149 11 of 13

Figure 8. The price prediction by 1DCNN-GRU model on the Ripple dataset.

6. Conclusions
This paper presents a hybrid deep learning model that harnesses the strengths of
1DCNN and stacked GRU for cryptocurrency price prediction. The historical price of three
cryptocurrencies are acquired, namely Bitcoin, Ethereum, and Ripple. The collected data
are normalized and pre-processed to remove the missing values. Subsequently, the pre-
processed data are passed into the hybrid 1DCNN-GRU model. The 1DCNN model
transforms the price data into a discriminative representation that captures the significant
patterns in the price data. Subsequently, the stacked GRU model encodes the long-range
dependencies in the representation to mitigate past information loss problems. The gating
mechanism of GRU determines the past and current information to be updated and reset,
thus alleviating diminishing gradient problems. The experimental results demonstrate that
the proposed 1DCNN-GRU outperforms the methods in comparison with the lowest RMSE
values of 43.933 on the Bitcoin dataset, 3.511 on the Ethereum dataset, and 0.00128 on the
Ripple dataset.
As a proof of concept and due to the limitations in computing resources, this study
only utilizes the historical data for one week. Training the model on the cryptocurrency
data for a longer time span should be able to further improve the generalization capability
of the model. In addition to the closing price, other factors such as the seasonality trends,
government policies and laws, social media, can also be considered as the input for price
prediction model.

Author Contributions: Conceptualization, C.Y.K. and C.P.L.; methodology, C.Y.K. and C.P.L.; soft-
ware, C.Y.K. and C.P.L.; validation, C.Y.K. and C.P.L.; formal analysis, C.Y.K.; investigation, C.Y.K.;
resources, C.Y.K.; data curation, C.Y.K. and C.P.L.; writing—original draft preparation, C.Y.K.;
writing—review and editing, C.P.L. and K.M.L.; visualization, C.Y.K. and C.P.L.; supervision, C.P.L.
and K.M.L.; project administration, C.P.L.; funding acquisition, C.P.L. All authors have read and
agreed to the published version of the manuscript.
Funding: The research in this work was supported by Telekom Malaysia Research & Development
under grant number RDTC/221045, Fundamental Research Grant Scheme of the Ministry of Higher
Education under award number FRGS/1/2021/ICT02/MMU/02/4, and Multimedia University
Internal Research Grant with award number MMUI/220021.
Institutional Review Board Statement: Not applicable.
Informed Consent Statement: Not applicable.
Data Availability Statement: Not applicable.
Conflicts of Interest: The authors declare no conflict of interest.
Data 2022, 7, 149 12 of 13

Abbreviations
The following abbreviations are used in this manuscript:

1DCNN-GRU 1-dimensional Convolutional Neural Network and Gated Recurrent Unit

1DCNN 1-dimensional Convolutional Neural Network
GRU Gated Recurrent Unit
ANN Artificial Neural Network
MLP Multilayer Perceptron
RMSE Root Mean Square Error
LSTM Long Short-Term Memory
RNN Recurrent Neural Networks
TCN Temporal Convolutional Networks
Conv1D 1D convolutional layer

References
1. Nakamoto, S. Bitcoin: A peer-to-peer electronic cash system. In Decentralized Business Review; Seoul, Korea, 2008; p. 21260.
Available online: https://www.debr.io/article/21260-bitcoin-a-peer-to-peer-electronic-cash-system (accessed on 19 June 2022).
2. Lim, J.Y.; Lim, K.M.; Lee, C.P. Stacked Bidirectional Long Short-Term Memory for Stock Market Analysis. In Proceedings of the
2021 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET), Kota Kinabalu, Malaysia,
13–15 September 2021; pp. 1–5.
3. Chong, L.S.; Lim, K.M.; Lee, C.P. Stock Market Prediction using Ensemble of Deep Neural Networks. In Proceedings of the 2020
IEEE 2nd International Conference on Artificial Intelligence in Engineering and Technology (IICAIET), Kota Kinabalu, Malaysia,
26–27 September 2020; pp. 1–5.
4. Islam, M.R.; Nguyen, N. Comparison of financial models for stock price prediction. J. Risk Financ. Manag. 2020, 13, 181. [CrossRef]
5. Koukaras, P.; Nousi, C.; Tjortjis, C. Stock Market Prediction Using Microblogging Sentiment Analysis and Machine Learning.
Telecom 2022, 3, 358–378. [CrossRef]
6. Park, J.; Seo, Y.S. A Deep Learning-Based Action Recommendation Model for Cryptocurrency Profit Maximization. Electronics
2022, 11, 1466. [CrossRef]
7. Manujakshi, B.; Kabadi, M.G.; Naik, N. A Hybrid Stock Price Prediction Model Based on PRE and Deep Neural Network. Data
2022, 7, 51.
8. Shahbazi, Z.; Byun, Y.C. Knowledge Discovery on Cryptocurrency Exchange Rate Prediction Using Machine Learning Pipelines.
Sensors 2022, 22, 1740. [CrossRef] [PubMed]
9. Patel, M.M.; Tanwar, S.; Gupta, R.; Kumar, N. A deep learning-based cryptocurrency price prediction scheme for financial
institutions. J. Inf. Secur. Appl. 2020, 55, 102583. [CrossRef]
10. Pintelas, E.; Livieris, I.E.; Stavroyiannis, S.; Kotsilieris, T.; Pintelas, P. Investigating the problem of cryptocurrency price prediction:
A deep learning approach. In Proceedings of the IFIP International Conference on Artificial Intelligence Applications and
Innovations, Neos Marmaras, Greece, 5–7 June 2020; Springer: Cham, Switzerland, 2020; pp. 99–110.
11. Gao, P.; Zhang, R.; Yang, X. The application of stock index price prediction with neural network. Math. Comput. Appl. 2020, 25, 53.
[CrossRef]
12. Carta, S.; Medda, A.; Pili, A.; Reforgiato Recupero, D.; Saia, R. Forecasting e-commerce products prices by combining an
autoregressive integrated moving average (ARIMA) model and google trends data. Future Internet 2018, 11, 5. [CrossRef]
13. Abraham, J.; Higdon, D.; Nelson, J.; Ibarra, J. Cryptocurrency price prediction using tweet volumes and sentiment analysis. SMU
Data Sci. Rev. 2018, 1, 1.
14. Dutta, A.; Kumar, S.; Basu, M. A gated recurrent unit approach to bitcoin price prediction. J. Risk Financ. Manag. 2020, 13, 23.
[CrossRef]
15. Sin, E.; Wang, L. Bitcoin price prediction using ensembles of neural networks. In Proceedings of the 2017 13th International
Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD), Guilin, China, 29–31 July 2017;
pp. 666–671.
16. Yenidoğan, I.; Çayir, A.; Kozan, O.; Dağ, T.; Arslan, Ç. Bitcoin forecasting using ARIMA and PROPHET. In Proceedings of the
2018 3rd International Conference on Computer Science and Engineering (UBMK), Sarajevo, Bosnia and Herzegovina, 20–23
September 2018; pp. 621–624.
17. McNally, S.; Roche, J.; Caton, S. Predicting the price of bitcoin using machine learning. In Proceedings of the 2018 26th Euromicro
International Conference on Parallel, Distributed and Network-based Processing (PDP), Cambridge, UK, 21–23 March 2018;
pp. 339–343.
18. Phaladisailoed, T.; Numnonda, T. Machine learning models comparison for bitcoin price prediction. In Proceedings of the 2018
10th International Conference on Information Technology and Electrical Engineering (ICITEE), Bali, Indonesia, 24–26 July 2018;
pp. 506–511.
19. Jiang, X. Bitcoin price prediction based on deep learning methods. J. Math. Financ. 2019, 10, 132–139. [CrossRef]
Data 2022, 7, 149 13 of 13

20. Politis, A.; Doka, K.; Koziris, N. Ether price prediction using advanced deep learning models. In Proceedings of the 2021 IEEE
International Conference on Blockchain and Cryptocurrency (ICBC), Sydney, Australia, 3–6 May 2021; pp. 1–3.
21. Tanwar, S.; Patel, N.P.; Patel, S.N.; Patel, J.R.; Sharma, G.; Davidson, I.E. Deep learning-based cryptocurrency price prediction
scheme with inter-dependent relations. IEEE Access 2021, 9, 138633–138646. [CrossRef]
22. Livieris, I.E.; Kiriakidou, N.; Stavroyiannis, S.; Pintelas, P. An advanced CNN-LSTM model for cryptocurrency forecasting.
Electronics 2021, 10, 287. [CrossRef]
23. Zhang, Z.; Dai, H.N.; Zhou, J.; Mondal, S.K.; García, M.M.; Wang, H. Forecasting cryptocurrency price using convolutional neural
networks with weighted and attentive memory channels. Expert Syst. Appl. 2021, 183, 115378. [CrossRef]
24. Jay, P.; Kalariya, V.; Parmar, P.; Tanwar, S.; Kumar, N.; Alazab, M. Stochastic neural networks for cryptocurrency price prediction.
IEEE Access 2020, 8, 82804–82818. [CrossRef]
25. Sebastião, H.; Godinho, P. Forecasting and trading cryptocurrencies with machine learning under changing market conditions.
Financ. Innov. 2021, 7, 1–30. [CrossRef] [PubMed]
26. Saadah, S.; Whafa, A.A. Monitoring Financial Stability Based on Prediction of Cryptocurrencies Price Using Intelligent Algorithm.
In Proceedings of the 2020 International Conference on Data Science and Its Applications (ICoDSA), Bandung, Indonesia,
5–6 August 2020; pp. 1–10.
27. Derbentsev, V.; Datsenko, N.; Babenko, V.; Pushko, O.; Pursky, O. Forecasting Cryptocurrency Prices Using Ensembles-Based
Machine Learning Approach. In Proceedings of the 2020 IEEE International Conference on Problems of Infocommunications.
Science and Technology (PIC S&T), Kharkiv, Ukraine, 6–9 October 2020; pp. 707–712.
28. Zielak. Bitcoin historical Data. Available online: https://www.kaggle.com/mczielinski/Bitcoin-historical-data (accessed on
17 May 2022).
29. Jaquart, P.; Dann, D.; Weinhardt, C. Short-term bitcoin market prediction via machine learning. J. Financ. Data Sci. 2021, 7, 45–66.
[CrossRef]