Finance, Markets and Valuation
DOI:
10.46503/LHTP1113
Corresponding author
Fernando García
Received: 10 Sep 2020
Revised: 22 Oct 2020
Accepted: 11 Nov 2020
Finance, Markets and
Valuation
ISSN 2530-3163.
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Leading research trends on trading strategies
Tendencias líderes de investigación sobre estrategias de
trading
Javier Oliver-Muncharaz
ID
1
, Fernando García
ID
2
1
Departamento de Economía y Ciencias Sociales, Universidad Politécnica de Valencia. Valencia,
España. Email: jaolmun@ade.upv.es
2
Departamento de Economía y Ciencias Sociales, Universidad Politécnica de Valencia. Valencia,
España. Email: fergarga@esp.upv.es
JEL: G10; G17
Abstract
Trading strategies have attracted the attention of academic researchers and practitioners for a long time,
but most specially in recent years due to the explosion of high-quality databases and computation capac-
ity. Numerous studies are devoted to the analysis and proposal of trading strategies which cover aspects
such as trend prediction, variables selection, technical analysis, pattern recognition etc. and apply many
dierent methodologies. This paper conducts a meta-literature review which covers 1187 research ar-
ticles from 1984 to 2020. The aim of this paper is to show the increasing importance of the topic and
present a systematic study of the leading research areas, countries, institutions and authors contribut-
ing to this field. Moreover, a network analysis to identify the main research streams and future research
opportunities is conducted.
Keywords: Trading strategy; Literature survey; Stock market
Resumen
La creación de estrategias de inversión siempre ha atraído la atención de los académicos y de los inver-
sores profesionales, pero, indudablemente, esta popularidad ha aumentado en los últimos años, con la
aparición de bases de datos más completas y mayor potencia de cálculo de las computadoras. Son nu-
merosos los estudios que analizan y proponen estrategias de inversión y que tratan aspectos como la
predicción de la tendencia, la selección de variables, el análisis técnico, el reconocimiento de patrones
etc. aplicando diferentes metodologías. En este trabajo se realiza un estudio bibliográfico que abarca
1187 artículos de investigación desde 1984 hasta 2020. El objetivo es mostrar la creciente importancia
de este campo de investigación y presentar un análisis sistemático de los países, instituciones y autores
que más están contribuyendo al avance del conocimiento. Además, se realiza un análisis de redes para
identificar las principales áreas de investigación y las tendencias futuras.
Keywords: Estrategia de inversión; Revisión bibliográfica; Mercado bursátil
How to cite this paper: Oliver-Muncharaz, J. and García, F. (2020) Leading research trends on trading
strategies. Finance, Markets and Valuation 6(2), pp. 27–54.
27
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
1 Introduction
In the last decades, the importance of the financial markets has increased dramatically all over
the globe. Many investors approach the dierent financial markets, such as the stocks markets,
bonds markets, foreign exchange market, etc.; seeking for a high and rapid return. Therefore,
not just big mutual fund managers but also individual investors and academics, of course, are
interested in the development of robust trading strategies which make it possible to beat the
market and obtain high yields.
Investors can use dierent approaches to manage their wealth. Do investors believe that the
market is eicient, that is, that it is not possible to beat the market in terms of return and risk,
then they choose a passive portfolio strategy (F. García & Guijarro, 2011). In this case, investors
replicate a stock index buying Exchange Trading Funds (ETF) or implementing partial index
tracking methodologies (Baccarin & Marazzina, 2015; F. García, Guijarro, & Moya, 2011, 2013;
F. García, Guijarro, & Oliver, 2017; Papantonis, 2016). There are many stock indices available,
so investors can decide which specific market they want to track. Currently, sustainable stock
indices are gaining popularity, as investors are more concerned with corporate social responsi-
bility issues (Arribas, Espinós-Vañó, García, & Morales-Bañuelos, 2019; Arribas, Espinós-Vañó,
García, & Tamoši
¯
unien
˙
e, 2019) or as they believe that sustainable companies have a better
performance (F. García, González-Bueno, Guijarro, & Oliver, 2020; Maciková, Smorada, Dorčák,
Beug, & Markovič, 2018; Simionescu & Dumitrescu, 2018). Nevertheless, investors should pay
attention to the index construction methodology to make sure the assets in the index really
match their interest (Arribas, Espinós-Vañó, García, & Oliver, 2019). Passive portfolio strategies
are specially recommended for long term investments or for markets with a very strong trend.
Active portfolio management is opposite to passive management. In this case, investors
believe that it is possible to beat the markets consistently. Usually, investors pick up a number
of assets to build their portfolio in order to maximize return and minimize risk. This investment
strategy was introduced by Markowitz (Markovitz, 1959) and has been further developed by
many other researchers (García, González-Bueno, Oliver, & Riley, 2019; F. García, González-
Bueno, Guijarro, & Oliver, 2020; F. García, González-Bueno, Guijarro, Oliver, & Tamoši
¯
unien
˙
e,
2020).
Finally, investors may not be interested in portfolio management, but concentrate on a
small number of assets and apply short-term strategies to speculate with the evolution of asset
prices. In this case, investors are interested in determining the market trend (F. García, Guijarro,
Oliver, & Tamoši
¯
unien
˙
e, 2018) or use trading rules based on pattern recognition or technical
analysis (Arévalo, García, Guijarro, & Peris, 2017; Cervelló-Royo, Guijarro, & Michniuk, 2015).
In this paper, we will analyze the raise of research papers devoted to the last topic, the
speculative use of short-term trading strategies. This research field has experienced a boom
since in the last decade databases cover more years and more assets, computation capacity has
improved considerably, and artificial intelligence has been further developed. In this context, it
is useful to gain an overview of the research field and identify the major actors and the most
attractive topics. To achieve our goal, we conduct a bibliometric analysis of a corpus including
1,187 research papers included in the Web of Science database.
The remainder of the paper is structured as follows: In the next section we describe the
methodology and the sample selection process, then we present the results of the dierent
analysis performed and finally we summarize the main outcomes in the conclusions section.
Javier Oliver-Muncharaz and Fernando García 28
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
2 Research methodology
The aim of this research is to identify and evaluate the existing body of research in the field of
trading strategies to get a precise picture of the most influential papers, authors, institutions
and journals. To this end, we conduct a citation and co-citation analysis. Finally, we find out
which are the main topics and research interests in the field, which can be helpful to suggest
future lines of research.
To achieve these goals, we apply both quantitative and qualitative techniques. First, we
apply a structured literature review for data collection and data evaluation in order to collect
the most influential papers, those with the highest impact in this field and to figure out the
topics which have attracted researchers’ interest the most. Second, a bibliometric analysis
is performed. Bibliometric analysis is suited to handle hundreds of papers and can provide a
comprehensive picture of the research field. Finally, we utilize a content analysis to investigate
the main areas of research. The bibliometric analysis conducted in this research has been
applied on various topics (Feng, Zhu, & Lai, 2017; Guijarro & Tsinaslanidis, 2020), but rarely on
the field of finance, with only a few exceptions in recent years, such as the paper by Bahoo, Alon,
and Paltrinieri (2020) devoted to sovereign wealth funds, the paper by Helbing (2019) which
reviews the literature on IPOs, and the article by Zamore, Djan, Alon, and Hobdari (2018) which
focuses on credit risk.
2.1 Sample selection
The first step in the data collection process consists on selecting the database to be used. In
this study, we choose ISI Web of Science (WoS) Core Collection, which is one popular database
and has a wide coverage of most prominent journals related with the topic of trading strategies.
This database has a powerful research engine and can conduct a number of interesting analysis.
In order to select the papers in the sample, we impose some conditions.: only research
papers are considered which are written in English. All research areas are eligible. We do not
include any condition regarding the timespan either, which lasts from 1900 until 2020.
Then, we search the papers using the topics “trading strategy” and “trading strategies”.
In order to more precisely focus the scope of the articles, we use following research strategy:
“trading strategy” or “trading strategies” and “stock market” not “portfolio”. Doing this, we
concentrate on those research articles which deal with the speculative use of short-term trading
strategies and erase from the database all papers applying portfolio selection strategies.
As the result of the searching strategy, 1,187 articles are saved (Table 1). The search results
include information for each article regarding title, authors and their ailiations, journal, year
of publication, volume and number, abstract, keywords, total cites received and cites per year,
as well as the reference list. Table 1 shows the main results of the searching strategy.
3 Descriptive analysis
In order to gain an overview of the selected sample, we conduct a preliminary descriptive
analysis. The sample includes 1,187 publications, which have been cited 17,369 times by 14,155
citing articles. The h-index of the sample is 65. The average citations per paper is 14.63.
Figure 1 shows the number of publications per year. The oldest paper was published in
1984 (Bilson, 1984). Then, several years past until the next paper was published in 1991. Since
then, the topic experiences an increasing trend, especially since year 2004. In our sample, in
year 2004 a total of 12 articles were published, compared to 158 in 2019. Interestingly, the last 3
years account for 34% of the publications, which is a sign of the increasing importance of the
Javier Oliver-Muncharaz and Fernando García 29
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Database Web of Science Core Collection
Timespan All years
Search date 27 October 2020
Search terms
“Trading strategy” OR “Trading strategies” AND “Stock market”
NOT “Portfolio”
Language English
Document type Article
Number of articles 1,187
Number of journals 418
Number of research areas 36
Number of authors 2,445
Table 1. Searching strategy and key figures
Figure 1. Total publications by year
Source: Web of Science
research in trading strategies at present.
The papers analyzed were published in 418 dierent journals. The 10 journals responsible
for the publication of the most papers in the field account for 20% of the total papers. Figure
2 shows the 10 top journals publishing in this research area. The most important journal
is “Quantitative Finance”, with 39 papers. The second most prominent journal is Journal of
Banking Finance, followed by Expert Systems with Applications, which have published 36 and
34 articles, respectively, according to the search in the Web of Science database.
Interestingly, manyof the journals which have been attracted by the topic are not specialized
in finance, but in mathematical methodologies. Therefore, it is worthy to investigate the
research areas involved in the study and development of trading strategies. As presented in
Figure 3, the papers have been published in journals assigned to dierent research areas. It
must be noted that a paper can simultaneously be assigned to more than one area. Most papers
have been assigned to the area of “Business Economics”, a total of 519. That means, 66% of the
papers dealing with trading strategies belong to this research area. The remaining areas have
not a direct relation with business, economics or finance, but with mathematics, computing
and engineering. In fact, the second most prominent area is “Mathematics” including 214
Javier Oliver-Muncharaz and Fernando García 30
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Figure 2. Top publishing journals contributing to the field of trading strategies
Source: Web of Science
papers and representing 18% of the sample, followed by “Computer science” (157 articles
representing 13% of the sample) and “Engineering” (100 articles representing 8% of the papers
in the sample). The remaining 6 areas are: “Operations research management science” (97
articles), “Mathematical methods in social science” (96 articles), “Physics” (54 articles), “Science
technology other topics” (27 articles), “Energy fuels” (22 articles) and “Telecommunications”
(58 articles). The 1,187 papers have been assigned to 36 dierent research areas. Although
most of the papers are assigned to the “Business Economics” area, it is noteworthy that many
other areas are also involved, especially those in the field of computing and mathematics. This
is surely related to the kind of quantitative research which is conducted currently regarding
trading strategies.
It is possible to use the Web of Science database to identify the authors who have published
the most articles in a specific field. Table 2 shows the 10 authors with the most publications
regarding trading strategies. Logically, the number of papers written by a single author is very
low compared with the total number of papers in the field and there are no dominant authors
in the field. In the selected sample of papers, there are 2,445 authors who have researched on
trading strategies. The author with the most publications is Hui ECM, who has published 10
papers, that is, less than 1% of all papers. This author has mainly analyzed calendar eects (Hui
& Chan, 2015, 2018, 2019; Hui, Wright, & Yam, 2013) and alternative strategies to buy-and-hold
(Hui & Chan, 2014; Hui & Yam, 2014).
There are two authors ranking second on the list: Plastum A. and Narayan, PK.
Plastum, A. has specialized in the research of market anomalies and market ineiciencies
(Caporale, Gil-Alana, & Plastun, 2016, 2017; Caporale, Gil-Alana, Plastun, & Makarenko, 2015;
Caporale & Plastun, 2017, 2019a, 2019b; Plastun, Sibande, Gupta, & Wohar, 2020). Plastum A.
has worked together with Caporale GM, who is the forth author on the list, with 7 papers on the
topic of trading strategies.
Narayan, PK has focused on intraday financial markets (Khademalomoom & Narayan, 2019;
Phan, Sharma, & Narayan, 2016) and the impact of financial news (Narayan & Bannigidadmath,
2017; Narayan, Phan, Narayan, & Bannigidadmath, 2017). All the three authors mentioned
Javier Oliver-Muncharaz and Fernando García 31
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Figure 3. Top 10 research areas contributing to the research on trading strategies
Source: Web of Science
Author Number of Publications
HUI ECM 10
NARAYAN PK 8
PLASTUN A 8
CAPORALE GM 7
CHAN KKK 7
DUNIS CL 7
STUBINGER J 7
SASS J 6
WU ME 6
BEKIROS SD 5
Table 2. Top 10 authors with most publications on trading strategies
Source: Web of Science
Javier Oliver-Muncharaz and Fernando García 32
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
University Number of Publications
Hong Kong Polytechnic University 16
Chinese University of Hong Kong 15
National University of Singapore 15
University of Pennsylvania 14
New York University 13
University of Illinois 13
University of Oxford 13
Columbia University 12
Cornell University 11
Tsinghua University 11
Table 3. Top 10 institutions with most publications on trading strategies
Source: Web of Science
started publishing their research in 2014 or later. It is also interesting that all of them work
together with other authors, building solid research cooperation links.
The top 10 institutions involved in the research and development of trading strategies are
listed on Table 3. Hong Kong Polytechnic University contributes most with 16 papers, followed
by the Chinese University of Hong Kong and the National University of Singapore, each of them
contributing with 15 papers to the sample. There is no leading institution and more than 1,150
institutions are involved in the research and improvement of trading strategies. This is an
important sign of the relevance of this topic, which can attract the attention of researchers
working in many dierent organizations around the globe.
As for the geographic distribution of the contributing organizations, Figure 4 shows the top
10 countries where most organizations are located. The USA is the leading country, where 341
institutions are located, followed by People’s Republic of China (193 institutions) and England
(141). When analyzing the country of origin, we notice that institutions from the USA participate
in 28% of the papers dealing with trading strategies. This country is clearly the leading country
in the field, which can be explained by the importance of the USA in the international financial
markets and the key role played in the international financial system by US financial institutions.
4 Citation analysis
The citation of an article is a sign of the its acceptance by peers. Therefore, the number of
citations may be used to proxy the influence of a publication or an author. Figure 5 shows
the evolution of the number of times the papers in the sample have been cited since 1986.
The number of citations has experienced a continuous increasing trend, as the topic “trading
strategies” is becoming more popular among researchers. The trend has a steep slope specially
since 2015. The reason for the fall of citations in 2020 is that our research is conducted in
October 2020, so the papers that will be cited in the next two months are not included in the
analysis.
The most prominent papers on trading strategies ranked by total citations are listed on
Table 4. None of the authors of these papers are among the most productive authors in the
field. It is interesting to note that the papers cover a wide range of topics within the field of
Javier Oliver-Muncharaz and Fernando García 33
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Figure 4. Top 10 countries contributing to the research on trading strategies
Source: Web of Science
Figure 5. Number of citations per year
Source: Web of Science
Javier Oliver-Muncharaz and Fernando García 34
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Rank Title Authors and year Total citations
1
Do Institutional Investors Prefer Near-
Term Earnings over Long-Run Value?
(Bushee, 2001) 842
2
Driven to Distraction: Extraneous Events
and Underreaction to Earnings News
(Hirshleifer, Lim, &
Teoh, 2009)
346
3
Tools of the trade: the socio-technology
of arbitrage in a Wall Street trading room
(Beunza, 2004) 270
4
Separating microstructure noise from
volatility
(Bandi & Russell,
2006)
263
5
Short-Sale Strategies and Return Pre-
dictability
(Diether, Lee, &
Werner, 2008)
255
6
Firm valuation, earnings expectations,
and the exchange-rate exposure eect
(Bartov & Bodnar,
1994)
239
7
2005 report on socially responsible in-
vesting trends in the United States
(Kempf & Ostho,
2007)
229
8
Application of neural networks to an
emerging financial market: forecasting
and trading the Taiwan Stock Index
(A.-S. Chen, Leung, &
Daouk, 2003))
209
9
The use of data mining and neural net-
works for forecasting stock market re-
turns
(Enke & Thaworn-
wong, 2005)
196
10
The price dynamics of common trading
strategies
(Farmer & Joshi,
2002)
195
Table 4. Top 10 institutions with most publications on trading strategies
Source: Web of Science
trading strategies. So, it is not possible to identify which topics are more trendy, that is, the
main approaches researchers are utilizing to develop and propose new trading strategies. It
must be highlighted that almost all papers in table 4 are more than 15 years old. Therefore, we
perform the same analyses just for the last 5 years.
The results of this analysis are shown on Table 5. Here we find 3 articles by Narayan and
Bannigidadmath (2017); Narayan, Narayan, and Westerlund (2015); Phan et al. (2016), who is
one of the most productive authors in this field and was included in Table 2. This table is much
more instructive than Table 4 regarding the main subareas in the field of trading strategies,
as there appear some clear lines of research. We can suppose that in the last years, as the
interest in the field has increased, researchers have specialized and some trading strategies
and research approaches outstand and become more important.
Table 5. Top 20 cited articles in the database, restricted to articles published since 2015
Rank Title Authors and year Total citations
1
Dynamic Mode Decomposition: Data-
Driven Modeling of Complex Systems
(Mann & Kutz, 2016) 117
Javier Oliver-Muncharaz and Fernando García 35
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Table 5. Top 20 cited articles in the database, restricted to articles published since 2015
Rank Title Authors and year Total citations
2
Forecasting daily stockmarket return us-
ing dimensionality reduction
(Zhong & Enke, 2017)
84
3 News Trading and Speed
(Foucault, Hombert,
& Roşu, 2016)
71
4 Google searches and stock returns
(Bijl, Kringhaug, Mol-
nár, & Sandvik, 2016)
59
5
Intraday volatility interaction between
the crude oil and equity markets
(Phan et al., 2016) 44
6
Risk-Averse Energy Trading in Multi-
energy Microgrids: A Two-Stage Stochas-
tic Game Approach
(C. Li, Xu, Yu, Ryan, &
Huang, 2017)
41
7
An intelligent short term stock trading
fuzzy system for assisting investors in
portfolio management
(Chourmouziadis &
Chatzoglou, 2016)
39
8
The profitability of pairs trading strate-
gies: distance, cointegration and copula
methods
(Rad, Low, & Fa,
2016)
38
9
Does Financial News Predict Stock Re-
turns? New Evidence from Islamic and
Non-Islamic Stocks
(Narayan & Bannigi-
dadmath, 2017)
36
10
Using Volume Weighted Support Vector
Machines with walk forward testing and
feature selection for the purpose of cre-
ating stock trading strategy
(Żbikowski, 2015) 33
11
Do order imbalances predict Chinese
stock returns? New evidence from in-
traday data
(Narayan et al., 2015)
31
12
Stock return predictability and investor
sentiment: A high-frequency perspec-
tive
(Naranjo & Santos,
2019)
30
13
Empirical analysis: stock market predic-
tion via extreme learning machine
(X. Li et al., 2014) 30
14
Trade the tweet: Social media text min-
ing and sparse matrix factorization for
stock market prediction
(A. Sun, Lachanski, &
Fabozzi, 2016)
28
15
An intelligent pattern recognition model
for supporting investment decisions in
stock market
(T.-L. Chen & Chen,
2016)
28
16
Trading on Twitter: Using Social Media
Sentiment to Predict Stock Returns
(Sul, Dennis, & Yuan,
2016)
27
Javier Oliver-Muncharaz and Fernando García 36
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Table 5. Top 20 cited articles in the database, restricted to articles published since 2015
Rank Title Authors and year Total citations
17
Using Twitter to Predict the Stock Mar-
ket Where is the Mood Eect?
(Nofer & Hinz, 2015) 26
18 News-based trading strategies
(Feuerriegel &
Prendinger, 2016)
25
19
Interval-valued time series forecasting
using a novel hybrid Holt(I) and MSVR
model
Xiong, Li, and Bao
(2017)
24
20
The skewness of commodity futures re-
turns
(Fernandez-Perez,
Frijns, Fuertes, &
Mire, 2018)
23
Market sentiment analysis has emerged as one important area of research, and several
authors use dierent sources, like twitter and google searches. In fact, 5 out of the 20 most
cited papers published since 2015 deal with market sentiment analysis and use social media as
information source. The impact of news on stock returns is becoming an increasingly popular
area of research, as well, and 3 of the 20 most cited papers use the news to develop trading
strategies. Therefore, we can identify a research trend that uses other information than the
traditional information of asset prices and the indicators that are calculated upon them. Never-
theless, price information remains the most important input to develop trading strategies. This
information is mainly used applying dierent artificial intelligence approaches.
In order to identify the most influential authors we conduct a citation analysis. The dataset
is analyzed using R (Team, 2013) a free soware environment for statistical computing and
graphics. Following Guijarro and Tsinaslanidis (2020), we analyze the relevance of dierent
authors in the topic according to the number of publications and the number of citations per
year. Figure 6 gives one line to each author, where the extremes represent the year of the first
(le circle) and last publication (right circle). The diameter of the circles varies in proportion to
the number of papers published each year and the color denotes the number of cites received.
This analysis is dierent than the simple citations count. Therefore, the list of the authors
included in Figure 6 does not exactly match the list of the most cited authors which could be
extracted from Table 5. It is noteworthy, that most authors in Figure 6 are also among the most
prolific authors, as shown in Table 2.
Figure 6 distinguishes two main groups of authors: Those who started publishing in the field
of trading strategies before the 2008 financial crisis and those who started later. The authors in
this last group publish more papers per year and publish almost every year. Their work also
receives more citations. This result also shows a change in the research dynamics in the field,
as the most prominent authors are devoted to the topic and publish on a continuous basis. The
number of citations per year received by the papers has also increased since 2016.
It is interesting to mention that just few papers have achieved a high number of citations.
As shown in Figure 7, only 2 papers have received more than 300 citations for the whole period
analyzed. Most papers have received just one citation (151 papers) or zero citations (258 papers),
which represents a third of the sample.
Javier Oliver-Muncharaz and Fernando García 37
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Figure 6. Authors’ relevance according to the number of publications and citations received
Source: Web of Science
Javier Oliver-Muncharaz and Fernando García 38
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Figure 7. Distribution of citations per paper
Source: Web of Science
5 Co-citation analysis
In the previous sections we have analyzed the most basic bibliometric measures. So, we have
analyzed the number of papers published and the citations received, which can be used as a
proxy to quantify the influence and recognition obtained by a research work. Next, we perform
a co-citation analysis. This kind of analysis measures the correlation between two dierent
papers. According to Guijarro and Tsinaslanidis (2020), co-citation implies that two articles
are cited in a third article, hence we can assume both cited papers are related. The co-citation
analysis is performed using the VOSViewer soware, which is a tool for creating maps based on
network data and for visualizing and exploring these maps van Eck and Waltman (2009).
First, we make a co-citation analysis of journals. This analysis shows the relevance of the
main journals publishing in the field of trading strategies. As Figure 8 shows, the Journal of
Finance is the most co-cited journal. Figure 8 also shows that it is possible to build clusters
using the co-citation analysis. In this case, we identify 5 clusters, which are represented with
dierent colors. The green cluster groups journals in the field of economic theory. The red
cluster covers the journals which focus in the development of trading methodologies. The blue
cluster includes the journals which are specialized in the analyses of the financial markets. The
violet cluster groups the econometric journals. Finally, the yellow cluster includes journals
publishing in the field of accounting.
Second, we make a co-citation analysis of authors. The results are shown in Figure 9.
Interestingly, none of the most prominent and influent authors according to the previous
analysis appears in the co-citation analysis. Most papers in Figure 9 were published in the last
century. Such is the case of the seminal works by Fama (Engle, Lilien, & Robins, 1987; Fama,
1970, 1973; Fama & French, 1992; Jegadeesh, 1993; Markovitz, 1959; Markowitz, 1952). We can
suppose that those papers are cited in the introductory section of many papers, that is why they
are so important in the co-citation analysis. In fact, they do not really deal with tradingstrategies,
but with other topics like portfolio selection, market eiciency or econometric modelling. The
Javier Oliver-Muncharaz and Fernando García 39
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Figure 8. Co-citation analysis. Journals
Source: Web of Science
only paper older than 20 years which is mentioned on figure 9 and that actually proposes trading
strategies is the one by Brock et al. (Brock, Lakonishok, & LeBaron, 1992). Market sentiment
analysis was also proposed in the late 1990s by Barberis et al. (Barberis, Shleifer, & Vishny,
1998). Moreover, this result reveals that it is becoming more diicult for authors to receive many
citations. In fact, as research becomes more specific on the one hand, but on the other hand
more and more papers are written in the field of trading strategies, it becomes very diicult
for authors to be up-to-date and have a precise overview of the state of the art. As a result, it
is becoming increasingly diicult that two papers are cited simultaneously by a third paper.
Furthermore, new methodologies and approaches are constantly proposed, so the citation life
of articles is reduced. The only exception are the very first papers which introduced the topic
and the basic methodologies, which are still oen mentioned in the introduction of the papers.
6 Leading topics in trading strategy research
In order to extract the leading topics in the research and development of trading strategies,
we have conducted a co-work network analysis. As explained by Feng et al. (2017), a co-word
analysis is a content analysis method which uses keywords of documents to capture scientific
maps within a field. Based on high frequencies of words that appear in the article, it generates
a network relationship among dierent keywords. For a clear understanding of the obtained
network, we will use the visualization tools in VOSviewer. VOS mapping is used to generate
a two dimensional diagram to reflect the location of two elements according to the distance
between them. Figure 10 shows the outcome of this analysis. A concept with yellow color and
higher density indicates that the concept is more frequently used in the field.
From the co-word analysis we can figure out what are some of the main topics researchers
are interested in. So, we see that the concept “stock market” is an important keyword, which
is a logical outcome. It is rather diicult to clearly extract dierent isolated research fields, as
most keywords are related with each other and refer to very basic concepts in the field of trading
strategies, but, nevertheless, we can identify three clusters. The first one deals with market
eiciency (keywords: anomaly, excess return, momentum, abnormal return, January, year),
Javier Oliver-Muncharaz and Fernando García 40
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Figure 9. Co-citation analysis. Authors
Source: Web of Science
Javier Oliver-Muncharaz and Fernando García 41
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Figure 10. Heat map of the co-word network on trading strategies
Source: Web of Science
Javier Oliver-Muncharaz and Fernando García 42
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Cluster 1. Market
eiciency
Cluster 2. Trading rules and
forecasting
Cluster 3: Pairs trading
Foucault et al. (2016)
Bijl et al. (2016)
Phan et al. (2016)
Chourmouziadis and
Chatzoglou (2016)
Narayan and Bannigi-
dadmath (2017)
C. Li et al. (2017)
L. Sun, Najand, and
Shen (2016a)
Sul et al. (2016)
Xiong et al. (2017)
Zhou, min Zhou, Yang,
and Yang (2019)
Zhong and Enke (2017)
T.-L. Chen and Chen (2016)
Arévalo et al. (2017)
Kumar, Meghwani, and Thakur
(2016)
Thenmozhi and Chand (2015)
F. García et al. (2018)
Picasso, Merello, Ma, Oneto, and
Cambria (2019)
Y. Kim, Ahn, Oh, and Enke (2017)
S. Chen, Bao, and Zhou (2016)
de Souza, Ramos, Pena, Sobreiro,
and Kimura (2018)
Yang, Tsai, Shyu, and Chang
(2016)
Knoll, Stübinger, and Grot-
tke (2018)
H. J. Chen, Chen, Chen, and
Li (2019)
Endres and Stübinger (2019)
Leung and Zhou (2019)
Wen, Ma, Wang, and Wang
(2018)
Table 6. Top articles in each cluster on citations which have been published since 2016
Source: Web of Science
the second cluster deals with trading rules and forecasting (keywords: algorithm, indicator,
trading strategy, technical analysis, technical indicator, neural network, prediction, trend), and
the third group, which is smaller and more isolated, deals with a specific trading strategy: pairs
trading (keywords: pairs, pairs trading strategy, spread). Table 6 shows the top articles in each
cluster based on citations which have been published since 2016.
The analysis of the leading topics makes it possible to identify some research directions
which are becoming more popular in recent years and will lead the future research on trading
strategies. We can group them regarding the information used and the data processing tools
applied. As for the information employed, most papers use price information, whereas other
articles analyze social media (Jin, Shen, & Zhang, 2016), mainly twitter (Bartov, Faurel, &
Mohanram, 2017; Behrendt & Schmidt, 2018; Ruan, Durresi, & Alfantoukh, 2018; A. Sun et
al., 2016), or news (Y. Zhang, Song, Shen, & Zhang, 2016). Papers which use price information
can be divided into those which apply pattern recognition and candlesticks (Arévalo et al., 2017;
Goumatianos, Christou, Lindgren, & Prasad, 2017; Ko, Song, & Chang, 2018; Naranjo & Santos,
2019; Ni, Cheng, Huang, & Day, 2018; P. Tsinaslanidis & Guijarro, 2020) and those focusing on
technical analysis (C.-H. Chen, Su, & Lin, 2016; S. Chen et al., 2016; de Souza et al., 2018; Detzel,
Liu, Strauss, Zhou, & Zhu, 2020; Eiamkanitchat, Moontuy, & Ramingwong, 2016; Gerritsen, 2016;
Jiang, Tong, & Song, 2017; Lam, Dong, & Yu, 2019; Maciel, 2018; Trivedi, 2020; Ye, Zhang, Zhang,
Fujita, & Gong, 2016). Papers that analyze social media and news mostly apply sentiment
analysis (Checkley, Higón, & Alles, 2017; Renault, 2017; L. Sun, Najand, & Shen, 2016b).
Regarding the data processing tools, most recent papers utilize artificial intelligence to
extract information from the data. Most common machine learning techniques include neural
networks (Borovkova & Tsiamas, 2019; Krauss, Do, & Huck, 2017; Maknickiene, Lapinskaite, &
Maknickas, 2018; Sezer & Ozbayoglu, 2018; Tsantekidis et al., 2017; Wang, Xu, Huang, & Yang,
2019), support vector machines (Y. Chen & Hao, 2018; Nti, Adekoya, & Weyori, 2020; Tang, Dong,
Javier Oliver-Muncharaz and Fernando García 43
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
& Shi, 2019), Bayesian approaches (Ardia, Gatarek, Hoogerheide, & van Dijk, 2016; Barone-
Adesi, Fusari, Mira, & Sala, 2020; Billio, Casarin, & Osuntuyi, 2018; Boako, Omane-Adjepong,
& Frimpong, 2015; Huang, Kong, Li, Yang, & Li, 2018; Huptas, 2018; Ito, Noda, & Wada, 2015;
Maragoudakis & Serpanos, 2015), and Markov models (Bejaoui & Karaa, 2016; Billio et al., 2018;
Chang & Lee, 2017; Liu & Wang, 2017; Rundo, Trenta, Stallo, & Battiato, 2019; Song, Ryu, &
Webb, 2018; M. Zhang, Jiang, Fang, Zeng, & Xu, 2019). Natural language processing is also
becoming popular in the field of sentiment analysis (Feuerriegel & Prendinger, 2016; Pröllochs,
Feuerriegel, & Neumann, 2016; Schnaubelt, Fischer, & Krauss, 2020). Finally, other processing
tools like dynamic time warping are gaining popularity (S. Kim et al., 2018; P. Tsinaslanidis &
Guijarro, 2020; P. E. Tsinaslanidis, 2018).
7 Conclusions
The development of trading strategies has become a popular field of research in the past 5 years
and many scholars from dierent research areas have been attracted into this multidisciplinary
topic. In this paper we have used the ISI Web of Science database to analyze the research
papers published on this topic during the last decades by means of both a descriptive and a
bibliometric analysis. A total of 1,187 articles have been collected using the search tools in
the ISI Web of Science Database. For the citation and co-citation analysis we have employed R
and VOSviewer, respectively, in order to provide a better visualization of the data and generate
clusters.
Results show that since 2015 papers published on trading strategies have experienced a
sharp increase. The field has evolved from an emerging field to a clearly consolidated one.
The authors are located in many dierent countries, although the USA is clearly the leading
country, and work in many dierent organizations and institutions. No institution has taken the
lead, as there are many organizations which are very active in this research topic. The research
background of the authors also diers, which proofs that this is a multidisciplinary field. In
fact, the study of the journals which publish articles on trading strategies also endorse this
finding. Not just journals specialized in finance, business and economics, but also those which
are focused on mathematics, soware and computer science, among others, are contributing
to the development of new and more complex trading strategies.
The citation analysis shows that the number of citations has been dramatically increasing
in the last years, but there are no leading authors in the field. Around one third of all papers
have receive one citation or no citation at all. Moreover, top cited papers dealing with trading
strategies are rather old, as they were published before the topic started its growing trend.
Besides, the result of the co-citation analysis shows that the most co-cited papers were pub-
lished in the last century and do not actually deal with trading strategies, but with economic
theories about the financial markets and econometric methodologies. Therefore, the mere
analysis of citations does not shed light into the analysis of the present situation regarding
the development of trading strategies. The analysis performed to identify the most relevant
authors in the field, which considers the number of publications and the citations received,
reveals that most of them have been very active since 2015, and gives some clues about present
research lines. To better identify the most important research directions at present, we con-
duct a co-word analysis and we label 3 dierent clusters: market eiciency, trading rules and
forecasting, and pairs trading. The analysis of the leading topics uncovers the most promis-
ing research topics on trading strategies. Main research lines dier regarding the data source
employed: traditional price and financial information, news and social media. According to
Javier Oliver-Muncharaz and Fernando García 44
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
the approach used to define the trading strategy, most papers are using technical analysis,
pattern recognition and candlesticks, and sentiment analysis approaches. The number of data
processing tools is increasing constantly, as databases become more exhaustive and accessible
and new methods are developed. Most of them make use of artificial intelligence, like machine
learning techniques and natural language processing.
Finally, we may conclude that the future path of research on the development of trading
strategies will be shaped by the increase of computational capacity, the use of new information
sources and the development of artificial intelligence and other data processing methods.
References
Ardia, D., Gatarek, L., Hoogerheide, L., & van Dijk, H. (2016). Return and risk of pairs trading
using a simulation-based bayesian procedure for predicting stable ratios of stock prices.
Econometrics, 4(4), 14. doi: https://doi.org/10.3390/econometrics4010014
Arévalo, R., García, J., Guijarro, F., & Peris, A. (2017). A dynamic trading rule based on filtered flag
pattern recognition for stock market price forecasting.
Expert Systems with Applications
,
81, 177–192. doi: https://doi.org/10.1016/j.eswa.2017.03.028
Arribas, I., Espinós-Vañó, M., García, F., & Morales-Bañuelos, P. (2019). The inclusion of socially
irresponsible companies in sustainable stock indices.
Sustainability
,
11
(7), 2047. doi:
https://doi.org/10.3390/su11072047
Arribas, I., Espinós-Vañó, M. D., García, F., & Oliver, J. (2019). Defining socially responsible
companies according to retail investors’ preferences.
Entrepreneurship and Sustainability
Issues, 7(2), 1641–1653. doi: https://doi.org/10.9770/jesi.2019.7.2(59)
Arribas, I., Espinós-Vañó, M. D., García, F., & Tamoši
¯
unien
˙
e, R. (2019). Negative screening
and sustainable portfolio diversification.
Entrepreneurship and Sustainability Issues
,
6
(4),
1566–1586. doi: https://doi.org/10.9770/jesi.2019.6.4(2)
Baccarin, S., & Marazzina, D. (2015). Passive portfolio management over a fi-
nite horizon with a target liquidation value under transaction costs and solvency
constraints.
IMA Journal of Management Mathematics
,
27
(4), 471–504. doi:
https://doi.org/10.1093/imaman/dpv002
Bahoo, S., Alon, I., & Paltrinieri, A. (2020). Sovereign wealth funds: Past, present
and future.
International Review of Financial Analysis
,
67
, 101418. doi:
https://doi.org/10.1016/j.irfa.2019.101418
Bandi, F. M., & Russell, J. R. (2006). Separating microstructure noise from volatility.
Journal of
Financial Economics
,
79
(3), 655–692. doi: https://doi.org/10.1016/j.jfineco.2005.01.005
Barberis, N., Shleifer, A., & Vishny, R. (1998). A model of investor sentiment.
Journal of Financial
Economics, 49(3), 307–343. doi: https://doi.org/10.1016/s0304-405x(98)00027-0
Barone-Adesi, G., Fusari, N., Mira, A., & Sala, C. (2020). Option market trading activity and the
estimation of the pricing kernel: A bayesian approach.
Journal of Econometrics
,
216
(2),
430–449. doi: https://doi.org/10.1016/j.jeconom.2019.11.001
Bartov, E., & Bodnar, G. M. (1994). Firm valuation, earnings expectations, and the
exchange-rate exposure eect.
The Journal of Finance
,
49
(5), 1755–1785. doi:
https://doi.org/10.1111/j.1540-6261.1994.tb04780.x
Bartov, E., Faurel, L., & Mohanram, P. S. (2017). Can twitter help predict firm-level earnings and
stock returns?
The Accounting Review
,
93
(3), 25–57. doi: https://doi.org/10.2308/accr-
51865
Behrendt, S., & Schmidt, A. (2018). The twitter myth revisited: Intraday investor sentiment,
Javier Oliver-Muncharaz and Fernando García 45
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
twitter activity and individual-level stock return volatility.
Journal of Banking & Finance
,
96, 355–367. doi: https://doi.org/10.1016/j.jbankfin.2018.09.016
Bejaoui, A., & Karaa, A. (2016). Revisiting the bull and bear markets notions in the tunisian stock
market: New evidence from multi-state duration-dependence markov-switching models.
Economic Modelling, 59, 529–545. doi: https://doi.org/10.1016/j.econmod.2016.08.018
Beunza, D. (2004). Tools of the trade: the socio-technology of arbitrage in a wall
street trading room.
Industrial and Corporate Change
,
13
(2), 369–400. doi:
https://doi.org/10.1093/icc/dth015
Bijl, L., Kringhaug, G., Molnár, P., & Sandvik, E. (2016). Google searches and
stock returns.
International Review of Financial Analysis
,
45
, 150–156. doi:
https://doi.org/10.1016/j.irfa.2016.03.015
Billio, M., Casarin, R., & Osuntuyi, A. (2018). Markov switching GARCH models for
bayesian hedging on energy futures markets.
Energy Economics
,
70
, 545–562. doi:
https://doi.org/10.1016/j.eneco.2017.06.001
Bilson, J. F. O. (1984). Purchasing power parity as a trading strategy.
The Journal of Finance
,
39(3), 715. doi: https://doi.org/10.2307/2327931
Boako, G., Omane-Adjepong, M., & Frimpong,J. M. (2015). Stock returns and exchangerate nexus
in ghana: A bayesian quantile regression approach.
South African Journal of Economics
,
84(1), 149–179. doi: https://doi.org/10.1111/saje.12096
Borovkova, S., & Tsiamas, I. (2019). An ensemble of LSTM neural networks for high-
frequency stock market classification.
Journal of Forecasting
,
38
(6), 600–619. doi:
https://doi.org/10.1002/for.2585
Brock, W., Lakonishok, J., & LeBaron, B. (1992). Simple technical trading rules and the
stochastic properties of stock returns.
The Journal of Finance
,
47
(5), 1731–1764. doi:
https://doi.org/10.1111/j.1540-6261.1992.tb04681.x
Bushee, B. J. (2001). Do institutional investors prefer near-term earnings over long-run value?
Contemporary Accounting Research
,
18
(2), 207–246. doi: https://doi.org/10.1506/j4gu-
bhwh-8hme-le0x
Caporale,G. M., Gil-Alana, L., & Plastun,A. (2016). Searching for ineiciencies in exchangerate dy-
namics.
Computational Economics
,
49
(3), 405–432. doi: https://doi.org/10.1007/s10614-
016-9567-2
Caporale, G. M., Gil-Alana, L., & Plastun, A. (2017). Short-term price overreactions:
Identification, testing, exploitation.
Computational Economics
,
51
(4), 913–940. doi:
https://doi.org/10.1007/s10614-017-9651-2
Caporale, G. M., Gil-Alana, L., Plastun, A., & Makarenko, I. (2015). Intraday anomalies and
market eiciency: A trading robot analysis.
Computational Economics
,
47
(2), 275–295.
doi: https://doi.org/10.1007/s10614-015-9484-9
Caporale, G. M., & Plastun, A. (2017). Price gaps: Another market anomaly?
Investment Analysts
Journal, 46(4), 279–293. doi: https://doi.org/10.1080/10293523.2017.1333563
Caporale, G. M., & Plastun, A. (2019a). The day of the week eect in the cryptocurrency market.
Finance Research Letters, 31. doi: https://doi.org/10.1016/j.frl.2018.11.012
Caporale, G. M., & Plastun, A. (2019b). On stock price overreactions: frequency, season-
ality and information content.
Journal of Applied Economics
,
22
(1), 602–621. doi:
https://doi.org/10.1080/15140326.2019.1692509
Cervelló-Royo, R., Guijarro, F., & Michniuk, K. (2015). Stock market trading rule
based on pattern recognition and technical analysis: Forecasting the DJIA index
Javier Oliver-Muncharaz and Fernando García 46
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
with intraday data.
Expert Systems with Applications
,
42
(14), 5963–5975. doi:
https://doi.org/10.1016/j.eswa.2015.03.017
Chang, Y.-H., & Lee, M.-S. (2017). Incorporating markov decision process on genetic algorithms
to formulate trading strategies for stock markets.
Applied So Computing
,
52
, 1143–1153.
doi: https://doi.org/10.1016/j.asoc.2016.09.016
Checkley, M., Higón, D. A., & Alles, H. (2017). The hasty wisdom of the mob: How market
sentiment predicts stock market behavior.
Expert Systems with Applications
,
77
, 256–263.
doi: https://doi.org/10.1016/j.eswa.2017.01.029
Chen, A.-S., Leung, M. T., & Daouk, H. (2003). Application of neural networks to an emerging
financial market: forecasting and trading the taiwan stock index.
Computers & Operations
Research, 30(6), 901–923. doi: https://doi.org/10.1016/s0305-0548(02)00037-0
Chen, C.-H., Su, X.-Q., & Lin, J.-B. (2016). The role of information uncertainty in moving-average
technicalanalysis: A studyof individual stock-option issuance in taiwan.
Finance Research
Letters, 18, 263–272. doi: https://doi.org/10.1016/j.frl.2016.04.026
Chen, H. J., Chen, S. J., Chen, Z., & Li, F. (2019). Empirical investigation of
an equity pairs trading strategy.
Management Science
,
65
(1), 370–389. doi:
https://doi.org/10.1287/mnsc.2017.2825
Chen, S., Bao, S., & Zhou, Y. (2016). The predictive power of japanese candlestick charting in
chinese stock market.
Physica A: Statistical Mechanics and its Applications
,
457
, 148–165.
doi: https://doi.org/10.1016/j.physa.2016.03.081
Chen, T.-L., & Chen, F.-Y. (2016). An intelligent pattern recognition model for supporting
investment decisions in stock market.
Information Sciences
,
346-347
, 261–274. doi:
https://doi.org/10.1016/j.ins.2016.01.079
Chen, Y., & Hao, Y. (2018). Integrating principle component analysis and weighted support
vector machine for stock trading signals prediction.
Neurocomputing
,
321
, 381–402. doi:
https://doi.org/10.1016/j.neucom.2018.08.077
Chourmouziadis, K., & Chatzoglou, P. D. (2016). An intelligent short term stock trading fuzzy
system for assisting investors in portfolio management.
Expert Systems with Applications
,
43, 298–311. doi: https://doi.org/10.1016/j.eswa.2015.07.063
de Souza, M. J. S., Ramos, D. G. F., Pena, M. G., Sobreiro, V. A., & Kimura, H. (2018). Examination
of the profitability of technical analysis based on moving average strategies in BRICS.
Financial Innovation, 4(1). doi: https://doi.org/10.1186/s40854-018-0087-z
Detzel, A., Liu, H., Strauss, J., Zhou, G., & Zhu, Y. (2020). Learning and predictability via technical
analysis: Evidence from bitcoin and stocks with hard-to-value fundamentals.
Financial
Management. doi: https://doi.org/10.1111/fima.12310
Diether, K. B., Lee, K.-H., & Werner, I. M. (2008). Short-sale strategies and return predictability.
Review of Financial Studies, 22(2), 575–607. doi: https://doi.org/10.1093/rfs/hhn047
Eiamkanitchat, N., Moontuy, T., & Ramingwong, S. (2016). Fundamental analysis and technical
analysis integrated system for stock filtration.
Cluster Computing
,
20
(1), 883–894. doi:
https://doi.org/10.1007/s10586-016-0694-2
Endres, S., & Stübinger, J. (2019). A flexible regime switching model with pairs trading applica-
tion to the s&p 500 high-frequency stock returns.
Quantitative Finance
,
19
(10), 1727–1740.
doi: https://doi.org/10.1080/14697688.2019.1585562
Engle, R. F., Lilien, D. M., & Robins, R. P. (1987). Estimating time varying risk pre-
mia in the term structure: The arch-m model.
Econometrica
,
55
(2), 391. doi:
https://doi.org/10.2307/1913242
Javier Oliver-Muncharaz and Fernando García 47
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Enke, D., & Thawornwong, S. (2005). The use of data mining and neural networks for fore-
casting stock market returns.
Expert Systems with Applications
,
29
(4), 927–940. doi:
https://doi.org/10.1016/j.eswa.2005.06.024
Fama, E. F. (1970). Eicient capital markets: A review of theory and empirical work.
The Journal
of Finance, 25(2), 383. doi: https://doi.org/10.2307/2325486
Fama, E. F. (1973). A NOTE ON THE MARKET MODEL AND THE TWO-PARAMETER
MODEL.
The Journal of Finance
,
28
(5), 1181–1185. doi: https://doi.org/10.1111/j.1540-
6261.1973.tb01449.x
Fama, E. F., & French, K. R. (1992). The cross-section of expected stock returns.
The Journal of
Finance, 47(2), 427–465. doi: https://doi.org/10.1111/j.1540-6261.1992.tb04398.x
Farmer, J., & Joshi, S. (2002). The price dynamics of common trading strategies.
Journal of
Economic Behavior & Organization
,
49
(2), 149–171. doi: https://doi.org/10.1016/s0167-
2681(02)00065-3
Feng, Y., Zhu, Q., & Lai, K.-H. (2017). Corporate social responsibility for supply chain manage-
ment: A literature review and bibliometric analysis.
Journal of Cleaner Production
,
158
,
296–307. doi: https://doi.org/10.1016/j.jclepro.2017.05.018
Fernandez-Perez, A., Frijns, B., Fuertes, A.-M., & Mire, J. (2018). The skewness of
commodity futures returns.
Journal of Banking & Finance
,
86
, 143–158. doi:
https://doi.org/10.1016/j.jbankfin.2017.06.015
Feuerriegel, S., & Prendinger, H. (2016). News-based trading strategies.
Decision Support
Systems, 90, 65–74. doi: https://doi.org/10.1016/j.dss.2016.06.020
Foucault, T., Hombert, J., & Roşu, I. (2016). News trading and speed.
The Journal of Finance
,
71(1), 335–382. doi: https://doi.org/10.1111/jofi.12302
García, González-Bueno, Oliver, & Riley. (2019). Selecting socially responsible
portfolios: A fuzzy multicriteria approach.
Sustainability
,
11
(9), 2496. doi:
https://doi.org/10.3390/su11092496
García, F., González-Bueno, J., Guijarro, F., & Oliver, J. (2020). Forecasting the environmental, so-
cial, and governance rating of firms by using corporate financial performance variables: A
rough set approach.
Sustainability
,
12
(8), 3324. doi: https://doi.org/10.3390/su12083324
García, F., González-Bueno, J., Guijarro, F., Oliver, J., & Tamoši
¯
unien
˙
e, R. (2020). MULTIOB-
JECTIVE APPROACH TO PORTFOLIO OPTIMIZATION IN THE LIGHT OF THE CREDIBILITY
THEORY.
Technological and Economic Development of Economy
,
26
(6), 1165–1186. doi:
https://doi.org/10.3846/tede.2020.13189
García, F., & Guijarro, F. (2011). Crisis bursátil:¿ es preferible una estrategia de gestión activa o
pasiva? INNOVAR. Revista de Ciencias Administrativas y Sociales, 21(39), 123–131.
García, F., Guijarro, F., & Moya, I. (2011). The curvature of the tracking frontier: A new criterion
for the partial index tracking problem.
Mathematical and Computer Modelling
,
54
(7-8),
1781–1784. doi: https://doi.org/10.1016/j.mcm.2011.02.015
García, F., Guijarro, F., & Moya, I. (2013). A MULTIOBJECTIVE MODEL FOR PASSIVE PORTFOLIO
MANAGEMENT: AN APPLICATION ON THE s&p 100 INDEX.
Journal of Business Economics
and Management, 14(4), 758–775. doi: https://doi.org/10.3846/16111699.2012.668859
García, F., Guijarro, F., & Oliver, J. (2017). Index tracking optimization with cardinality constraint:
a performance comparison of genetic algorithms and tabu search heuristics.
Neural
Computing and Applications
,
30
(8), 2625–2641. doi: https://doi.org/10.1007/s00521-017-
2882-2
García, F., Guijarro, F., Oliver, J.,& Tamoši
¯
unien
˙
e, R. (2018). HYBRID FUZZY NEURAL NETWORK TO
Javier Oliver-Muncharaz and Fernando García 48
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
PREDICT PRICE DIRECTION IN THE GERMAN DAX-30 INDEX.
Technological and Economic
Development of Economy
,
24
(6), 2161–2178. doi: https://doi.org/10.3846/tede.2018.6394
Gerritsen, D. F. (2016). Are chartists artists? the determinants and profitability of recommenda-
tions based on technical analysis.
International Review of Financial Analysis
,
47
, 179–196.
doi: https://doi.org/10.1016/j.irfa.2016.06.008
Goumatianos, N., Christou, I. T., Lindgren, P., & Prasad, R. (2017). An algorithmic framework for
frequent intraday pattern recognition and exploitation in forex market.
Knowledge and
Information Systems, 53(3), 767–804. doi: https://doi.org/10.1007/s10115-017-1052-2
Guijarro, F., & Tsinaslanidis, P. (2020). Analysis of academic literature on environmental
valuation.
International Journal of Environmental Research and Public Health
,
17
(7), 2386.
doi: https://doi.org/10.3390/ijerph17072386
Helbing, P. (2019). A review on IPO withdrawal.
International Review of Financial Analysis
,
62
,
200–208. doi: https://doi.org/10.1016/j.irfa.2018.09.001
Hirshleifer, D., Lim, S. S., & Teoh, S. H. (2009). Driven to distraction: Extraneous events
and underreaction to earnings news.
The Journal of Finance
,
64
(5), 2289–2325. doi:
https://doi.org/10.1111/j.1540-6261.2009.01501.x
Huang, Q., Kong, Z., Li, Y., Yang, J., & Li, X. (2018). Discovery of trading points based
on bayesian modeling of trading rules.
World Wide Web
,
21
(6), 1473–1490. doi:
https://doi.org/10.1007/s11280-018-0534-9
Hui, E. C. M., & Chan, K. K. K. (2014). Can we still beat “buy-and-hold” for individual
stocks?
Physica A: Statistical Mechanics and its Applications
,
410
, 513–534. doi:
https://doi.org/10.1016/j.physa.2014.05.061
Hui, E. C. M., & Chan, K. K. K. (2015). Testing calendar eects on global securitized
real estate markets by shiryaev-zhou index.
Habitat International
,
48
, 38–45. doi:
https://doi.org/10.1016/j.habitatint.2015.03.009
Hui, E. C. M., & Chan, K. K. K. (2018). NEW TESTS OF CALENDAR EFFECTS ON EQUITY AND SECURI-
TIZED REAL ESTATE MARKETS.
International Journal of Strategic Property Management
,
22(4), 314–336. doi: https://doi.org/10.3846/ijspm.2018.4400
Hui, E. C. M., & Chan, K. K. K. (2019). Alternative trading strategies to beat “buy-
and-hold”.
Physica A: Statistical Mechanics and its Applications
,
534
, 120800. doi:
https://doi.org/10.1016/j.physa.2019.04.036
Hui, E. C. M., Wright, J. A., & Yam, S. C. P. (2013). Calendar eects and real estate
securities.
The Journal of Real Estate Finance and Economics
,
49
(1), 91–115. doi:
https://doi.org/10.1007/s11146-012-9398-4
Hui, E. C. M., & Yam, S.-C. P. (2014). CAN WE BEAT THE “BUY-AND-HOLD” STRAT-
EGY? ANALYSIS ON EUROPEAN AND AMERICAN SECURITIZED REAL ESTATE IN-
DICES.
International Journal of Strategic Property Management
,
18
(1), 28–37. doi:
https://doi.org/10.3846/1648715x.2013.862190
Huptas, R. (2018). Point and density prediction of intra-day volume using bayesian linear ACV
models: evidence from the polish stock market.
Quantitative Finance
,
18
(5), 749–760.
doi: https://doi.org/10.1080/14697688.2017.1414491
Ito, M., Noda, A., & Wada, T. (2015). The evolution of stock market eiciency in the US: a
non-bayesian time-varying model approach.
Applied Economics
,
48
(7), 621–635. doi:
https://doi.org/10.1080/00036846.2015.1083532
Jegadeesh, N. (1993). Treasury auction bids and the salomon squeeze.
The Journal of Finance
,
48(4), 1403–1419. doi: https://doi.org/10.1111/j.1540-6261.1993.tb04759.x
Javier Oliver-Muncharaz and Fernando García 49
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Jiang, F., Tong, G., & Song, G. (2017). Technical analysis profitability without data snooping bias:
Evidence from chinese stock market.
International Review of Finance
,
19
(1), 191–206. doi:
https://doi.org/10.1111/irfi.12161
Jin, X., Shen, D., & Zhang, W. (2016). Has microblogging changed stock market behavior?
evidence from china.
Physica A: Statistical Mechanics and its Applications
,
452
, 151–156.
doi: https://doi.org/10.1016/j.physa.2016.02.052
Kempf, A., & Ostho, P. (2007). The eect of socially responsible investing on
portfolio performance.
European Financial Management
,
13
(5), 908–922. doi:
https://doi.org/10.1111/j.1468-036x.2007.00402.x
Khademalomoom, S., & Narayan, P. K. (2019). Intraday eects of the currency mar-
ket.
Journal of International Financial Markets, Institutions and Money
,
58
, 65–77. doi:
https://doi.org/10.1016/j.intfin.2018.09.008
Kim, S., Lee, H., Ko, H., Jeong, S., Byun, H., & Oh, K. (2018). Pattern matching trading sys-
tem based on the dynamic time warping algorithm.
Sustainability
,
10
(12), 4641. doi:
https://doi.org/10.3390/su10124641
Kim, Y., Ahn, W., Oh, K. J., & Enke, D. (2017). An intelligent hybrid trading system for discovering
trading rules for the futures market using rough sets and genetic algorithms.
Applied So
Computing, 55, 127–140. doi: https://doi.org/10.1016/j.asoc.2017.02.006
Knoll, J., Stübinger, J., & Grottke, M. (2018). Exploiting social media with higher-order factoriza-
tion machines: statistical arbitrage on high-frequency data of the s&p 500. Quantitative
Finance, 19(4), 571–585. doi: https://doi.org/10.1080/14697688.2018.1521002
Ko, B., Song, J. W., & Chang, W. (2018). Crash forecasting in the korean stock market based on
the log-periodic structure and pattern recognition.
Physica A: Statistical Mechanics and
its Applications, 492, 308–323. doi: https://doi.org/10.1016/j.physa.2017.09.074
Krauss, C., Do, X. A., & Huck, N. (2017). Deep neural networks, gradient-boosted trees, random
forests: Statistical arbitrage on the s&p 500.
European Journal of Operational Research
,
259(2), 689–702. doi: https://doi.org/10.1016/j.ejor.2016.10.031
Kumar, D., Meghwani, S. S., & Thakur, M. (2016). Proximal support vector machine based hybrid
prediction models for trend forecasting in financial markets.
Journal of Computational
Science, 17, 1–13. doi: https://doi.org/10.1016/j.jocs.2016.07.006
Lam, Dong, & Yu. (2019). Value premium and technical analysis: Evidence from the china stock
market. Economies, 7(3), 92. doi: https://doi.org/10.3390/economies7030092
Leung, T., & Zhou, Y. (2019). Optimal dynamic futures portfolio in a regime-switching mar-
ket framework.
International Journal of Financial Engineering
,
06
(04), 1950034. doi:
https://doi.org/10.1142/s2424786319500348
Li, C., Xu, Y., Yu, X., Ryan, C., & Huang, T. (2017). Risk-averse energy trading in multienergy micro-
grids: A two-stage stochastic game approach.
IEEE Transactions on Industrial Informatics
,
13(5), 2620–2630. doi: https://doi.org/10.1109/tii.2017.2739339
Li, X., Xie, H., Wang, R., Cai, Y., Cao, J., Wang, F., ... Deng, X. (2014). Empirical analysis: stock
market prediction via extreme learning machine.
Neural Computing and Applications
,
27(1), 67–78. doi: https://doi.org/10.1007/s00521-014-1550-z
Liu, Z., & Wang, S. (2017). Decoding chinese stock market returns: Three-state
hidden semi-markov model.
Pacific-Basin Finance Journal
,
44
, 127–149. doi:
https://doi.org/10.1016/j.pacfin.2017.06.007
Maciel, L. (2018). Technical analysis based on high and low stock prices forecasts: evidence for
brazil using a fractionally cointegrated VAR model.
Empirical Economics
,
58
(4), 1513–1540.
Javier Oliver-Muncharaz and Fernando García 50
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
doi: https://doi.org/10.1007/s00181-018-1603-8
Maciková, L., Smorada, M., Dorčák, P., Beug, B., & Markovič, P. (2018). Financial aspects of
sustainability: An evidence from slovak companies.
Sustainability
,
10
(7), 2274. doi:
https://doi.org/10.3390/su10072274
Maknickiene, N., Lapinskaite, I., & Maknickas, A. (2018). Application of ensemble of recurrent
neural networks for forecasting of stock market sentiments.
Equilibrium
,
13
(1), 7–27. doi:
https://doi.org/10.24136/eq.2018.001
Mann, J., & Kutz, J. N. (2016). Dynamic mode decomposition for finan-
cial trading strategies.
Quantitative Finance
,
16
(11), 1643–1655. doi:
https://doi.org/10.1080/14697688.2016.1170194
Maragoudakis, M., & Serpanos, D. (2015). Exploiting financial news and social media opinions
for stock market analysis using MCMC bayesian inference.
Computational Economics
,
47(4), 589–622. doi: https://doi.org/10.1007/s10614-015-9492-9
Markovitz, H. M. (1959).
Portfolio selection: Eicient diversification of investments
. John Wiley.
Markowitz, H. (1952). Portfolio selection.
The Journal of Finance
,
7
(1), 77–91. doi:
https://doi.org/10.1111/j.1540-6261.1952.tb01525.x
Naranjo, R., & Santos, M. (2019). A fuzzy decision system for money investment in stock markets
based on fuzzy candlesticks pattern recognition.
Expert Systems with Applications
,
133
,
34–48. doi: https://doi.org/10.1016/j.eswa.2019.05.012
Narayan, P. K., & Bannigidadmath, D. (2017). Does financial news predict stock returns? new
evidence from islamic and non-islamic stocks.
Pacific-Basin Finance Journal
,
42
, 24–45.
doi: https://doi.org/10.1016/j.pacfin.2015.12.009
Narayan, P. K., Narayan, S., & Westerlund, J. (2015). Do order imbalances predict chinese stock
returns? new evidence from intraday data.
Pacific-Basin Finance Journal
,
34
, 136–151.
doi: https://doi.org/10.1016/j.pacfin.2015.07.003
Narayan, P. K., Phan, D. H. B., Narayan, S., & Bannigidadmath, D. (2017). Is there a financial
news risk premium in islamic stocks?
Pacific-Basin Finance Journal
,
42
, 158–170. doi:
https://doi.org/10.1016/j.pacfin.2017.02.008
Ni, Y., Cheng, Y., Huang, P., & Day, M.-Y. (2018). Trading strategies in terms of
continuous rising (falling) prices or continuous bullish (bearish) candlesticks emit-
ted.
Physica A: Statistical Mechanics and its Applications
,
501
, 188–204. doi:
https://doi.org/10.1016/j.physa.2018.02.038
Nofer, M., & Hinz, O. (2015). Using twitter to predict the stock market.
Business & Information
Systems Engineering, 57(4), 229–242. doi: https://doi.org/10.1007/s12599-015-0390-4
Nti, I. K., Adekoya, A. F., & Weyori, B. A. (2020). Eicient stock-market prediction using
ensemble support vector machine.
Open Computer Science
,
10
(1), 153–163. doi:
https://doi.org/10.1515/comp-2020-0199
Papantonis, I. (2016). Cointegration-based trading: evidence on index tracking & market-neutral
strategies.
Managerial Finance
,
42
(5), 449–471. doi: https://doi.org/10.1108/mf-12-2014-
0318
Phan, D. H. B., Sharma, S. S., & Narayan, P. K. (2016). Intraday volatility interaction between
the crude oil and equity markets.
Journal of International Financial Markets, Institutions
and Money, 40, 1–13. doi: https://doi.org/10.1016/j.intfin.2015.07.007
Picasso, A., Merello, S., Ma, Y., Oneto, L., & Cambria, E. (2019). Technical analysis and sentiment
embeddings for market trend prediction.
Expert Systems with Applications
,
135
, 60–70.
doi: https://doi.org/10.1016/j.eswa.2019.06.014
Javier Oliver-Muncharaz and Fernando García 51
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Plastun, A., Sibande, X., Gupta, R., & Wohar, M. E. (2020). Price gap anomaly in the US stock
market: The whole story.
The North American Journal of Economics and Finance
,
52
,
101177. doi: https://doi.org/10.1016/j.najef.2020.101177
Pröllochs, N., Feuerriegel, S., & Neumann, D. (2016). Negation scope detection in sentiment
analysis: Decision support for news-driven trading.
Decision Support Systems
,
88
, 67–75.
doi: https://doi.org/10.1016/j.dss.2016.05.009
Rad, H., Low, R. K. Y., & Fa, R. (2016). The profitability of pairs trading strategies: dis-
tance, cointegration and copula methods.
Quantitative Finance
,
16
(10), 1541–1558. doi:
https://doi.org/10.1080/14697688.2016.1164337
Renault, T. (2017). Intraday online investor sentiment and return patterns
in the u.s. stock market.
Journal of Banking & Finance
,
84
, 25–40. doi:
https://doi.org/10.1016/j.jbankfin.2017.07.002
Ruan, Y., Durresi, A., & Alfantoukh, L. (2018). Using twitter trust network for
stock market analysis.
Knowledge-Based Systems
,
145
, 207–218. doi:
https://doi.org/10.1016/j.knosys.2018.01.016
Rundo, F., Trenta, F., Stallo, A. L. D., & Battiato, S. (2019). Advanced markov-based machine
learning framework for making adaptive trading system.
Computation
,
7
(1), 4. doi:
https://doi.org/10.3390/computation7010004
Schnaubelt, M., Fischer, T. G., & Krauss, C. (2020). Separating the signal from the noise –
financial machine learning for twitter.
Journal of Economic Dynamics and Control
,
114
,
103895. doi: https://doi.org/10.1016/j.jedc.2020.103895
Sezer, O. B., & Ozbayoglu, A. M. (2018). Algorithmic financial trading with deep convolutional
neural networks: Time series to image conversion approach.
Applied So Computing
,
70
,
525–538. doi: https://doi.org/10.1016/j.asoc.2018.04.024
Simionescu, L., & Dumitrescu, D. (2018). Empirical study towards corporate social
responsibility practices and company financial performance. evidence for compa-
nies listed on the bucharest stock exchange.
Sustainability
,
10
(9), 3141. doi:
https://doi.org/10.3390/su10093141
Song, W., Ryu, D., & Webb, R. I. (2018). Volatility dynamics under an endogenous markov-
switching framework: a cross-market approach.
Quantitative Finance
,
18
(9), 1559–1571.
doi: https://doi.org/10.1080/14697688.2018.1444551
Sul, H. K., Dennis, A. R., & Yuan, L. I. (2016). Trading on twitter: Using social me-
dia sentiment to predict stock returns.
Decision Sciences
,
48
(3), 454–488. doi:
https://doi.org/10.1111/deci.12229
Sun, A., Lachanski, M., & Fabozzi, F. J. (2016). Trade the tweet: Social media text mining and
sparse matrix factorization for stock market prediction.
International Review of Financial
Analysis, 48, 272–281. doi: https://doi.org/10.1016/j.irfa.2016.10.009
Sun, L., Najand, M., & Shen, J. (2016a). Stock return predictability and investor senti-
ment: A high-frequency perspective.
Journal of Banking & Finance
,
73
, 147–164. doi:
https://doi.org/10.1016/j.jbankfin.2016.09.010
Sun, L., Najand, M., & Shen, J. (2016b). Stock return predictability and investor senti-
ment: A high-frequency perspective.
Journal of Banking & Finance
,
73
, 147–164. doi:
https://doi.org/10.1016/j.jbankfin.2016.09.010
Tang, H., Dong, P., & Shi, Y. (2019). A new approach of integrating piecewise linear representation
and weighted support vector machine for forecasting stock turning points.
Applied So
Computing, 78, 685–696. doi: https://doi.org/10.1016/j.asoc.2019.02.039
Javier Oliver-Muncharaz and Fernando García 52
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Team, R. C. (2013). R: A language and environment for statistical computing. Vienna, Austria.
Thenmozhi, M., & Chand, G. S. (2015). Forecasting stock returns based on information trans-
mission across global markets using support vector machines.
Neural Computing and
Applications, 27(4), 805–824. doi: https://doi.org/10.1007/s00521-015-1897-9
Trivedi, S. R. (2020). Technical analysis using heiken ashi stochastic: To catch a trend, use a HAS-
TOC.
International Journal of Finance & Economics
. doi: https://doi.org/10.1002/ijfe.2245
Tsantekidis, A., Passalis, N., Tefas, A., Kanniainen, J., Gabbouj, M., & Iosifidis, A. (2017).
Forecasting stock prices from the limit order book using convolutional neural net-
works. In
2017 IEEE 19th conference on business informatics (CBI).
IEEE. doi:
https://doi.org/10.1109/cbi.2017.23
Tsinaslanidis, P., & Guijarro, F. (2020). What makes trading strategies based on chart pattern
recognition profitable? Expert Systems. doi: https://doi.org/10.1111/exsy.12596
Tsinaslanidis, P. E. (2018). Subsequence dynamic time warping for charting: Bullish and bearish
class predictions for NYSE stocks.
Expert Systems with Applications
,
94
, 193–204. doi:
https://doi.org/10.1016/j.eswa.2017.10.055
van Eck, N. J., & Waltman, L. (2009). Soware survey: VOSviewer, a computer program for bib-
liometric mapping.
Scientometrics
,
84
(2), 523–538. doi: https://doi.org/10.1007/s11192-
009-0146-3
Wang, Q., Xu, W., Huang, X., & Yang, K. (2019). Enhancing intraday stock price manipulation
detection by leveraging recurrent neural networks with ensemble learning.
Neurocom-
puting, 347, 46–58. doi: https://doi.org/10.1016/j.neucom.2019.03.006
Wen, D., Ma, C., Wang, G.-J., & Wang, S. (2018). Investigating the featuresof pairs trading strategy:
A network perspective on the chinese stock market.
Physica A: Statistical Mechanics and
its Applications, 505, 903–918. doi: https://doi.org/10.1016/j.physa.2018.04.021
Xiong, T., Li, C., & Bao, Y. (2017). Interval-valued time series forecasting using
a novel hybrid HoltI and MSVR model.
Economic Modelling
,
60
, 11–23. doi:
https://doi.org/10.1016/j.econmod.2016.08.019
Yang, J.-W., Tsai, S.-Y., Shyu, S.-D., & Chang, C.-C. (2016). Pairs trading: The
performance of a stochastic spread model with regime switching-evidence from
the s&p 500.
International Review of Economics & Finance
,
43
, 139–150. doi:
https://doi.org/10.1016/j.iref.2015.10.036
Ye, F., Zhang, L., Zhang, D., Fujita, H., & Gong, Z. (2016). A novel forecasting method based
on multi-order fuzzy time series and technical analysis.
Information Sciences
,
367-368
,
41–57. doi: https://doi.org/10.1016/j.ins.2016.05.038
Zamore, S., Djan, K. O., Alon, I., & Hobdari, B. (2018). Credit risk research: Re-
view and agenda.
Emerging Markets Finance and Trade
,
54
(4), 811–835. doi:
https://doi.org/10.1080/1540496x.2018.1433658
Żbikowski, K. (2015). Using volume weighted support vectormachines with walk forwardtesting
and feature selection for the purpose of creating stock trading strategy.
Expert Systems
with Applications, 42(4), 1797–1805. doi: https://doi.org/10.1016/j.eswa.2014.10.001
Zhang, M., Jiang, X., Fang, Z., Zeng, Y., & Xu, K. (2019). High-order hidden markov model for trend
prediction in financial time series.
Physica A: Statistical Mechanics and its Applications
,
517, 1–12. doi: https://doi.org/10.1016/j.physa.2018.10.053
Zhang, Y., Song, W., Shen, D., & Zhang, W. (2016). Market reaction to internet news:
Information diusion and price pressure.
Economic Modelling
,
56
, 43–49. doi:
https://doi.org/10.1016/j.econmod.2016.03.020
Javier Oliver-Muncharaz and Fernando García 53
Finance, Markets and Valuation Vol. 6, Num. 2 (July-December 2020), 27–54
Zhong, X., & Enke, D. (2017). Forecasting daily stock market return using di-
mensionality reduction.
Expert Systems with Applications
,
67
, 126–139. doi:
https://doi.org/10.1016/j.eswa.2016.09.027
Zhou, F., min Zhou, H., Yang, Z., & Yang, L. (2019). EMD2fnn: A strategy combining
empirical mode decomposition and factorization machine based neural network for
stock market trend prediction.
Expert Systems with Applications
,
115
, 136–151. doi:
https://doi.org/10.1016/j.eswa.2018.07.065
Javier Oliver-Muncharaz and Fernando García 54