\documentclass[10pt]{article}
\usepackage{fullpage}
\usepackage{setspace}
\usepackage{parskip}
\usepackage{titlesec}
\usepackage[section]{placeins}
\usepackage{xcolor}
\usepackage{breakcites}
\usepackage{lineno}
\usepackage{hyphenat}
\PassOptionsToPackage{hyphens}{url}
\usepackage[colorlinks = true,
linkcolor = blue,
urlcolor = blue,
citecolor = blue,
anchorcolor = blue]{hyperref}
\usepackage{etoolbox}
\makeatletter
\patchcmd\@combinedblfloats{\box\@outputbox}{\unvbox\@outputbox}{}{%
\errmessage{\noexpand\@combinedblfloats could not be patched}%
}%
\makeatother
\usepackage{natbib}
\renewenvironment{abstract}
{{\bfseries\noindent{\abstractname}\par\nobreak}\footnotesize}
{\bigskip}
\titlespacing{\section}{0pt}{*3}{*1}
\titlespacing{\subsection}{0pt}{*2}{*0.5}
\titlespacing{\subsubsection}{0pt}{*1.5}{0pt}
\usepackage{authblk}
\usepackage{graphicx}
\usepackage[space]{grffile}
\usepackage{latexsym}
\usepackage{textcomp}
\usepackage{longtable}
\usepackage{tabulary}
\usepackage{booktabs,array,multirow}
\usepackage{amsfonts,amsmath,amssymb}
\providecommand\citet{\cite}
\providecommand\citep{\cite}
\providecommand\citealt{\cite}
% You can conditionalize code for latexml or normal latex using this.
\newif\iflatexml\latexmlfalse
\providecommand{\tightlist}{\setlength{\itemsep}{0pt}\setlength{\parskip}{0pt}}%
\AtBeginDocument{\DeclareGraphicsExtensions{.pdf,.PDF,.eps,.EPS,.png,.PNG,.tif,.TIF,.jpg,.JPG,.jpeg,.JPEG}}
\usepackage[utf8]{inputenc}
\usepackage[T2A]{fontenc}
\usepackage[polish,english]{babel}
\usepackage{float}
\begin{document}
\title{Forecasting Financial Cycles: Can Big Data Help?}
\author[1]{Marinko Škare}%
\affil[1]{Juraj Dobrila University of Pula}%
\vspace{-1em}
\date{\today}
\begingroup
\let\center\flushleft
\let\endcenter\endflushleft
\maketitle
\endgroup
\selectlanguage{english}
\begin{abstract}
Pellentesque tincidunt lobortis orci non venenatis. Cras in justo
luctus, pulvinar augue id, suscipit diam. Morbi aliquet fringilla nibh,
vel pellentesque dui venenatis eget. Orci varius natoque penatibus et
magnis dis parturient montes, nascetur ridiculus mus. Donec ultricies
ultrices magna gravida porta. Maecenas accumsan diam dui, auctor ornare
ex pellentesque id. Integer tempus massa id augue finibus convallis.
Nulla vestibulum, nisl id tempor pulvinar, felis dui pellentesque lacus,
quis bibendum metus enim sed ex.%
\end{abstract}%
\sloppy
\par\null
\section*{Introduction}
{\label{874460}}
The global financial crisis of 2008 after decades of the great
moderation policy governance opened the discussion of the financial
stability importance for economic activity. Identification of the
earning warning signals to predict business cycles and avoid instability
in the economy was always the primary goal of the policymakers. Our
paper is the first to combine financial big data to forecast financial
cycles.
First to mention the importance of the big data for macroeconomic
management was~\hyperref[csl:1]{(Phillips 1962)}. Phillips (1962) put forward the
assumption that policymakers can not design effective economic policy
without quantitative knowledge behind the main economic forces governing
the economic system.~ Main economic forces consist of employment,
inflation and growth as instruments and policy goals at the same time.
Therefore, it is not possible to design an optimal economic policy
without knowing the quantitative relations that hold between these
economic forces. To be able to measure and identify the correct
quantitive relationship among employment, inflation and growth, a big
data approach is essential.~
Fluctuations in financial variables always had a significant impact on
real economic activities. That is the case today but was all the same
3000 years ago. Oscillatory behaviour in savings and investments
dynamics and price targeting articulate economic cycle, see Ji
Ran~\hyperref[csl:2]{(Milburn 2007)}. Consequently, policymakers must always monitor
the saving-investments cycle keeping prices under control to ensure the
smooth running of the economy.~ The same concept highlighting the
importance of financial conditions for business cycles is extended
in~\hyperref[csl:3]{(Keynes 1936)},~\hyperref[csl:4]{(Schumpeter 1939)},~\hyperref[csl:5]{(Minsky 1963: 101–111}; \hyperref[csl:6]{Minsky 1975)}.
Inherent dynamics in financial conditions articulate the dynamics of the
business cycles driving economic booms and downturns. Financial markets
offer a large number of financial data reflecting financial conditions
still the issue of financial cycles definition, measurement and
forecasting remain undisclosed. We can understand the complexity of the
problem from the fact that today we still miss a generalised definition
of financial cycles. General literature uses Minsky's financial
instability hypothesis to define financial cycles in the form of the
Minsky's cycle. Pioneering works of~\hyperref[csl:7]{(Borio et al. 2011: 237–268}; \hyperref[csl:8]{Drehmann et al. 2012: 1–38}; \hyperref[csl:9]{Drehmann et al. 2013: 131–156)} define financial
cycles as long swings in financial conditions (credit and assets price).
A large body of research focuses on the issue of finding an optimal
method for measuring financial
cycles~~\hyperref[csl:10]{(Sch{\"{u}}ler et al. 2015)},~\hyperref[csl:11]{(Strohsal et al. 2019)},~\hyperref[csl:12]{(Hiebert et al. 2014: 109–117)},~\hyperref[csl:13]{(R{\"{u}}nstler et al. 2018: 212–226)},~\hyperref[csl:14]{(Strohsal et al. 2019)},~\hyperref[csl:15]{(Skare et al. 2019)}.~~
In this paper, we use quarterly big data for the United Kingdom, the
United States, Japan and China from Q1 2004 Q1 2019. We use web-based
indicators from the Google trends, financial market data (house price
index and credit volume, share in the GDP), long- interest rates on
10-year government treasury bond, consumer and business confidence index
and share price index. Using frequency domain time-series methods
singular~ (SSA) and multichannel singular spectrum analysis (MSSA), we
test the impact of big data statistics on financial cycles forecasting.
Our results show that policymakers can obtain better macro-aggregates to
use in financial cycles forecasting and thus better forecasting accuracy
and validity. Assuring better information support and prognosis on
financial cycles can help economic agents in the decision-making process
on financial markets. In the same time, using relevant micro-financial
data improve the relevance of macro-financial aggregates. Financial
cycles reflect fluctuations in macro-financial aggregates. Thus, more
precise measurement and identification of financial cycles support
central bank policies meeting information needs for price and
macro-financial stability. Comparing the forecasting results in this
study, we can see that the results of the~\hyperref[csl:16]{(Diebold et al. 1995)} test
support the hypothesis that more accurate forecasting of the financial
cycles can be obtained using financial big data. Big data financial
cycles can serve the purpose of developing early warning signals of
financial distress as financial crisis predictor. Since more
contemporary studies show financial conditions articulate real economic
activity dynamics and thus business cycles, understanding the true
nature of the financial cycles is of crucial importance for unravelling
business cycles. Our study results in financial big data can have an
essential role in this attempt.~~
The rest of the papers is structured as follows: after the introduction
on financial cycles and big data link, literature with interest in
financial big data is presented. In section three, we describe data used
in the study and methodology we apply to obtain the results on tested
hypothesis. Empirical results discussion and implications are presented
in section four, while part five bring up conclusions on the role and
importance of financial big data for financial and economic stability
analysis.~
\par\null
\section*{\texorpdfstring{`Financial Big Data' Implication for Financial
Cycles: A
Review}{Financial Big Data Implication for Financial Cycles: A Review}}
{\label{127577}}\par\null
The literature on the importance of financial big data for financial
cycles measurement is novel and scarce.~\hyperref[csl:17]{(Hassani et al. 2015)} offer a
review of the pros and cons of using big data for the purpose of
forecasting.~\hyperref[csl:18]{(Alessi et al. 2009)} study show large macroeconomic and
financial data improve forecast performance in finance and
economics.~\hyperref[csl:19]{(Altissimo et al. 2010)} provide evidence of using big data to
improve the forecast accuracy when using band-pass filters. Using data
from the google trends in the study of~\hyperref[csl:20]{(Choi et al. 2012)} improve the
forecasting prediction for economic indicators.~\hyperref[csl:21]{(Gupta et al. 2014: 229–264)}~
forecast employment using classical and Bayesian methods applied to
eight sectors for the US economy with 143 monthly series. Forecast model
using big data information outperform other models in forecast
accuracy.~
Large data sets (big data) availability is essential but not sufficient
condition for improving forecast accuracy or model
predictions~\hyperref[csl:22]{(Silver 2012)}.~\hyperref[csl:23]{(Ba{\'{n}}bura et al. 2014)} find forecasting
with large datasets more complex for the purpose of signal extraction.~
To fully understand financial cycles we need big data on the micro and
macro level.~\hyperref[csl:24]{(Wibisono et al. 2019: 970)}~
define big data as a large volume of information resulting from the web,
financial, administrative and commercial records. They find the
financial big data phenomenon as a new opportunity for decision-making
process improvement (complete, immediate and granural information adding
new value to `traditional' macroeconomic indicators). Therefore, big
data analytics and artificial intelligence offer new opportunities to
central banks and economic agents on the financial markets.
Opportunities but challenges as well (resources availability, unresolved
changing decision-making processes, best policy
introduction).~\hyperref[csl:25]{(Subrahmanyam 2019)}~review the body of literature on big
data in the finance application.~ Big data application in finance ranges
from the basic application as in~\hyperref[csl:26]{(TETLOCK 2007: 1139–1168)} to
complex~\hyperref[csl:27]{(Tetlock et al. 2008)}. According to their study, text analysis in
the financial press capture hard-to-quantify aspects of firms'
fundamental supporting robust low firm' earning forecasting. Big data
based on quantifying language application can help to improve methods
for measuring firms' fundamentals or forecast market trends. Big data in
finance also help to fill in the gap between qualitative and
quantitative data application~\hyperref[csl:28]{(Huang 2018: 164–182)}. His study results
show big data on consumers opinions (from Amazon. com) when used provide
a more robust prediction about firms' cash flow and stock
pricing.~~\hyperref[csl:29]{(Chordia et al. 2018: 4650–4687)}~ show that using newsfeed data on
macroeconomic conditions only minorly increase profits from fast
trading. According to the study of~\hyperref[csl:30]{(Fan et al. 2012: 412–428)}, using
high-frequency financial data improve the efficiency and stability of
portfolio selection. The literature on big data application for policy
purpose is much more limited~\hyperref[csl:31]{(Tissot 2019: 1–21)}. He lists the
advantages and disadvantages of using financial big data to obtain
macro-relevant micro information, better macro aggregates to improve
policy design and assessment.~
Financial big data opened its way to portfolio and decision making
processes on the micro-level and it is just moving (slowly) on the
macro-level (central banks and financial authorities).~
\par\null
\section*{Dataset and Stylized Facts on Financial Cycles in the UK, USA,
Japan and China 2005 -
2019}
{\label{381762}}
Our paper is first to combine financial big data for the purpose of
financial cycles predictions. We follow~~\hyperref[csl:24]{(Wibisono et al. 2019: 970)}~definition
of financial big data and use the following variables:~
\begin{itemize}
\tightlist
\item
HPI =~Residential property prices selected - Real - Index, 2010 = 100,
Bank for International Settlements
\item
CRS =~Credit to Private non-financial sector from all sectors at
Market value - Percentage of GDP - Adjusted for breaks, Bank for
International Settlements
\item
CRT =~Credit to Private non-financial sector from all sectors at
Market value - US dollar - Adjusted for breaks, Bank for International
Settlements
\item
SHARE =~OECD (2019), Share prices (indicator). doi:
10.1787/6ad82f42-en (Accessed on 29 October 2019), 2015=100
\item
CCI =~OECD (2019), Consumer confidence index (CCI) (indicator). doi:
10.1787/46434d78-en (Accessed on 30 October 2019), Long-term
average=100
\item
BCI =~OECD (2019), Business confidence index (BCI) (indicator). doi:
10.1787/3092dc4f-en (Accessed on 30 October 2019), Long-average=100
\item
WEB =~Google trends data on a financial crisis search term (Numbers
represent search interest relative to the highest point on the chart
for the given region and time. A value of 100 is the peak popularity
for the term. A value of 50 means that the term is half as popular. A
score of 0 means there was not enough data for this term)
\item
OECD (2019), Long-term interest rates (indicator). doi:
10.1787/662d712c-en (Accessed on 29 October 2019), Long-term interest
rates refer to government bonds maturing in ten years. For China we
use~China 10-Year Bond Yield government bonds maturing in ten years,
investing com,
\url{https://www.investing.com/rates-bonds/china-10-year-bond-yield-historical-data}.
\end{itemize}
We use data for the United Kingdom (UK), United States (US), Japan (Jap)
and China (CHI) from Q1 2004 to Q1 2019 (quarterly data).~ Previous
studies on financial cycles use data on residential property prices,
credits to private non-financial sectors and credits to private
non-financial sectors share in the GDP (gross domestic product). Facing
limited data availability on financial conditions and web we had to
choose between longer time series and a variety of data sources. For the
purpose of testing the importance of financial big data in financial
cycles prediction, we use data from various sources: web-based
indicators - social networks (financial crisis search term importance),
financial market data (share prices, residential property prices,
credits), administrative data (consumer confidence index, business
confidence index, long-term interest rates), commercial data sets
(government bonds yields).~
To measure financial cycle components, we use spectral analysis
techniques - Eviews 10.0 adds-in for Spectral
analysis~\hyperref[csl:32]{(Ronderos 2014)}. Prior to analysis, we normalize and centre
all the series for the purpose of eliminating noise in the series. Since
normalization procedure increases the possibility of spurious cycles
existence in the series, we apply~\hyperref[csl:32]{(Ronderos 2014)} significant pass
filter (SPF) method of the form:
\(F_{t}=\sum_{k=0}^{n / 2}\left[A_{k} \cos \left(\omega_{k} t\right)+B_{k} \sin \left(\omega_{k} t\right)\right]\)(1)
with F\textsubscript{t} = filtered series,~\((A_{k}=a_{k}), (B_{k}=b_{k}) ordinate (I\left(\omega_{k}\right))\) to test
statistical significance of the deterministic component in the spectrum.
\par\null
To test if the isolated deterministic cycles are statistically
significant we employ the following set of tests \hyperref[csl:32]{(Ronderos 2014)},
\hyperref[csl:33]{({William Wei} 1994)}, \hyperref[csl:34]{(Whittle 1952: 309)}, \hyperref[csl:35]{(Fisher 1929: 54–59)},
\hyperref[csl:36]{(Bartlett 1954: 296–298)}:
F test~~\(F=\frac{\left(a_{k}^{2}+b_{k}^{2}\right) / \nu_{1}}{\sum_{j=1, j \neq k}^{n / 2}\left(a_{j}^{2}+b_{j}^{2}\right) / \nu_{2}} \sim F\left(\nu_{1}, \nu_{2}\right)\) (2)
Fisher test~~\(T=\frac{\max \left\{I\left(\omega_{k}\right)\right\}}{\sum_{k=1}^{n / 2} I\left(\omega_{k}\right)}\) (3)
Whittle test~~\( T_{2}=\frac{I^{(2)}\left(\omega_{(2)}\right)}{\sum_{k=1}^{n / 2} I\left(\omega_{k}\right)-I^{(1)}\left(\omega_{(1)}\right)}\) (4)\selectlanguage{english}
\begin{figure}[H]
\begin{center}
\includegraphics[width=1.00\columnwidth]{figures/figure1/figure1}
\caption{{Spectrum of residential property prices, credit to private non-financial
sector, credit share in the GDP in the UK Q1 2005 - Q1 2019
{\label{114939}}%
}}
\end{center}
\end{figure}
Source: Authors' calculation
Figure 1 shows spectrum for the three financial series -~HPI
=~Residential property prices selected,~CRS =~Credit to Private
non-financial sector from all sectors at Market value - Percentage of
GDP,~CRT =~Credit to Private non-financial sector from all sectors at
Market value - US dollar in the UK. The shaded area shows deterministic
cycles between 0.016 and 0.032 frequencies (cycle/time unit)
corresponding to 61 and 31 quarters or 15 and 8 years period.\selectlanguage{english}
\begin{figure}[H]
\begin{center}
\includegraphics[width=1.00\columnwidth]{figures/figure2/figure2}
\caption{{Spectrum of residential property prices, credit to private non-financial
sector, credit share in the GDP in the USA Q1 2005 - Q1 2019~
{\label{139899}}%
}}
\end{center}
\end{figure}
Source: Authors' calculation
Figure 2 confirms the results we find for the UK. In the United States,
all three financial series show the same behaviour as in the UK. As we
can see from the figure 2, the grey area shows the statistically
significant component cycles which correspond to 8 and 15 years for the
residential property prices, credit to private non-financial sectors and
credit share in the GDP.~ Outside the area between 0.016 and 0.032
frequencies (cycle/time unit) corresponding to 61 and 31 quarters or 15
and 8 years period, we did not isolate important deterministic cycles.~\selectlanguage{english}
\begin{figure}[H]
\begin{center}
\includegraphics[width=1.00\columnwidth]{figures/figure3/figure3}
\caption{{This is a Spectrum of residential property prices, credit to private
non-financial sector, credit share in the GDP in Japan Q1 2005 - Q1
2019~caption
{\label{232179}}%
}}
\end{center}
\end{figure}
Figure 3 shows more variability in the housing and financial markets in
Japan. Although we can observe several possible deterministic cycles in
the housing and financial markets in Japan statistical tests shows
statistically significant cycles in the financial series are present
within 8 and 15 years. Thus, results for Japan are in line with the one
we observe for the UK and the US. F test, Fisher test and Whittle test
confirm the statistical significance of the deterministic cycles between
8 to 15 years.~\selectlanguage{english}
\begin{figure}[H]
\begin{center}
\includegraphics[width=1.00\columnwidth]{figures/figure4/figure4}
\caption{{This is a Spectrum of residential property prices, credit to private
non-financial sector, credit share in the GDP in China Q1 2005 - Q1
2019~
{\label{461894}}%
}}
\end{center}
\end{figure}
Volatility on the housing and financial markets in China is more similar
to the dynamics we find in Japan. Large volatility, as expected to be
present, is visible on the housing market in China. Such price dynamics
on the housing market is expected as a consequence of the changes in the
Hukou system (policy regulated migration from the countryside to the
cities) having a direct influence on the demand for housing in China.
Housing demand dynamics is reflected in the credit demand (mortgage
loans) that is observed in figure 4 (graph on the right). Cyclical
fluctuations both for housing prices and credit to the private
non-financial sector is statistically significant for the cycle period
between 8 to 15 years. The cyclical fluctuation on the credit market (\%
share in the GDP) after testing for deterministic cycles also exhibits
an 8 to 15 years pattern with smaller volatility in comparison to the
volatility on the housing market and credit to a private non-financial
sector (volume).~
Deterministic cycle test results validate the results of the previous
studies on financial cycles finding a cyclical pattern in the financial
time series ranging from 8 to 15 years on average for the UK, USA, Japan
and China. After the financial cycles identification by the means of
spectral analysis, we proceed by testing if Big data can help to improve
the financial cycles forecasting.
\par\null
\section*{Using Financial Big Data for Improving Financial Cycles
Forecasting
Accuracy}
{\label{651868}}
To test the hypothesis that financial big data improve financial cycles
forecasting we proceed in several steps. First by the means of the
singular spectrum analysis (SSA) of the form~\hyperref[csl:37]{(Vautard et al. 1992: 95–126)}
\(c_{i j}=\frac{1}{N-|i-j|} \sum_{t=1}^{N-|i-j|} X(t) X(t+|i-j|)\)(5)
where
c\textsubscript{ij} = lag covariance matrix
N = number of data points in time series
i,j = time indices
t = continuous time t [?] R
x(t) = observed time series.
using data on housing prices and credits we isolate financial cycles for
the UK, USA, Japan and China. Following on the isolate (SSA) components,
we apply a linear recurrent formula for the purpose of (SSA)
forecasting. As a final outcome, we get an R-forecasting (SSA
forecasting method) for~residential property prices, credit to the
private non-financial sector, credit share in the GDP over the eight
quarters (2017Q2 2019Q1).
To check if financial big data can help in raising the financial cycles
forecasting efficiency, we apply
(MSSA) of the form~\hyperref[csl:38]{(Ghil et al. 2002)} on~residential property prices,
credit to private non-financial sector, credit share in the GDP:
\par\null
\(\begin{array}{l}{\left(C_{l, l^{\prime}}\right)_{i, j}=\frac{1}{\bar{N}} \sum_{t=\min \left(1,1,1^{\prime}+i-j\right)}^{\max (N+i-j)} x_{l}(t) x_{l^{\prime}}(t+i-j)} \\ {\widetilde{N}=\min \{N, N+i-j\}-\max \{1,1+i-j\}+1}\end{array}\)(6)
where
c\textsubscript{ij} = lag covariance matrix
cl,l\textsubscript{j} =lag cross-covariance matrix
N = number of data points in a time series
i,j = indices of time
t = continuous time t [?] R
x(t) = L-channel vector time series.
As in the case of (SSA), using the R-forecasting (MSSA forecasting
method) we now get the (MSSA) forecasting results (forecasting including
financial big data) for the residential property prices, credit to
private non-financial sector, credit share in the GDP over the period
2017Q2 - 2019Q1.~
To test the improved accuracy (better forecasting results) we obtain
when using financial big data we use the Diebold - Mariano
test~\hyperref[csl:16]{(Diebold et al. 1995}; \hyperref[csl:39]{Diebold 2015)} of the form:
\(D M_{12}=\frac{\bar{d}_{12}}{\hat{\sigma}_{\bar{d}_{12}}} \rightarrow N(0,1)\) (7)
where~~
\(\bar{d}_{12}=\frac{1}{T} \sum_{t=1}^{T} d_{12 t}\) = sample means loss differential
\(\hat{\sigma}_{\bar{d}_{12}}\)= consistent estimate of standard deviation.
Diebold - Mariano test results confirm our hypothesis that financial big
data improve forecasting accuracy for financial cycles (see table 1 for
the UK).~\selectlanguage{english}
\begin{table}[H]
\centering
\normalsize\begin{tabulary}{1.0\textwidth}{CCCCC}
& RMSE & MAE & MAPE & SMAPE \\
SSA & 0.33 & 0.28 & 27.58 & 33.41 \\
MSSA & 0.29 & 0.25 & 23.98 & 28.38 \\
Residential property prices & & & & \\
SSA & 0.37 & 0.26 & 33.43 & 36.09 \\
MSSA & 0.3 & 0.2 & 25.61 & 26.9 \\
Credit to private non-financial sector & & & & \\
SSA & 0.44 & 0.39 & 289.35 & 164.75 \\
MSSA & 0.33 & 0.27 & 239.18 & 145.67 \\
Credit share in the GDP & & & & \\
\end{tabulary}
\caption{{Forecast Accuracy for the SSA, MSSA for Financial Series in the UK
2017Q2 - 2019Q1
{\label{311509}}%
}}
\end{table}From the table 1, we can see that various measures for forecast
accuracy, (RMSE - root mean square error), (MAE - mean square error),
(MAPE - mean absolute percentage error), (SMAPE - symmetric mean
absolute percentage error) for the financial series in the UK from
2017Q2 to 2019Q1. The scores from table 1 show that the (MSSA) forecasts
(including financial big data) are superior to the (SSA) forecasts (not
including financial big data). We can observe that forecasts we obtain
using (MSSA) for the period 2017Q2 - 2019Q1 (out of the sample forecasts
since we use a sample for the forecasting accuracy comparison from
2004Q1 to 2017Q1) for the~residential property prices, credit to private
non-financial sector, credit share in the GDP in the UK are far superior
to the one we obtain using (SSA). Taking into account financial big data
improves forecasting accuracy for financial series in the UK. Similar
results we observe in the case of the USA (see table 2).~\selectlanguage{english}
\begin{table}[H]
\centering
\normalsize\begin{tabulary}{1.0\textwidth}{CCCCC}
& RMSE & MAE & MAPE & SMAPE \\
SSA & 0.16 & 0.14 & 26.22 & 31.03 \\
MSSA & 0.1 & 0.08 & 17.85 & 18.47 \\
Residential property prices & & & & \\
SSA & 0.46 & 0.38 & 60.29 & 101.11 \\
MSSA & 0.34 & 0.29 & 46.19 & 67.66 \\
Credit to private non-financial sector & & & & \\
SSA & 0.29 & 0.25 & 14.81 & 15.2 \\
MSSA & 0.25 & 0.22 & 13.63 & 13.42 \\
Credit share in the GDP & & & & \\
\end{tabulary}
\caption{{Forecast Accuracy for the SSA, MSSA for Financial Series in the USA
2017Q2 - 2019Q1
{\label{961702}}%
}}
\end{table}As table 2 shows, forecast accuracy scores for residential property
prices show (MSSA using financial big data) significantly increase. A
significant increase in the forecast accuracy of (MSSA) also is present
for the credit to private non-financial sector time-series data. Still
statistically significant but with lower forecast accuracy in relation
to the (MSSA) forecasts for the residential property prices and credit
to the private non-financial sector is the forecast accuracy for the
credit share in the GDP. We can conclude that statistical tests for
forecast accuracy show financial time series (financial cycle
components) can be better forecast when using financial big data in the
USA.
\par\null
For Japan (see table 3), we can also observe that forecast accuracy for
the financial cycle components increase if we use financial big data in
the forecast process. Statistical test (forecast accuracy scores) show
that we can make more accurate forecasts for residential property prices
in Japan using financial big data. The same holds for the credit to
private non-financial sector time series data with accuracy scores in
favor of using (MSSA) for forecasting. We can notice a significant
increase in the forecast accuracy for the credit share in the GDP time
series data with residual errors being 2 to 3 times lower if we use
financial big data and (MSSA) for forecasting.~\selectlanguage{english}
\begin{table}[H]
\centering
\normalsize\begin{tabulary}{1.0\textwidth}{CCCCC}
& RMSE & MAE & MAPE & SMAPE \\
SSA & 0.38 & 0.28 & 59.77 & 34.64 \\
MSSA & 0.32 & 0.24 & 54.01 & 31.7 \\
Residential property prices & & & & \\
SSA & 0.4 & 0.34 & 52.18 & 74.63 \\
MSSA & 0.3 & 0.26 & 114.02 & 52.45 \\
Credit to private non-financial sector & & & & \\
SSA & 0.73 & 0.66 & 256.54 & 160.17 \\
MSSA & 0.26 & 0.24 & 74.18 & 104.32 \\
Credit share in the GDP & & & & \\
\end{tabulary}
\caption{{Forecast Accuracy for the SSA, MSSA for Financial Series in Japan 2017Q2
- 2019Q1
{\label{844513}}%
}}
\end{table}Table 4 show forecast accuracy scores for the (SSA) and (MSSA) in
forecasting financial cycle components in China.~\selectlanguage{english}
\begin{table}[H]
\centering
\normalsize\begin{tabulary}{1.0\textwidth}{CCCCC}
& RMSE & MAE & MAPE & SMAPE \\
SSA & 1.51 & 1.2 & 64.79 & 111.03 \\
MSSA & 0.81 & 0.7 & 39.62 & 51.4 \\
Residential property prices & & & & \\
SSA & 0.61 & 0.53 & 31.03 & 33.03 \\
MSSA & 0.46 & 0.44 & 28.35 & 26.27 \\
Credit to private non-financial sector & & & & \\
SSA & 0.25 & 0.19 & 12.01 & 11.42 \\
MSSA & 0.24 & 0.18 & 12.05 & 11.04 \\
Credit share in the GDP & & & & \\
\end{tabulary}
\caption{{Forecast Accuracy for the SSA, MSSA for Financial Series in China 2017Q2
- 2019Q1
{\label{847809}}%
}}
\end{table}Forecast accuracy for residential property prices in China improves
significantly when we use financial big data for forecasting in relation
to the results we obtain without these data. We can see from table 4
that all forecast accuracy scores prove the validity of this statement.
For the credit to private non-financial sector time series forecast
accuracy when using financial big data improves as well (on a smaller
scale when compared to the forecast accuracy for the residential
property prices). The same result holds for the credit share in the GDP
series with forecast accuracy using financial big data (MSSA) outperform
the forecast produces by (SSA) without financial big data.~
Forecast accuracy tests and scores show on the sample for the UK, USA,
Japan and China (four growth potential economies quite different in
structure and size) that financial big data can significantly improve
forecasting of the financial cycle components (residential property
prices, credit to private non-financial sector and credit share in the
GDP).~
\par\null
\section*{Conclusion}
{\label{905822}}
This study has demonstrated that using financial big data significantly
improve the forecast accuracy for financial cycle components
(residential property prices, credit to private non-financial sector and
credit share in the GDP). The forecast test results show on the data for
the UK, USA, Japan and China that inclusion of the financial big data
significantly (on the level from 30\% to four times) improves forecast
accuracy for financial cycle components. This is the first study to
examine the role of the financial big data in the study of financial
cycles. Inclusion of the financial big data in the various model (time
series, frequency domain, turning point, multiple cycles) aiming at
measuring the exact length of financial cycles. Such a knowledge
(financial big data) will help to better understand the mechanism behind
financial cycles, methods and tools for their monitoring and
forecasting. Policymakers and central banks motivated to mitigate the
risks of the financial cycles will find this knowledge useful in
building new models for financial cycles detection and forecasting.~
The lack of studies using financial big data for measuring and
forecasting financial cycles may indicate that policymakers,
practitioners and academics do not find the link between financial big
data and financial cycles important or promising. Another plausible
explanation is that financial big data from their point of view serve
the purpose of forecasting financial conditions~\hyperref[csl:25]{(Subrahmanyam 2019)},
market portfolio selection~\hyperref[csl:30]{(Fan et al. 2012: 412–428)}, equity prices
forecasting, mitigating risks and volatility on the financial markets.
Although all these issues are important for financial
studies~\hyperref[csl:18]{(Alessi et al. 2009)}, no previous study on the link between
financial cycles and big data exists.~
Our analysis suggests research on financial cycles can be significantly
improved if the financial big data are used in the research. The Diebold
- Mariano test result confirms the validity of the hypothesis that
financial big data are important for measurement and forecasting of the
financial cycles. Our findings bring important insight to the
policymakers and financial practitioners and academic community as well
as interested in monitoring and studying the nature and consequence of
the financial cycles and their role in financial crisis and thus
business cycles.~
An important strength of our study is that we use several financial big
data (supporting the research of~\hyperref[csl:26]{(TETLOCK 2007: 1139–1168)} for a sample of four
countries reporting several forecast accuracy scores and Diebold-Mariano
test results. However, since financial big data are not available in a
long time series form, we use a limited-time series sample. Furthermore,
research results should be validated for a larger sample of countries
that could bring additional insight into the research question.~
In our sample, all forecast accuracy statistics and Diebold-Mariano test
results put forward a single, statistically validated conclusion -
financial big data are an important element for studying financial
cycles. We encourage further research to clearly distinguish whether
financial cycles research is based on financial big data; identify the
most important sources of such data (statistical robustness), and become
familiar with developing new study models on financial cycles using
financial big data.~
\par\null
\selectlanguage{english}
\FloatBarrier
\section*{References}\sloppy
\phantomsection
\label{csl:18}Alessi L., Barigozzi M., Capasso M., Others 2009. {Forecasting large datasets with conditionally heteroskedastic dynamic common factors}, \textit{European Central Bank Working Paper} 1115.
\phantomsection
\label{csl:19}Altissimo F., Cristadoro R., Forni M., Lippi M., Veronese G. 2010. {New Eurocoin: Tracking economic growth in real time}, \textit{Review of Economics and Statistics}. DOI: 10.1162/REST_a_00045 .
\phantomsection
\label{csl:36}Bartlett M.S. 1954. {A note on the multiplying factors for various {\$}\chi{\$} 2 approximations}, \textit{Journal of the Royal Statistical Society. Series B (Methodological)}: 296–298.
\phantomsection
\label{csl:23}Ba{\'{n}}bura M., Modugno M. 2014. {Maximum likelihood estimation of factor models on datasets with arbitrary pattern of missing data}, \textit{Journal of Applied Econometrics}. DOI: 10.1002/jae.2306 .
\phantomsection
\label{csl:7}Borio C., Drehmann M. 2011. {Financial Instability and Macroeconomics: Bridging the Gulf}, : 237–268. DOI: 10.1142/9789814322096_0017 .
\phantomsection
\label{csl:20}Choi H., Varian H. 2012. {Predicting the Present with Google Trends}, \textit{Economic Record}. DOI: 10.1111/j.1475-4932.2012.00809.x .
\phantomsection
\label{csl:29}Chordia T., Green T.C., Kottimukkalur B. 2018. {Rent Seeking by Low-Latency Traders: Evidence from Trading on Macroeconomic Announcements}, \textit{The Review of Financial Studies} 31(12): 4650–4687. DOI: 10.1093/rfs/hhy025 .
\phantomsection
\label{csl:39}Diebold F.X. 2015. {Comparing Predictive Accuracy, Twenty Years Later: A Personal Perspective on the Use and Abuse of Diebold–Mariano Tests}, \textit{Journal of Business and Economic Statistics}. DOI: 10.1080/07350015.2014.983236 .
\phantomsection
\label{csl:16}Diebold F.X., Mariano R.S. 1995. {Comparing predictive accuracy}, \textit{Journal of Business and Economic Statistics}. DOI: 10.1080/07350015.1995.10524599 .
\phantomsection
\label{csl:8}Drehmann M., Borio C., Tsatsaronis K. 2012. {Characterising the Financial Cycle: Don't Lose Sight of the Medium Term!}, \textit{BIS Working Papers} (380): 1–38. DOI: DOI: .
\phantomsection
\label{csl:9}Drehmann M., Borio C., Tsatsaronis K. 2013. {Can We Identify the Financial Cycle?} In \textit{World Scientific Studies in International Economics}. {WORLD} {SCIENTIFIC}. DOI: 10.1142/9789814449922_0007 .
\phantomsection
\label{csl:30}Fan J., Li Y., Yu K. 2012. {Vast Volatility Matrix Estimation Using High-Frequency Data for Portfolio Selection}, \textit{Journal of the American Statistical Association} 107(497): 412–428. DOI: 10.1080/01621459.2012.656041 .
\phantomsection
\label{csl:35}Fisher R.A. 1929. {Tests of significance in harmonic analysis}, \textit{Proceedings of the Royal Society of London. Series A, Containing Papers of a Mathematical and Physical Character} 125(796): 54–59.
\phantomsection
\label{csl:38}Ghil M., et al. 2002. {Advanced spectral methods for climatic time series}, \textit{Reviews of Geophysics}. DOI: 10.1029/2000RG000092 .
\phantomsection
\label{csl:21}Gupta R., Kabundi A., Miller S.M., Uwilingiye J. 2014. {Using large data sets to forecast sectoral employment}, \textit{Statistical Methods {\&} Applications} 23(2): 229–264.
\phantomsection
\label{csl:17}Hassani H., Silva E.S. 2015. {Forecasting with Big Data: A Review}, \textit{Annals of Data Science}. DOI: 10.1007/s40745-015-0029-9 .
\phantomsection
\label{csl:12}Hiebert P., Klaus B., Peltonen T.A., Sch{\"{u}}ler Y.S., Welz P. 2014. {Capturing the financial cycle in euro area countries}, \textit{ECB Financial Stability Review} (November): 109–117Prieiga per internetą: \url{http://www.group30.org/images/PDF/Macroprudential{\_}Report{\_}Final.pdf.}
\phantomsection
\label{csl:28}Huang J. 2018. {The customer knows best: The investment value of consumer opinions}, \textit{Journal of Financial Economics} 128(1): 164–182. DOI: 10.1016/j.jfineco.2018.02.001 .
\phantomsection
\label{csl:3}Keynes J.M. 1936. \textit{{The general theory of employment, interest and money}}London : Macmillan, 1936.Prieiga per internetą: \url{https://search.library.wisc.edu/catalog/999623618402121.}
\phantomsection
\label{csl:2}Milburn O. 2007. {The book of the young master of accountancy: An ancient Chinese economics text}, \textit{Journal of the Economic and Social History of the Orient}. DOI: 10.1163/156852007780324002 .
\phantomsection
\label{csl:5}Minsky H.P. 1963. {Can 'it' happen aggain?} In D. Carson, ed. \textit{Banking and Monetary Studies}. , Illinois: Homewood.
\phantomsection
\label{csl:6}Minsky H.P. 1975. \textit{{John Maynard Keynes}}, New York: Columbia University Press.
\phantomsection
\label{csl:1}Phillips A.W. 1962. {Employment, Inflation and Growth}, \textit{Economica}. DOI: 10.1111/j.1468-0335.1962.tb00001.x .
\phantomsection
\label{csl:32}Ronderos N. 2014. {Spectral Analysis using EViews}Prieiga per internetą: \url{https://www.eviews.com/Addins/SpectralAnalysis.aipz.}
\phantomsection
\label{csl:13}R{\"{u}}nstler G., Vlekke M. 2018. {Business and Financial Cycles : an Unobserved Components Models Perspective}, \textit{Journal of Applied Econometrics} 33(2): 212–226.
\phantomsection
\label{csl:4}Schumpeter J.A. 1939. \textit{{Business Cycles: A Theoretical, Historical, and Statistical Analysis of the Capitalist Process}} First, New York: McGraw-Hill.
\phantomsection
\label{csl:10}Sch{\"{u}}ler Y.S., Hiebert P.P., Peltonen T.A. 2015. {Characterising the financial cycle: a multivariate and time-varying approach}, \textit{ECB Working Paper Series}.
\phantomsection
\label{csl:22}Silver N. 2012. \textit{{The Signal and the Noise: Why So Many Predictions Fail-but Some Don't}}Penguin Publishing Group.Prieiga per internetą: \url{https://books.google.hr/books?id=SI-VqAT4{\_}hYC.}
\phantomsection
\label{csl:15}Skare M., Rochon M.P. 2019. {Multi-channel Singular-Spectrum Analysis (MSSA) of Financial Cycles in Ten Developed Economies 1970-2018}, \textit{Journal of Business Research} Forthcoming.
\phantomsection
\label{csl:11}Strohsal T., Proa{\~{n}}o C.R., Wolters J. 2019. {Characterizing the financial cycle: Evidence from a frequency domain analysis}, \textit{Journal of Banking and Finance} 49(0). DOI: 10.1016/j.jbankfin.2019.06.010 .
\phantomsection
\label{csl:14}Strohsal T., Proa{\~{n}}o C.R., Wolters J. 2019. {Characterizing the financial cycle: Evidence from a frequency domain analysis}, \textit{Journal of Banking and Finance}. DOI: 10.1016/j.jbankfin.2019.06.010 .
\phantomsection
\label{csl:25}Subrahmanyam A. 2019. {Big Data in Finance: Evidence and Challenges}, \textit{Borsa Istanbul Review}.
\phantomsection
\label{csl:26}TETLOCK P.A.U.L.C. 2007. {Giving Content to Investor Sentiment: The Role of Media in the Stock Market}, \textit{The Journal of Finance} 62(3): 1139–1168. DOI: 10.1111/j.1540-6261.2007.01232.x .
\phantomsection
\label{csl:27}Tetlock P.C., Saar-Tsechansky M., Macskassy S. 2008. {More Than Words: Quantifying Language to Measure Firms' Fundamentals}, \textit{Journal of Finance}. DOI: 10.1111/j.1540-6261.2008.01362.x .
\phantomsection
\label{csl:31}Tissot B. 2019. {Financial big data and policy work: opportunities and challenges}, : 1–21. DOI: 10.2785/093952 .
\phantomsection
\label{csl:37}Vautard R., Yiou P., Ghil M. 1992. {Singular-spectrum analysis: A toolkit for short, noisy chaotic signals}, \textit{Physica D: Nonlinear Phenomena} 58(1-4): 95–126. DOI: 10.1016/0167-2789(92)90103-T .
\phantomsection
\label{csl:34}Whittle P. 1952. {Tests of Fit in Time Series}, \textit{Biometrika} 39(3/4): 309. DOI: 10.2307/2334027 .
\phantomsection
\label{csl:24}Wibisono O., Ari H.D., Widjanarti A., Zulen A.A., Tissot B. 2019. {The use of big data analytics and artificial intelligence in central banking} In \textit{Proceedings of the IFC – Bank Indonesia International Workshop and Seminar in Bali on 23-26 July 2018}. Irving Fisher Committee on Central Bank Statistics.
\phantomsection
\label{csl:33}{William Wei} W.S. 1994. {Time Series Analysis. Univariate and Multivariate Methods}, \textit{Ed. Addison Wesley, California, Redwood}.
\end{document}