=Paper=
{{Paper
|id=Vol-2732/20200385
|storemode=property
|title=Risks of the Methodology for Forecasting the Price of Bitcoin and the
Frequency of its Online Requests in the Digitalization of Economic Systems
|pdfUrl=https://ceur-ws.org/Vol-2732/20200385.pdf
|volume=Vol-2732
|authors=Hanna Kucherova,Dmytro Ocheretin,Vita Los,Natalia Venherska
|dblpUrl=https://dblp.org/rec/conf/icteri/KucherovaOLV20
}}
==Risks of the Methodology for Forecasting the Price of Bitcoin and the
Frequency of its Online Requests in the Digitalization of Economic Systems==
https://ceur-ws.org/Vol-2732/20200385.pdf
Risks of the methodology for forecasting the price of
bitcoin and the frequency of its online requests in the
digitalization of economic systems
Hanna Kucherova1, Dmytro Ocheretin2, Vita Los2, Natalia Venherska2
1
Classic Private University, 70B, Zhukovsky st., Zaporizhzhia, 69002 Ukraine
kucherovahanna@gmail.com
2
Zaporizhzhia National University, 66, Zhukovsky st., Zaporizhzhia, 69600 Ukraine
odvisua@gmail.com, vitalos.2704@gmail.com,
nataljavengerskaja@ukr.net
Abstract. Research goals and objectives: to study the series of dynamics of the
frequency of requests and the price of bitcoin under the conditions of taking
into account the risks of using various forecasting methods.
Subject of research: proof of importance of the role, statistical dependence and
interdependence of the series of dynamics of the price of bitcoin and the
frequency of its online requests.
Research methods used: analytical methods, econometric models, nonlinear
dynamics methods.
Results of the research: The research grounded the approach and the forecasting
procedure for the series of dynamics of the price of bitcoin and the frequency of
its online requests, which in essence correspond to the basic principles of the
implementation of the forecasting methodology, take into account the specifics
of the formation of the frequency of online requests for bitcoin prices and the
socio-economic meaning of its functioning. The practical value consists in
determining that the minimum risks for the study of a time series dynamics of
bitcoin price and frequency of requests for bitcoin price were demonstrated by
the neural network methodology in comparison with the use of the ARIMA
model and other methods of economic and mathematical modeling that proves
the proposed methodology for determining the direction of the trend outside the
study period.
Keywords. bitcoin price, frequency of requests, time series of dynamics,
forecasting, risks, methodology, neural networks, ARIMA models.
1 Introduction
The cryptocurrency phenomenon has proved the promise of the search for alternative
exchange units, whose circulating capabilities will not be limited by state money
supply regulation mechanisms and exchange rate policies of national banks, and, in
Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
general, will operate according to the principles of decentralization in the online
environment. Only market conditions in their pure form make it possible to reliably
assess the investment attractiveness and financial prospects of new instruments, the
functioning space of which are not limited to the real market, but cover the online
environment. This is completely logical, since bitcoin is a product of cryptography,
the development of digital technologies, and the spread of their use in economic
systems.
The atypical and contradictory nature of bitcoin requires a thorough study of its
parameters and features of functional development in a real socio-economic
environment of practitioners and scientists who still have not come to a final thought
about the benefits and the risks that accompany them [1]. The cryptocurrency
decentralization mechanism, which is manifested in the confidentiality and
unrestrictedness of purchases and sales, includes all the same elements of centralized
functioning due to the involvement of intermediaries in the mechanism.
Intermediaries, in particular, for the provision of digital wallet services, Mixers,
Mining Pools and others, which together provide minimization of constant costs,
expand the capabilities of users and etcetera, but also have a cost and additional risks
[2]. Over time, the complexity of the functional mechanism of cryptocurrencies only
increases, so the systemic and non-systemic risks change, form a new list of threats.
However, interest in cryptocurrencies is not waning.
Thus, the growing attention of the world community to the digitalization of socio-
economic processes is a prerequisite for the emergence of a new alternative exchange
currency – cryptocurrency. Their gradually increasing availability in the markets,
despite the attendant risks, has formulated a steady demand for cryptocurrency for
both the object of investment and exchange. Therefore, the mechanism of functioning
of the cryptocurrency and cursive differences require a systematic monitoring of key
parameters, which is easiest and fastest to do in an online environment.
Now, sufficient technical attention to cryptocurrency has supplemented with
economic content and outlined the circle of social issues that arose in the formation of
the cryptocurrency market. In general, Marella V., Lindman J., Rossi M., and
Tuunainen V. consider that “Bitcoin is a social movement in the financial industry”
[3]. As a result, despite the insufficient level of awareness, technical and financial
literacy of the population of developing countries, and thanks to the principle of
decentralization, the dynamics of interest in cryptocurrencies in the online
environment, in particular, bitcoin, are changing in accordance with changes in trends
in their exchange rate, which is currently little studied.
The purpose of the paper is to study the time series of dynamics of the frequency
of requests for bitcoin, taking into account the risk of using various forecasting
methods. The object of the research is the time series of the frequency of requests for
bitcoin in Ukraine according to Google Trends and bitcoin price. The subject of the
research is the risks of forecasting series of dynamics.
2 Related Work
The dynamic series of cryptocurrencies are investigated by a wide range of methods,
which today has formed a certain knowledge base of their accuracy, adequacy and
appropriateness of application. But, given the constant updating of statistical data, the
search for an adequate methodology for forecasting cryptocurrency parameters will be
relevant and timely at every stage of development.
Today, the results of researches of the bitcoin price time series dynamics in the
context of explaining the laws of its changes by the situation of modern economic
theories have proved their practical value; also, the activity and behavior of market
agents in general were taken into account, in particular, the influence of social
networks and the structure of the formed cryptocurrency market, which is constantly
evolving, was noted and is being improved [5]. The methods of machine learning and
modeling are actively used to forecast the trajectory of changes in the parameters of
bitcoin (most often, the dynamics of the price) and the cryptocurrency market [4, 5].
In particular, there are results of using:
linear models [8], but non-linearity is inherent in socio-economic processes, which
limits the possibility of applying the approach;
nonlinear autoregression [9], where the accuracy and quality of approaches is
limited when applied to data such as random walk;
binomial logistic regression [10], the implementation of a Bayesian optimized
recurrent neural network, Long Short Term Memory network and the ARIMA
model [6], effect of Bayesian neural networks [7], where from the practice of using
approaches it is proved that in the accuracy of forecasts ARIMA models are
significantly inferior to the results of using neural networks;
methods of the theory of complex systems have been successfully used to justify
the forerunners of critical changes in the bitcoin exchange rate [11], but qualitative
results were obtained on the trend in 2017 and it is not known what results will be
for the updated trend of the input data and whether the technology can determine
the direction of the trend.
Separately, note that a connection has already been established between bitcoins
and search information in Google, Wikipedia materials about them in an online
environment [12]. In addition, researches of the interdependence of requests in social
networks and the bitcoin exchange rate [13] are valuable, where a positive effect of
the growth of its popularity on the growth of search queries was established. In the
article [14], the authors studied the self-similarity and multifractal features of the
bitcoin exchange rate series, which corresponds to the nature and degree of
complexity of the bitcoin ecosystem. Also, the authors of [14] proved the feasibility
of taking into account indicators of social networks in order to predict the exchange
rate of bitcoin using fractal analysis methods.
The results of forecasting accuracy and the adequacy of forecasting models differ
methods at different periods of bitcoin course research, but scientists focus mainly on
machine learning methods. However, today the social aspect of the cryptocurrency
market is actively being studied, the quantitative and qualitative impact of this
phenomenon on various areas of socio-economic existence.
3 Risk
Forecasting as a methodology is constantly tested for adequacy to the realities of
socio-economic processes, since their complexity and unpredictability only increase
over time. The emergence of new tools requires taking into account not only the
results of the analysis of the series of dynamics that they produce, their economic
meaning, but also against the background of taking into account the risks of
functioning of the research object itself, the risks of using the chosen forecasting
methodology.
Thus, the risk structure is presented as a set of risks directly using the forecasting
methodology, and a set of risks that are inherent in the bitcoin functioning system
(forming a circle of relevant interests of online market agents), namely: internal and
external (technological, social, economic, interest in security, political and so on):
R RS , RM , t , (1)
where R S ri S – the set of systemic risks inherent in the price of bitcoin (the
frequency of requests for bitcoin), which are allocated from the socio-economic
environment for the period t ;
R M r jM – the set of methodological risks of forecasting for the period t .
The list of risks of the forecasting methodology includes such factors as: the
probability of making a mistake in choosing formal-informal methods and models; the
probability of achieving the goal of the study; the reliability of the results; accuracy of
their interpretation; excessive subjectivity in prediction; reassessment of the
capabilities of the resulting models; quality and reliability of information support and
etcetera. Most of these risks relate to the subjective and organizational aspects,
therefore, their level directly depends on the subject who makes the decision and the
availability of methodological tools, the measure of their mastery, reliable initial data
for the required period. Prediction as a phased process forms the level of aggregate
risk with a cumulative total, therefore its final value is determined by the product of
risk indicators of each stage of its implementation. Significant of taking into account
methodological risks involve that the prognostic results are based on entities making
financial and investment decisions, which together form the behavior and set the
cryptocurrency spread rates, the unregulatedness of which also forms a circle of risks
for users. Therefore, the issue of choosing a forecasting methodology is given special
attention.
4 Method
The forecasting methodology should include the use of several methods to develop a
forecast and select the best of them based on estimates of the accuracy and quality of
the forecast. Thus, the authors proposed a methodology for predicting the price of
bitcoin and the frequency of online requests for bitcoin, which consists of four
interrelated steps (fig. 1).
Collection of statistical information about the object of research:
– analysis of available sources of statistical information;
– use of online resources of Google, Yahoo, Yandex and others.
Statistical analysis of time series:
– analysis of the dynamics of the investigated time series:
determining the growth rate, average value, coefficient of variation, and
so on;
– determination of the relationship between the studied time series
(calculation of the correlation coefficient).
Comparative analysis of methods for forecasting time series
Formation Development of a Evaluation of
predictive forecast for test the quality of
models data forecasts
The choice of forecasting method and forecast model
Development of a forecast for the investigated time series
Fig. 1. Methodology of time series forecasting
The set of initial statistics consists of two time series, namely: the frequency of online
requests for bitcoin in Ukraine and the price of bitcoin. Time series were generated
using data from Google Trends [15] and InvestFunds [16] for the period from January
18, 2015 to January 12, 2020.
Statistical analysis of the studied time series will reveal the maximum, minimum
and average values of the series, as well as establish the growth rate, measure the
variability of the series and measure the relationship between the studied series. If
necessary, standardizing of time series is carried out.
Further, in accordance with fig. 1, forecast models are directly developed. To study
the series of dynamics, the authors selected several approaches to forecasting
(econometric models and non-linear dynamics methods), among which the best
results were shown by neural networks and ARIMA models. Thus Auto-Regressive
Integrated Moving Average (ARIMA) model and Neural Network Auto-Regressive
(NNAR) model were chosen.
The Auto-Regressive Integrated Moving Average (ARIMA) model describes the
time series by two main processes, namely: the process of autoregression and moving
average. Most time series contain elements that are sequentially dependent on each
other. This dependence can be expressed by the equation:
xt 1 xt 1 2 xt 2 3 xt 3 ... t , (2)
where – constant;
1 , 2 , 3 – autoregressive parameters;
– random component.
Thus, each observation is the sum of a random component and a linear
combination of previous observations. The autoregression process will be stationary
only when its parameters are in a certain range. For example, if there is only one
parameter, then it must be in the range 1 1 . In the opposite case, the
previous values will accumulate and the values of the next xt can be unlimited,
respectively, the time series will not be stationary.
Unlike the autoregression process, in the moving average process, each element of
the series falls under the combined influence of previous errors. In general terms, this
can be represented as follows:
xt 1 xt 1 2 xt 2 3 xt 3 ... t , (3)
where – constant;
1 , 2 , 3 – moving average parameters;
– random component.
That is, the current observation of a time series is the sum of a random component
at a given point in time and a linear combination of random influences at previous
points in time. It should be noted that between the processes of the moving average
and autoregression there is “duality” – one equation can be rewritten in the form of
another and vice versa (reversibility property). Similar to the stationary conditions,
there are conditions that ensure the reversibility of the model.
The generalized ARIMA model includes both autoregressive parameters and
moving average parameters. The model is described using three parameters:
autoregressive parameters (p), difference order (d) and moving average parameters
(q). This model is described as follows: ARIMA (p, d, q).
The next forecasting method is the Neural Network Auto-Regressive (NNAR)
model. Artificial neural networks allow to explore complex non-linear relationships
between incoming and outgoing variables. They are widely used for approximating
functions and forecasting. The main advantage of these models is that they allow the
approximation of a large class of functions with a high level of accuracy. In this
model, older values of the time series are used as input data of the model, and forecast
values are used as outgoing values. The NNAR model can be represented as a neural
network, which includes a linear combination function and an activation function [17,
18, 19]. The linear combination function can be given in the following form:
net j wij хij . (4)
i
The activation function is a sigmoid function and is defined as follows:
f х
1
. (5)
1 exp х
The network inputs are connected using a linear function and, as a result of various
combinations, are then transmitted through a sigmoid nonlinear activation function. In
accordance with the article [20], the weights of the neural network are updated using
the inverse propagation algorithm. Weights in the neural network are selected so that
the forecast error is minimal.
This article uses the following model designation: NNAR (p, k), where the first
parameter (p) shows the number of lags and the second (k) – the number of nodes in
the hidden layer.
Having built forecast models ARIMA and NNAR, they should be verified and the
quality and accuracy of the forecast should be determined. As estimates of the
accuracy of the forecast, mean absolute percentage error (MARE) is used, which is
determined by the following formula:
100 T xt xˆt
MAPE
t T 1 xt
. (5)
As a result of model verification, the model that has the minimum forecast error is
selected [21].
5 Results
The forecasting methodology proposed by the authors was tested for two time series:
the price of bitcoin and the frequency of requests for bitcoin of Ukrainian online users
in Google Trends. The initial data are weekly values, and the observation base was
261 periods. Thus, the regulatory independence of Bitcoin has led to a close
relationship between its price and demand, which proves the similarity of the series of
request frequency and bitcoin price in fig. 2. The circle of interests in
cryptocurrencies in the online environment is characterized by the structure of the
semantic core of requests from market agents, the frequency of which in different
periods determines the direction of their changes, which is explained by the socio-
economic factors of influence of the studied period. Consequently, the level of
interest in the object and the frequency of its online queries is characterized by a
direct proportion. The most popular structure of the semantic core is the simplest
semantic unit, therefore it has a significant number of semantic links and corresponds
directly to the name of the electronic currency - "bitcoin". The relationship of more
complex requests with the core "bitcoin" has not been investigated.
Bitcoin Price, USD
120 25 000,00
Interest over Time
100 20 000,00
80 15 000,00
60 10 000,00
40
20 5 000,00
0 0,00
18.1.2015
18.7.2015
18.1.2016
18.7.2016
18.1.2017
18.7.2017
18.1.2018
18.7.2018
18.1.2019
18.7.2019
Time
frequency of requests "bitcoin" bitcoin price
Fig.2. The time series of dynamics of the price of bitcoin and the frequency of online requests
"bitcoin" according to Google Trends in Ukraine
In accordance with the data in fig. 2, as we can see the price of bitcoin is quite
volatile. So, on August 06, 2012, its maximum value is traced at the level of 3,213.94
USD, and on January 18, 2015, the minimum value is recorded – 210.34 USD. It was
found that for the study period, the price of bitcoin increased weekly by an average of
2%, and the frequency of requests - by 2.1%. The maximum increase in bitcoin value
is 41.5% (July 23, 2017), the minimum increase is 29.8% (April 02, 2018), and the
average price of bitcoin was 4023.752 USD. In the studied time series of the price of
bitcoin, there is a high variability of values, as evidenced by the coefficient of
variation, which is 91%.
It was during the period when the bitcoin price reached its maximum that the
frequency of requests in the online environment for the keyword "bitcoin" also
reached its maximum value - 100 interest over time. At the same time, the minimum
value of the number of bitcoin price request frequency rates (5 interest over time) was
observed in several periods: April 19,2015, May 17, 2015, June 06, 2015, June 14,
2015, September 06, 2015, September 13, 2015, April 10, 2015, November 10, 2015.
These dates correspond to the period when the bitcoin price dynamics is characterized
by a low level of volatility. For the analyzed period, it was found that on average
there were 17 interest over time per week. Thus, it can be argued that the interest in
bitcoin in the online environment increases and forms a number of dynamics similar
to the dynamics of its value in periods of significant fluctuations. The stability of its
exchange rate does not arouse the interest of market agents, therefore, they conduct
certain periodic monitoring.
The correlation coefficient between the studied series of dynamics (fig. 2) is 0,73,
which proves the tightness of the relationship and the interdependence of their trends.
A more pronounced similarity of trends is observed during periods when the Bitcoin
exchange rate was characterized by significant volatility. Consequently, the variability
of exchange rate fluctuations, among other factors, causes an increase in interest from
market agents, which is expressed by a corresponding change in the frequency of their
requests in the online environment. The weight of the research of the influence of the
dynamics of the frequency of requests “bitcoin” is explained by the fact that this
semantic core with a significant level of popularity in the online environment
determines the behavior of market agents. In addition, the frequency of the indicator
may form an idea of the possible demand for cryptocurrency.
The indicated sensitivity of the frequency of online requests to exchange rate
fluctuations of bitcoin is more pronounced than in other currencies, in particular,
between the exchange rates of the euro, the dollar and the frequency of their online
requests (fig. 3).
120 40
100 35
Interest over Time
30
Exchange Rate
80 25
60 20
40 15
10
20 5
0 0
3.7.2016
12.10.2014
10.5.2015
6.12.2015
29.1.2017
27.8.2017
25.3.2018
21.10.2018
19.5.2019
Time
dollar exchange rate, USD/UAH
frequency of requests for the keyword 'dollar exchange rate'
euro exchange rate,€/UAH
frequency of requests for the keyword 'euro exchange rate'
Fig. 3. The time series of dynamics of the exchange rates and the frequency of online requests
"dollar" and "euro" according to Google Trends in Ukraine
The aforementioned is explained by the limiting influence of the monetary policy of
the states and the International Monetary Fund, therefore, the connection density is
present, but not significant (k = 0.37). And this is logical, since at the given moment
all states are trying to limit the possibility of the outflow of the national currency from
the country by means of cryptocurrencies and technologies [22; 23].
In accordance with the proposed methodology (fig. 1), the next step is to build
models for predicting the studied time series, namely, the price of bitcoin and the
frequency of requests. To build the models, used the tools of the R environment,
namely the "forecast" library. The time series was divided into training and test sets.
The training set was 96% of the data (251 values, data from January 18, 2015 to
November 03, 2019), and the test set was 4% of data (10 values, from November 10,
2019 to January 12, 2020).
By analyzing the data in fig. 2, we can state that there are peaks and drops in the
trend direction in the time series. The investigated time series are non-stationary,
which confirms the advanced Dickey-Fuller Test. On the other hand, with a fairly
high level of confidence, it can be argued that the first-order differences of the series
are stationary, that is, these are integrated first-order time series. There is no seasonal
component in the time series, but a random component is present. In the medium
term, compared the predictive models of ARIMA and the neural network.
In fig. 4 and fig. 5 shows the constructed predictive models for the test set of the
time series – the price of bitcoin.
ARIMA (2,1,2)
Bitcoin Price, USD
12000
10000
8000
6000
2.6.2019
2.7.2019
2.8.2019
2.9.2019
2.1.2020
2.10.2019
2.11.2019
2.12.2019
Time
Real Data ARIM A(2,1,2) forecast
Fig. 4. Forecast from ARIMA (2, 1, 2) for the test set the price of bitcoin
Thus, the constructed ARIMA model (2,1,2) contains two autoregressive
parameters and two moving average parameters, which are calculated for a time series
after taking the difference with lag 1. Also, the authors obtained the NNAR neural
network (7, 7), in which the length of the lag and the number of nodes in the hidden
layer are 7.
NNAR (7,7)
Bitcoin Price, USD
12000
10000
8000
6000
2.6.2019
2.7.2019
2.8.2019
2.9.2019
2.1.2020
2.10.2019
2.11.2019
2.12.2019
Time
Real Data NNAR(7, 7) forecast
Fig. 5. Forecast from NNAR (7, 7) for the test set the price of bitcoin
Compared the obtained predicted values for the constructed models with real data
in the test set. From the graphical representation of the data in fig. 4 and fig. 5 shows
that the predicted data of the NNAR model (7, 7) are closer to real ones. From fig. 6
as we can see the obtained forecast data do not go beyond the 95% confidence
interval, that is, there is a fairly accurate forecast. This is also evidenced by the value
of the mean absolute percentage error (MAPE): for ARIMA it is 18.4%, and for the
neural network – 6.1%. Therefore, for medium-term forecasting of the price of
bitcoin, it is better to use a neural network NNAR (7, 7), since the forecast will be
more accurate.
The results of forecasting the price of bitcoin for the next 10 weeks (January 19,
2020 – March 22, 2020) using the model NNAR (7,7) are presented in fig. 7.
In accordance with the forecast, the price of bitcoin in this period will have a
decreasing trend and decrease by 25, 6%, from 8192.49 USD to 6093.467 USD per
bitcoin.
For the time series of the "bitcoin" request frequency from Ukrainian online users
the best ARIMA model for test data was ARIMA (0, 1, 0). And the best neural model
for the time series of requests for bitcoin is the NNAR (8.7) (fig. 8).
Comparing the predicted values for the obtained models with real data in the test
sample (fig. 9), we see that they do not go beyond the 95% confidence interval.
The mean absolute percentage error (MAPE) value for the ARIMA model is
9.09%, and for the neural network – 11.7% (table 1). But it should be noted that the
ARIMA model (0,1,0) is a random walk model, so the forecast can be made only one
period ahead. Therefore, this model can only be used for short-term forecasting. For
medium-term forecasting of requests for bitcoin of Ukrainian online users, a neural
network model was used, namely, NNAR (8, 7).
15500
13500
Bitcoin Price, USD
11500
9500
7500
5500
3500
5.1.2020
1.12.2019
8.12.2019
12.1.2020
10.11.2019
17.11.2019
24.11.2019
15.12.2019
22.12.2019
29.12.2019
Time
Real Data ARIM A (2,1,2)
NNAR (7,7) 95% lower confidence criterion
95% upper confidence criterion
Fig. 6. Forecast for the test set the price of bitcoin
NNAR (7,7)
Bitcoin Price, USD
13000
8000
3000
2.6.2019
2.7.2019
2.8.2019
2.9.2019
2.1.2020
2.2.2020
2.3.2020
2.10.2019
2.11.2019
2.12.2019
Time Real Data NNAR(7,7)
Fig. 7. Forecast from NNAR (7, 7) for the price of bitcoin
NNAR (8,7)
Interest over Time
40
30
20
10
0
2.6.2019
2.7.2019
2.8.2019
2.9.2019
2.1.2020
2.10.2019
2.11.2019
2.12.2019
Time Real Data NNAR(8, 7) forecast
Fig. 8. Forecast from NNAR (8, 7) for the test set the requests "bitcoin"
30 Real Data
Interest over Time
25 ARIM A (0,1,0)
NNAR (8,7)
20 95% confidence criterion
15 95% confidence criterion
10
5
0
5.1.2020
10.11.2019
17.11.2019
24.11.2019
1.12.2019
8.12.2019
15.12.2019
22.12.2019
29.12.2019
12.1.2020
-5
Time
Fig. 9. Forecast for the test set the requests "bitcoin"
Table 1. Comparing forecasting results
Auto-Regressive Integrated Neural Network Auto-Regressive
Moving Average (ARIMA) model (NNAR) model
Time the frequency of the frequency of
the price of the price of
requests for requests for
bitcoin bitcoin
bitcoin bitcoin
10.11.2019 8878,67 12 8721,588 10,134
17.11.2019 9227,636 12 8211,657 8,497
24.11.2019 9148,794 12 7962,576 8,135
01.12.2019 8943,138 12 7876,07 8,370
08.12.2019 9230,276 12 7733,796 9,366
15.12.2019 9092,271 12 7823,07 9,749
22.12.2019 9001,815 12 7781,075 9,816
29.12.2019 9214,146 12 7628,991 9,478
05.01.2020 9060,785 12 7344,58 9,218
12.01.2020 9049,155 12 7016,984 9,249
MAPE 18,4% 9,09% 6,1% 11,7%
The results of forecasting the frequency of requests "bitcoin" by Ukrainian online
users for the next 10 weeks (January 19, 2020 - March 22, 2020) are presented in
table 2.
According to the forecast, the frequency of requests “bitcoin” of Ukrainian online
users in this period will increase by 41.7%, from 12 interest over time to 17 interest
over time per week. Thus, it is forecasted that the average frequency of requests will
increase by 2.4% weekly.
Table 2. The forecast of the studied indicators by the method NNAR
The frequency of requests for
The price of bitcoin
bitcoin
Time
Rate of Request Rate of
$USD
increase, % frequency increase, %
19.01.2020 7627,617 – 13,83168 –
26.01.2020 7421,916 -2,70% 14,71267 6,37%
02.02.2020 7058,429 -4,90% 14,03004 -4,64%
09.02.2020 6631,057 -6,05% 15,26786 8,82%
16.02.2020 6556,085 -1,13% 16,18115 5,98%
23.02.2020 6238,652 -4,84% 15,41361 -4,74%
01.03.2020 6267,147 0,46% 15,93974 3,41%
08.03.2020 6252,667 -0,23% 16,31639 2,36%
15.03.2020 6123,963 -2,06% 16,42473 0,66%
22.03.2020 6093,467 -0,50% 17,04905 3,80%
6 Conclusions
As a result of the research, the importance of taking into account the risks of the
methodology for predicting the key parameters of bitcoin, whose nature and
mechanism of functioning are distinguished by decentralization, self-organization and
the internal complexity of processes increasing in time, is confirmed. The indicated
characteristics of an electronic instrument today have shown a limited methodology
and variability in the risks of using various methods of forecasting and predicting both
the price of bitcoin and the frequency of requests "bitcoin". The studied series of
dynamics are defined as integrated time series of the first order, non-stationary, with
no seasonal, but with a random component present, which corresponds to the features
of the mechanism of functioning of bitcoin. The statistical dependence and
interdependence of the series of the dynamics of the price of bitcoin and the
frequency of online requests for bitcoin is proved. Interest in bitcoin in the online
environment is growing like the dynamics of its course during periods of significant
volatility. Whereas during the period of stabilization of the price of bitcoin, uniform
periodic monitoring is carried out in the online environment. Certain patterns can be
used to explain the trends in bitcoin parameters and the socio-economic behavior of
agents in this market sector. The article defines the approach and forecasting
procedure for the studied series of dynamics, which essentially correspond to the
basic principles of the forecasting methodology and takes into account the specifics
and socio-economic content of the price of bitcoin and the frequency of online
requests about it. Based on the results of applying forecasting methods to the studied
time series of dynamics, it was determined that the processes of self-organization of
the bitcoin functioning mechanism provide for the advisability of using forecasting
methods with internal procedures for self-learning, self-tuning and adaptation in real
time. So, the minimum risks for the study of the bitcoin price time series dynamics
were demonstrated by the neural network methodology in comparison with the use of
the ARIMA model. Although estimates of forecasting quality using the methods used
are generally acceptable, the risk of using the ARIMA model methodology also lies in
the fact that its advisability can be limited only to short-term forecasting (for one
period), while neural network technology justifies itself in medium-term forecasting
tasks. Given the dynamism and daily updating of data on the parameters of bitcoin, in
practice it most often manifests itself in short-term forecasting, while for basic
research is - medium and long-term forecasting. The authors also note that the results
of forecasting the price of bitcoin for the period January 19, 2020 - March 22, 2020
prove the formation of a decreasing trend (-25.6%), while the forecast frequency of
requests during this period will increase by 41.7%. Since the authors have proved that
an increase in the frequency of requests "bitcoin" corresponds to its high volatility in
the direction of increase, it is logical to say that in the forecast period, the dynamics of
the price of bitcoin will be characterized by high variability and an increase will take
place after a certain decline. Subsequent researchers provide for a recurrency analysis
of bitcoin prices and the frequency of online requests "bitcoin", which will
complement knowledge about the risks of using separate methodologies for their
forecasting, evaluation, and analysis.
References
1. Dumitrescu, G. C.: Bitcoin–a brief analysis of the advantages and disadvantages. Global
Economic Observer 5(2), 63-71 (2017).
2. Böhme, R., Christin, N., Edelman, B., Moore, T.: Bitcoin: Economics, technology, and
governance. Journal of economic Perspectives 29(2), 213-38 (2015).
3. Marella, V., Lindman, J., Rossi, M., Tuunainen, V.: Bitcoin: A social movement under
attack. Scandinavian IRIS Association Issue Nr 8 (2017). 1.
http://aisel.aisnet.org/iris2017/1, last accessed 2019/12/015
4. Saad, M., Choi, J., Nyang, D., Kim, J., Mohaisen, A.: Toward Characterizing Blockchain-
Based Cryptocurrencies for Highly Accurate Predictions. IEEE Systems Journal 14, 321-
332 (2019).
5. Krafft, P. M., Della Penna, N., Pentland, A. S.: An experimental study of cryptocurrency
market dynamics. Conference CHI’18 paper 605, pp. 1-13 (2018).
6. McNally, S.: Predicting the price of Bitcoin using Machine Learning (Doctoral
dissertation, Dublin, National College of Ireland). (2016).
7. Jang, H., Lee, J.: An empirical study on modeling and prediction of bitcoin prices with
bayesian neural networks based on blockchain information. Ieee Access 6, 5427-5437
(2017).
8. Ciaian, P., Rajcaniova, M., Kancs, D.: The economics of Bitcoin price formation. Applied
Economics 48(19), 1799-1815 (2016).
9. Indera, N., Yassin, I., Zabidi, A., Rizman, Z.: Non-linear autoregressive with exogeneous
input (NARX) bitcoin price prediction model using PSO-optimized parameters and
moving average technical indicators. J. Fundam. Appl. Sci. 9, pp. 791-808 (2017).
10. Madan, I., Saluja, S., Zhao, A.: Automated bitcoin trading via machine learning
algorithms, http://cs229. stanford. edu/proj2014/Isaac% 20Madan, 20, last accessed
2019/12/02
11. Soloviev, V. N., Belinskiy, A.: Complex Systems Theory and Crashes of Cryptocurrency
Market. In International Conference on Information and Communication Technologies in
Education, Research, and Industrial Applications, pp. 276-297. Springer, Cham (2018).
12. Kristoufek, L.: Bitcoin meets Google trends and Wikipedia: Quantifying the relationship
between phenomena of the Internet era. Scientific reports 3, 3415 (2013).
13. Garcia, D., Tessone, C.J., Mavrodiev, P., Perony, N.: The digital traces of bubbles:
feedback cycles between socio-economic signals in the Bitcoin economy. Journal of the
Royal Society Interface 11.99, 20140623 (2014).
14. Kirichenko, L., Radivilova, T., Bullakh, V., Chakryan, V.: Analysis of the interdependence
of bitcoin time series and community activity on social networks. International Journal
"Information Technologies & Knowledge 12.1, 43-55 (in Ukrainian) (2018).
15. Google Trends Home page, https://trends.google.com.ua/trends/?geo=UA, last accessed
2020/01/25
16. Bitcoin. InvestFunds. Home page, https://investfunds.ru/indexes/9021/, last accessed
2020/01/25
17. Hyndman, R. J., Athanasopoulos, G.: Forecasting: principles and practice. Second print
edition. OTexts (2018).
18. Faraway, J., Chatfield, C.: Time series forecasting with neural networks: a comparative
study using the airline data. Journal of the Royal Statistical Society: Series C (Applied
Statistics) 47. 2, 231-250 (1998).
19. Thoplan, R.: Simple v/s sophisticated methods of forecasting for mauritius monthly tourist
arrival data. International Journal of Statistics and Applications, 4(5), 217-223 (2014).
DOI: 10.5923/j.statistics.20140405.01
20. Core Team R.: A language and environment for statistical computing. R Foundation for
Statistical Computing, Vienna, Austria (2014), http://www.R-project.or/, last accessed
2020/02/28
21. Munim, Z. H., Shakil, M. H., Alon, I.: Next-Day Bitcoin Price Forecast. Journal of Risk
and Financial Management 12(2), 15 (2019). DOI: 10.3390/jrfm12020103
22. D.K. Bitcoin’s Collapse: China Blues. The Economist (2013),
https://www.economist.com/schumpeter/2013/12/18/china-blues, last accessed 2020/01/08
23. McLeod, A. S.: Bitcoins Soar in Value in Argentina due to Capital Control Laws. Forex
Magnates (2013), https://www.financemagnates.com/cryptocurrency/trading/bitcoins-soar-
in-value-in-argentina-due-to-capital-control-laws-bitcoin-meetup-held-in-nations-capital/,
last accessed 2020/02/03