ECONOMIC ANNALS-XXI
FINANCES, ACCOUNTING AND AUDIT
ECONOMIC ANNALS-XXI
ISSN 1728-6239 (Online)
ISSN 1728-6220 (Print)
https://doi.org/10.21003/ea
http://www.soskin.info/ea/
Volume 190 Issue (5-6(2))’2021
Citation information: Csesznik, Z., Gáspár, S., Thalmeiner, G., & Zéman, Z. (2021). Examining the effectiveness of fundamental
analysis in a long-term stock portfolio. Economic Annals-XXI, 190(5-6(2)), 119-127. doi: https://doi.org/10.21003/ea.V190-11
Zoltán Csesznik
PhD Student (Economics),
Institute of Business Regulation and Information Management,
Hungarian University of Agriculture and Life Sciences
1 Pater K. Str., Gödöllő, 2100, Hungary
csesznik@gmail.com
ORCID ID: https://orcid.org/0000-0003-4751-9662
Sándor Gáspár
PhD Student (Economics),
Institute of Business Regulation and Information Management,
Hungarian University of Agriculture and Life Sciences
1 Pater K. Str., Gödöllő, 2100, Hungary
gaspar.sandor.2@hallgato.uni-szie.hu
ORCID ID: https://orcid.org/0000-0002-6874-559X
Gergő Thalmeiner
PhD Student (Economics),
Institute of Business Regulation and Information Management,
Hungarian University of Agriculture and Life Sciences
1 Pater K. Str., Gödöllő, 2100, Hungary
thalmeiner.gergo@hallgato.uni-szie.hu
ORCID ID: https://orcid.org/0000-0002-7224-1028
Zoltán Zéman
D.Sc. (Economics), Professor,
Institute of Business Regulation and Information Management,
Hungarian University of Agriculture and Life Sciences
1 Pater K. Str., Gödöllő, 2100, Hungary
zeman.zoltan@uni-mate.hu
ORCID ID: https://orcid.org/0000-0003-2504-028X
Examining the effectiveness of fundamental analysis
in a long-term stock portfolio
Abstract. Over the past decade, a number of modern and sophisticated methods have been developed to
optimize the composition of equity portfolios. Most of these methods are based on complex mathematical
or financial modelling. Less emphasis has been placed on companies’ internal data, while in recent years
external data have become increasingly important. However, for long-term investments, the dominance
of external data is not necessarily an efficient way to construct an appropriate portfolio. In this paper,
we highlight the phenomenon that complex mathematical models, the based on simpler fundamental
indicators can also be an efficient investment tool for in making investment decisions. Our results show
that our hypothesis has been confirmed that some basic-based indicators can achieve alpha returns. Our
analysis is based on financial reporting data in the form of various financial indicators. We used the S&P500
index as benchmark. A comparative analysis of the stock portfolio created illustrates that basic analysis
can be more effective than a chosen market-based stock index. By the end of the period under review, the
portfolio based on the selected five core financial indicators had a market capitalization 1.68% higher than
the benchmark. The alpha return achieved also demonstrates that even simpler models can be efficient and
effective in creating an equity portfolio.
Keywords: Portfolio Management; Fundamental Analysis; S&P500; Reports; Stock Market
JEL Classification: E47; F30; G11
Acknowledgements and Funding: The authors received no direct funding for this research.
Contribution: The authors contributed equally to this work.
Data Availability Statement: The dataset is available from the authors upon request.
DOI: https://doi.org/10.21003/ea.V190-11
1. Introduction
The stock market forecasting models and investment strategies that have emerged in recent
years offer investors a wide range of options for selecting the right stocks and portfolios. However,
Csesznik, Z., Gáspár, S., Thalmeiner, G., & Zéman, Z. / Economic Annals-XXI (2021), 190(5-6(2)), 119-127
© Institute of Society Transformation, 2021
119
ECONOMIC ANNALS-XXI
FINANCES, ACCOUNTING AND AUDIT
for long-term investments, the accuracy of these models and strategies is questionable due to the
long horizon and the resulting high stochasticity (Khan et al., 2011).
Diversifying the risk of long-term investment portfolios is also a controversial topic in the litera-
ture (Abramov et al., 2015). Diversification is a complex task for investors due to high volatility and
the unpredictability of economic cycles.
Choosing an investment strategy and constructing an investment portfolio is a multi-factor
decision model. Several models classify stocks from an investment perspective based on mar-
ket volatility, short-term drivers and different trends. Among the various analyses, the conside
ration of intrinsic factors based on fundamental analysis has taken a back seat in recent years to
market trend analysis and short-term industry or market factors, which have different influences
(Jovic et al., 2019; Uddin, 2009). Neural networks and stock market trading robots are proving to
be an excellent tool and method for short-term investments and speculative trading. However, they
are not effective enough for long-term decisions and the associated risk assessment. In contrast
to these models, the investment focus for fundamental analysis is on intrinsic factors. The use of
data from these analyses and the resulting strategy and portfolio design rely on companies’ inter-
nal data, and thus on long-term company performance and potential, rather than on trends and ex-
ternal factors. The assessment and influence of internal factors can be influenced by the company,
which in turn can provide an opportunity to influence share prices according to organizational ob-
jectives (Jovic et al., 2019; Nikou et al., 2019).
Therefore, many companies that take this into account and consciously build their strategy
around it may be able to maximize shareholder value even in the long run. And for investors, it
can be an important indicator of long-term investment. Thus, identifying and monitoring indi-
cators that effectively measure corporate performance is a key consideration for all investors
(Szilágyi, 2017).
Corporate performance can be assessed based on internal factors, value creation and various
financial data. Financial accounting data from stock market reports can serve as a good database
for selecting appropriate indicators. However, the relationship between the various indicators de-
rived from the audit analysis of financial accounting and stock price developments is not always
clear (Thakur et al., 2020).
For investors to effectively evaluate and influence share prices, they need to identify and moni-
tor related or high-impact financial and accounting indicators.
In our research, we have used the most important financial indicators in the literature to deve
lop different valuation criteria. In most cases, the selected indicators have a significant impact on
the share price (Galankashi et al., 2020). Based on the selected indicators, a portfolio of stocks is
constructed and its performance is compared to a standard market benchmark.
2. Brief Literature Review
Financial markets have gone through several periods of crisis in recent years, resulting
in increased volatility and a fall in the stock market. One of the most significant crises was the
Greek crisis of 2015 and the bursting of the Chinese stock market bubble on the world market
(Szilágyi, 2017). As a result of these events, among others, the development of effective portfolio
analyzes has become more valuable. Effective analyzes based on appropriate indicators can en-
sure that the maturity value of the portfolio is greater than, or at least equal to, the level given as a
percentage of the initial investment (Cont & Tankov, 2007).
Nowadays, the importance of market economies and share prices is even more appreciated
than ever. In this way, a broad analysis and understanding of financial markets can be seen as
a vital task (Sági et al., 2020). Financial markets are affected by a number of uncertain factors
(e.g., general economic conditions, national and international social factors - changes in poli
tical events) that make analysis and forecasting a complex task (Bisoi & Dash, 2014; Lin, 2018;
Lentner et al., 2018). Some of these factors affect markets in the long run, while others have only
short-term effects (Yiwen et al., 2000). Three main approaches to monitoring changes in stock pri
ces have emerged: fundamental analysis, technical analysis and technology (Machine learning)
methods (Dunne, 2015).
The fundamental analysis performs an analysis of stocks based on publicly available data from
the economy, industry, and the company. Technical analysis examines stock prices based on past
data from various technical indicators for decision making (Nti et al., 2020). In most of the literature
focusing on stock price forecasting, technology methods use data mining and machine learning
Csesznik, Z., Gáspár, S., Thalmeiner, G., & Zéman, Z. / Economic Annals-XXI (2021), 190(5-6(2)), 119-127
120
ECONOMIC ANNALS-XXI
FINANCES, ACCOUNTING AND AUDIT
techniques, notably the implementation of variants of artificial neural networks (ANN) (Fajiang &
Wang, 2012). Furthermore, the ongoing use of hybrid ensemble machine-learning method has
become widespread.
Fundamental analysis
In the history of trading created countless premises and theories to predict market movements.
Fundamental analysis is a method of measuring a company’s stock intrinsic value by examining
economic, industrial and financial factors (Kovács & Terták, 2019). In terms of the development
of the method, it can be traced back to the 1930s, more precisely to the formation of the Securi-
ties Exchange Committee. The task of the committee was to regulate the market and punish mar-
ket manipulation activities. During the audits, the fundamental analyzes proved to be effective.
The cornerstone of fundamental analysis is his book «Security Analysis» published by Graham and
Dodd (1934). In their book, the authors emphasized that a complete analysis of a company can
provide good returns and properly identify the value of stocks (Suciu, 2013). By filtering out mar-
ket-distorting effects and using publicly available information such as general economic condi-
tions, industry analyzes, and valuations of a company’s fundamentals, the method can be used
to determine the share price (Lam, 2004). Thus, in applying the method, the characteristics of the
firm’s financial position, economic environment, assets, debts, and management must be taken
into account (Chen et al., 2017).
In applying fundamental analysis, previous research has suggested different approaches to se-
lecting the indicators included in the analysis. Thawornwong and Enke (2004) propose to include
adaptive financial and economic variables in the analysis, which are selected using artificial neural
networks. In another study, the authors used three methods: principal component analysis (PCA),
genetic algorithms (GA), and decision trees (CART) to identify more representative variables to
improve prognosis (Tsai & Hsiao, 2010). But a number of studies address the influential impact
of social media. Bollen et al. (2011) in their study examined whether Twitter posts have influential
power or can be used to predict the stock market.
Most of the studies clearly highlight the important role of financial indicators in the application
of fundamental analysis. The selection of financial ratios is an important task because different fi-
nancial ratios may be relevant in different industries (Arslanian & Fischer, 2019). By determining
the relevant indicators, the accuracy of the stock market prediction can be increased. Therefore,
it is recommended to examine several financial indicators of the company to conduct the analysis
(Venkatesh, 2012).
Young (2010) conducted the company analysis by calculating the following indicators: earnings/
share, price/earnings ratio, return on assets, return on equity, debt/equity ratio, market capitali-
zation, price/sales ratio and price/book ratio. In their study, Herawati and Putra (2018) used addi-
tional indicators in the analysis of stock prices. In addition to debt to equity ratio and return on as-
sets, they also included current ratio, price earnings ratio, and total assets turnover indicators in
their analysis. Astuty (2017) found a significant correlation between price earnings ratio, earnings
per share, net profit margin, price to book value and systematic risk indicators and stock price
variation. Edirisinghe and Zhang (2007) analyze 18 financial ratios to determine the relative finan-
cial strength index (RFSI) of an organization, which can be used to predict the stock price return
of a company. The ratios examine the underlying performance of the organization through diffe
rent performance perspectives covering profitability, asset utilization, liquidity, leverage, valuation
and growth perspective.
It can be stated that a number of financial indicators can be used in fundamental analysis. By in-
cluding relevant and extensive financial indicators, the stock market price prediction can be made
more accurate (Galankashi et al., 2020). The analysis is basically effective for long-term invest-
ments, less suitable for making short- and intraday forecasts (Khan et al., 2011). Consequently,
the use of fundamental analysis can be considered as an effective method in long-term equity in-
vestment decision-making (Renu & Christie, 2018).
3. Purpose
Nowadays, making investment decisions can be considered a complex task. As a result of the
development of digitization, a number of internal and external data are available, for the analysis
of which complex indicators and indices have been created. In our research, we highlight that in
addition to the application of complex mathematical models, analyzes based on simpler funda-
mental indicators can also be considered effective in making investment decisions. In our study,
Csesznik, Z., Gáspár, S., Thalmeiner, G., & Zéman, Z. / Economic Annals-XXI (2021), 190(5-6(2)), 119-127
121
ECONOMIC ANNALS-XXI
FINANCES, ACCOUNTING AND AUDIT
we focus on financial indicators in fundamental analysis. Using the fundamental financial indica-
tors included in the analysis, we created a stock portfolio. By comparative analysis of the created
stock portfolio, we illustrate that fundamental analysis can be more effective than a market-based
stock index
4. Results
Among the many financial ratios that can be used in fundamental analysis, Mohamed et al. (2021)
built their model based on the results of internal financial indicators. In their study, an efficient stock
price prediction model was constructed using these indicators. Based on Mohamed et al. (2021)
and other literature, we hypothesize the following: In our hypothesis, we assume that using a few in-
trinsic indicators linked to fundamental analysis, a more efficient stock portfolio can be constructed
than a market index. Efficiency is judged by the measure of return.
Following Edirisinghe and Zhang (2007), our research has three main preferences. The first
is profitability from year to year. Second, it should have a healthy debt ratio, it should not take on
more debt that it can easily cover. The last one is liquidity, which is important because the ability to
reliably meet short-term and long-term liabilities is a prerequisite for long-term operations.
These ratios characterize solid, well managed companies. Probably the growth prospects are
not the highest ones, but when we examine the performance of the entire market the average will
consist of companies with stumbling results, companies which are at the end of their growth cy-
cles therefore are declining. Our logic conclusion is if we filter the solidity in the markets then these
companies should still outperform the crowd (Kovács & Terták, 2019).
For the purpose of this research, only one indicator was selected for each area. However, it
should be emphasized that a number of indicators can be used to assess the areas. The more in-
dicators that are included in the analysis, the more reliable the portfolio will become. However, the
complexity of the analysis increases with the inclusion of additional indicators.
Steps of modelling:
Step 1: Financial indicators should be defined which are suitable for the assessment of any stock.
Step 2: A portfolio of stock is created based on predefined normative values of the selected finan-
cial indicators.
Step 3: Comparison of the portfolio of stock with the overall market or with portfolios of stocks
created by other methods.
Step 1
The financial indicators included in the analysis were selected on the basis of a norma-
tive choice. However, our choice is matched by several studies (Macharia & Gatuhi, 2013;
Mohamed et al., 2021; Jatoi, 2014; Edirisinghe & Zhang, 2007; Maryyam, 2016).
Indicators included in the study are as follows (Table 1).
Net profit margin: compares the sales and the profits. It divides the net profit with the total
sales. Net margin is one of those comparative figures that should be steady over time. The more
consistent the better. One important characteristic of a well-managed company is the consistent
net profit margin. This is especially true if the revenue is growing period after period because this
case the management can cope with the growth problems (Brealey et al., 2001).
Debt to equity ratio: is calculated by dividing the total liabilities by the shareholder equity. It is
an important metric; it shows the ability of shareholder equity to cover all the debts. Obviously, a
high value means high debt. D/E values around 1 mean a turning point because then the company
just have enough assets to pay back its debts, so the creditor has to consider the risk that there is
not enough collateral to cover the debts (Thomsett, 1998).
Current ratio: measures the company’s ability to pay its short-term debt, typically those which
due within a year. We can calculate it by dividing the current assets with the current liabilities. It is a
Table 1:
Main indicators
Source: Compiled by authors based on Thomsett (1998)
and Brealey et al. (2001)
Csesznik, Z., Gáspár, S., Thalmeiner, G., & Zéman, Z. / Economic Annals-XXI (2021), 190(5-6(2)), 119-127
122
ECONOMIC ANNALS-XXI
FINANCES, ACCOUNTING AND AUDIT
very useful ratio because it shows immediately how liquid the company is. Values under 1 signals
danger, because the company has little assets (cash, receivables, inventory) to cover the interest
payments. Values over 3 are considered too high because the management is not able to use the
assets optimally. Values between 1-3 are generally accepted (Thomsett, 1998).
For the screening settings we require net profit margin, current ratio and debt to equity ratio to
fall between predefined values every year from 2011 to 2015.
To increase the accuracy of our method, we include two additional indicators in our analy-
sis (Table 2). The two other indicators included in the analysis are earnings per share and the
price-earnings ratio. These consider the expectations of market participants, which might be
useful because through the stock price it provides an insight how the market evaluates the
company (Wewege & Thomsett, 2019).
Table 2:
Additional indicators
Source: Compiled by authors based on Thomsett (1998)
and Brealey et al. (2001)
Earnings per share (EPS): The value of the indicator determines the amount of profit after tax
per ordinary share of the organization. The value of the indicator can be calculated according to
the following formula: profit after tax / number of outstanding shares. This ratio showed how much
the value of the share had gone up or down over a given period (Renu & Christie, 2018).
P/E ratio: it is a division between the stock’s current price per share and the annual earnings
per share of common stock. The ratio shows what the market thinks a dollar of earning worth. In
other words, how many years it will take for the company to earn the current value of its shares’
price. If the P/E ratio is very low (under 5) then the shares of the company are not interesting for
the investors. As a general guidance higher P/E ratio means higher than average growth poten-
tial. However higher ratios have to be handled with reservations because the market might assign
great importance to future growth, which places a lot of pressure on the management (Thomsett,
1998). The P/E ratio is a useful indicator because it compares the stock price with the fundamen-
tals. It is imperfect like most ratios, because it is reporting in a stationary manner. When the ratio is
fluctuating around the same values over time it is a sign that the market is thinking similarly about
the stock (Brealey et al., 2001).
For EPS and P/E data, only 2015 data are analyzed. The reason for this is because we are as-
sessing the valuation of market participants’ shares at portfolio launch.
This value perspective can be seen as a fourth fundamental perspective. This aspect differs
from the points of view raised in the literature (Galankashi et al., 2020; Mohamed et al., 2021;
Jatoi, 2014; Edirisinghe & Zhang, 2007).
Step 2
We compile the equity portfolio based on the selected valuation indicators and the limits set
for them. In our case, the selected data set, which includes the companies to be examined, is
limited to shares traded on the NYSE and NASDAQ stock exchanges. It is highlighted that we can
find more than 6000 listed companies on these two stock exchanges. For the analysis, we used
the service of https://www.marketinout.com/, which operates an extensive historical database of
both technical and fundamental data.
As a result of the analysis, the securities of 56 listed organizations met the pre-defined criteria.
Table 3 shows the stock exchange abbreviated designations of 56 companies.
The 56 selected organizations make up the portfolio we use in our analysis. The resulting port-
folio is compared with the results of the S&P500 index. We chose this index for the benchmark be-
cause it is a commonly used index for stock market analysis and because it follows market trends
effectively (Rounaghi & Zadeh, 2016). The study period is defined as January 2015 to April 2021.
During this period, we compare the actual performance of the two portfolios. Thus, in our analy-
sis, we use past period data to determine performance. To illustrate the comparison, we assume
a stock market position opening of USD 2,000. Hence, on the same day we open a long position in
Csesznik, Z., Gáspár, S., Thalmeiner, G., & Zéman, Z. / Economic Annals-XXI (2021), 190(5-6(2)), 119-127
123
ECONOMIC ANNALS-XXI
FINANCES, ACCOUNTING AND AUDIT
Table 3:
56 stock exchange organizations
Source: Compiled by authors using data from https://www.marketinout.com/ (2021)
every stock on the list in the same dollar amount. We dedicate USD 2,000 to each position, which
corresponds to a total of USD 112,000. At the same time, we invest USD 112,000 into the S&P500
index, which we use as a benchmark to be able to compare the performance of our portfolio with
the index.
Table 4 illustrates the changes in the portfolio we created and the results of the S&P500 during
the period under review.
A comparison of the data for the period under review (Table 4) shows that the portfolio we have
created performs better than the benchmark index. Table 4 shows percentages, the calculation
method of which is in each case a comparison of the closing value of the previous period with the
closing value of the relevant period. In the case of determining the total percentage of the calcu-
lation, the closing period always means the result at the end of the previous year and this value is
compared with the closing value of the current year.
Based on the annual differences, it can be seen that the portfolio performs better in most
years than the benchmark. The portfolio achieved a 125% increase in capital (not considering
any slippage and commission), while the S&P500 index achieved a 103% increase in capital.
This difference can also be observed in the annualized return, which is 13.0% for the portfolio
and 11.3% for the benchmark. Figure 1 illustrates that the portfolio remains consistently above
the benchmark. This also demonstrates the benefits of selecting stocks based on fundamen-
tal indicators.
Table 4:
Portfolio and benchmark analysis
Source: Compiled by authors using data from https://www.marketinout.com/ (2021)
Csesznik, Z., Gáspár, S., Thalmeiner, G., & Zéman, Z. / Economic Annals-XXI (2021), 190(5-6(2)), 119-127
124
ECONOMIC ANNALS-XXI
FINANCES, ACCOUNTING AND AUDIT
The portfolio reached market capitalization of USD 252,089 (Figure 1). This means that the
total profit of the portfolio was USD 14,089. An analysis of the S&P500 index revealed a market
capitalization of USD 227,439. In this case, the total return on the portfolio can be determined at
USD 115,439. Based on these, it can be stated that the equity portfolio created on the basis of the
fundamental financial indicators on which our analysis is based, achieved a higher alpha return.
Hence, the portfolio outperformed the average market returns.
Rakićević et al. (2019) have come to the same conclusion as our research. The portfolio in their
research was also created on the basis of fundamental indicators. They determined the composi-
tion of their stock portfolio using an interpolative boolean fuzzy selection model. Their equity port-
folio returns exceeded the average of the 2016 S&P500 index. Furthermore, these results exceed
the 10-year return of the S&P500 index they studied (0.42%).
Coleman (2019) evaluated the S&P500 companies on the basis of fundamental indicators. In
his analysis, he concluded that fundamental indicators are not suitable for creating long-term in-
vestment portfolios.
In their research, Beyaz et al. (2018) assess whether basic or technical analysis is better suited
for predicting stock prices using machine learning models. Machine learning methods have been
used to learn from previous movements in the stock price of firms and to make predictions. Tests
performed on 140 companies in the S&P500 show that models that use indicators based on fun-
damental analysis outperform models that use technical analysis indicators in almost all cases. At
the same time, the results show that forecasting models should be used in conjunction with indi-
cators from fundamental and technical analyzes to successfully forecast the exchange rate and
determine expected returns.
In their research, Silva et al. (2015) investment models include a basic and technical approach
that uses fundamental financial and technical indicators. The Multi-Objective Evolutionary Algo-
rithms (MOEA) was chosen as the method used to optimize the return and risks of the portfolios.
The simulations show that stock selection based on financial indicators has put together a more
effective stock portfolio than the benchmark index (S&P500). The result of the portfolio they crea
ted, similar to the portfolio created in our research, achieved a higher alpha return compared to
the benchmark in the period under review.
Figure 1:
Comparison of screened portfolio versus S&P500
Source: Compiled by authors using data from https://www.marketinout.com/ (2021)
5. Conclusion
In this paper, we illustrate that, in addition to the use of complex mathematical models, ana
lyses based on simpler fundamental indicators can also be effective in making investment deci-
sions. Our results support our hypothesis that by applying a few indicator-based methods we can
achieve above-market returns.
We construct a portfolio using the fundamental financial indicators included in our analysis. By
comparatively analyzing the constructed equity portfolio, we illustrate that fundamental analysis
can be more efficient than a market-based stock market index. The portfolio constructed u sing the
selected five fundamental financial indicators has achieved a market capitalization 1.68% higher
Csesznik, Z., Gáspár, S., Thalmeiner, G., & Zéman, Z. / Economic Annals-XXI (2021), 190(5-6(2)), 119-127
125
ECONOMIC ANNALS-XXI
FINANCES, ACCOUNTING AND AUDIT
than the S&P500 index at the end of the period under study. The alpha yields also proves the as-
sumption that simpler models can be effective when constructing an equity portfolio.
The results obtained using fundamental analysis tools also show that for long-term invest-
ments, the financial and operational performance of the company is a very important factor. One
of the main advantages of our methodology, apart from its simplicity, is that it requires data from
public reports. For large and complex models, obtaining complex and difficult to access data can
often be a bottleneck. The disadvantage of the method is the limited range of viewpoints and in-
dicators used. Many viewpoints cannot be measured from data in different reports. These include
brand awareness, industry strength, research and development activity which determines innova-
tion potential.
Another research opportunity is to analyze the dividend policy of individual companies and their
impact on the performance of their equity portfolios. It could be extended to basic but not financial
indicators. In addition, the results could be compared with other benchmarks.
References
1. Abramov, A., Radygin, A., & Chernova, M. (2015). Long-term portfolio investments: New insight into return and risk.
Russian Journal of Economics, 1(3), 273-293. https://doi.org/10.1016/j.ruje.2015.12.001
2. Arslanian, H., & Fischer, F. (2019). The Future of Finance: The Impact of FinTech, AI, and Crypto on Financial Services.
Springer. https://doi.org/10.1007/978-3-030-14533-0
3. Astuty, P. (2017). The Influence of Fundamental Factors and Systematic Risk to Stock Prices on Companies Listed in
the Indonesian Stock Exchange. European Research Studies Journal, 20(4), 230-240. https://www.researchgate.net/
publication/321671861_The_influence_of_fundamental_factors_and_systematic_risk_to_stock_prices_on_companies_
listed_in_the_Indonesian_stock_exchange
4. Beyaz, E., Tekiner, F., Zeng, X., & Keane, J. (2018). Comparing Technical and Fundamental Indicators in Stock Price
Forecasting. 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE
16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/
SmartCity/DSS), (pp. 1607-1613). https://doi.org/10.1109/HPCC/SmartCity/DSS.2018.00262
5. Bisoi, R., & Dash, P. K. (2014). A hybrid evolutionary dynamic neural network for stock market trend analysis and
prediction using unscented Kalman filter. Applied Soft Computing, 19, 41-56. https://doi.org/10.1016/j.asoc.2014.01.039
6. Bollen, J., Mao, H., & Zeng, X. (2011). Twitter mood predicts the stock market. Journal of Computational Science, 2(1),
1-8. https://doi.org/10.1016/j.jocs.2010.12.007
7. Brealey, R., Myers, S., & Marcu, A. (2001). Fundamentals of Corporate Finance. The McGraw-Hill Companies Inc.
8. Chen, Y.-J., Chen, Y.-M., & Lu, Ch. L. (2017). Enhancement of stock market forecasting using an improved
fundamental analysis-based approach. Soft Computing, 21, 3735-3757. https://doi.org/10.1007/s00500-016-2028-y
9. Christie, R., & Renu, I. R. (2018). Fundamental analysis versus technical analysis - a comparative review. International
Journal of Recent Scientific Research, 9(1), 23009-23013. https://www.researchgate.net/publication/324516986_
FUNDAMENTAL_ANALYSIS_VERSUS_TECHNICAL_ANALYSIS-A_COMPARATIVE_REVIEW
10. Coleman, L. (2019). Fundamental Analysis of Equities. In New Principles of Equity Investment, (pp. 95-122). Emerald
Publishing Limited, Bingley. https://doi.org/10.1108/978-1-78973-063-020191006
11. Cont, R., & Tankov, P. (2007). Constant Proportion Portfolio Insurance in Presence of Jumps in Asset Prices.
Columbia University Center for Financial Engineering, Financial Engineering Report, 10, 1-27. https://doi.org/10.2139/
ssrn.1021084
12. Dunne, M. (2015). Stock market prediction. University College Cork, Cork. http://markd.ie/public/mark-dunne-
stock-market-prediction.pdf
13. Edirisinghe, N. C. P., & Zhang, X. (2007). Generalized DEA model of fundamental analysis and its application to
portfolio optimization. Journal of Banking & Finance, 31(11), 3311-3335. https://doi.org/10.1016/j.jbankfin.2007.04.008
14. Fajiang Liu, & Jun Wang (2012). Fluctuation prediction of stock market index by Legendre neural network with random
time strength function. Neurocomputing, 83, 12-21. https://doi.org/10.1016/j.neucom.2011.09.033
15. Galankashi, M. R., Rafiei F. M., & Ghezelbash, M. (2020). Portfolio selection: A fuzzy-ANP approach. Financial
Innovation, 6(1), 1-34. https://doi.org/10.1186/s40854-020-00175-4
16. Graham, B., & Dodd, D. L. (1934). Security Analysis. McGraw-Hill Education.
17. Herawati, A., & Putra, A. S. (2018). The Influence of Fundamental Analysis on Stock Prices: The Case of Food and
Beverage Industries. European Research Studies Journal, 21(3), 316-326. https://doi.org/10.35808/ersj/1063
18. Jatoi, M., Shabir, G., Hamad, N., Iqbal, N., & Muhammad, K. (2014). A regression impact of earning per share
on market value of share: a case study: cement industry of Pakistan. International Journal of Academic Research in
Accounting, Finance, and Management Sciences, 4, 221-227. https://doi.org/10.6007/IJARAFMS/v4-i4/1323
19. Jovic, S., Smigic Miladinovic, J., Micic, R., Markovic, S., & Rakic, G. (2019). Analyzing of exchange rate and gross
domestic product (GDP) by adaptive neuro-fuzzy inference system (ANFIS). Physica A: Statistical Mechanics and its
Applications, 513, 333-338. https://doi.org/10.1016/j.physa.2018.09.009
20. Khan, H. Z., Alin, S. T., & Hussain, A. (2011). Price prediction of share market using artificial neural network (ANN).
International Journal of Computer Applications, 22(2), 42-47. https://doi.org/10.5120/2552-3497
21. Kovács, L., & Terták, E. (2019). Financial Literacy-Theory and Evidence. Verlag Dashöfer. https://bankszovetseg.hu/
Public/publikacio/Financial%20literacy.pdf
22. Lam, M. (2004). Neural network techniques for financial performance prediction: integrating fundamental and
technical analysis. Decision Support Systems, 37(4), 567-581. https://doi.org/10.1016/S0167-9236(03)00088-5
Csesznik, Z., Gáspár, S., Thalmeiner, G., & Zéman, Z. / Economic Annals-XXI (2021), 190(5-6(2)), 119-127
126
ECONOMIC ANNALS-XXI
FINANCES, ACCOUNTING AND AUDIT
23. Lentner, Cs., Vasa, L., Kolozsi, P. P., & Zéman, Z. (2019). New dimensions of internal controls in banking after the
GFC. Economic Annals-XXI, 176(3-4), 38-48. https://doi.org/10.21003/ea.V176-04
24. Lin, Z. (2018). Modelling and forecasting the stock market volatility of SSE composite index using GARCH models.
Future Generation Computer Systems, 79(3), 960-972. https://doi.org/10.1016/j.future.2017.08.033
25. Macharia, P., & Gatuhi, S. K. (2013). Effect of financial performance indicators on market price of shares in commercial
banks of Kenya. International Journal of Management & Business Studies, 3(3), 57-60. http://www.ijmbs.com/33/peter.pdf
26. MarketInOut. (2021). Data collection 2015-2021. https://www.marketinout.com/stock-screener/stock_screener.php
27. Maryyam, A. (2016). Impact of firms’ performance on stock returns (evidence from listed companies of FTSE-100
index London, UK). Global Journal of Management and Business Research, 16(1), 30-39. https://globaljournals.org/
item/5870-impact-of-firms-performance-on-stock-returns-evidence-from-listed-companies-of-ftse-100-index-london-uk
28. Mohamed, E. A., Ahmed, I. E., Mehdi, R., & Hussain, H. (2021). Impact of corporate performance on stock price
predictions in the UAE markets: Neuro-fuzzy model. Intelligent Systems in Accounting, Finance and Management, 28(1),
52-71. https://doi.org/10.1002/isaf.1484
29. Nikou, M., Mansourfar, G., & Bagherzadeh, J. (2019). Stock price prediction using DEEP learning algorithm
and its comparison with machine learning algorithms. Journal of Intelligent Systems in Accounting, Finance and
Management, 26(4), 164-174. https://doi.org/10.1002/isaf.1459
30. Nti, I. K., Adekoya, A. F., & Weyori, B. A. (2020). A systematic review of fundamental and technical nalysis of stock
market predictions. Artificial Intelligence Review, 53, 3007-3057. https://doi.org/10.1007/s10462-019-09754-z
31. Rakićević, A., Milošević, P., Poledica, A., Dragović, I., & Petrović, B. (2019). Interpolative Boolean Approach for Fuzzy
Portfolio Selection. In Meier A., Portmann E., & Terán L. (Eds.) Applying Fuzzy Logic for the Digital Economy and Society.
Fuzzy Management Methods, (pp. 23-46). Springer, Cham. https://doi.org/10.1007/978-3-030-03368-2_2
32. Rounaghi, M., M., & Zadeh, F. N. (2016). Investigation of market efficiency and Financial Stability between S&P 500
and London Stock Exchange: Monthly and yearly Forecasting of Time Series Stock Returns using ARMA model. Physica
A: Statistical Mechanics and its Applications, 456(2), 10-21. https://doi.org/10.1016/j.physa.2016.03.006
33. Sági, J., Vasa, L., & Lentner, Cs. (2020). Innovative Solutions in the Development of Households’ Financial
Awareness: A Hungarian Example. Economics and Sociology, 13(3), 27-45.
34. Silva, A., Neves, R., & Horta, N. (2015). A hybrid approach to portfolio composition based on fundamental and
technical indicators. Expert Systems with Applications, 42(4), 2036-2048. https://doi.org/10.1016/j.eswa.2014.09.050
35. Suciu, T. (2013). Elements of stock market analysis. Bulletin of the Transilvania University of Brasov, 55(6(2)), 153-160.
http://webbut.unitbv.ro/BU2013/Series%20V/BULETIN%20V/026%20articol%20BUT%20suciu%20titus.pdf
36. Szilágyi, B. (2017). Portfolio insurance strategies: Analyzing the CPPI strategy. E-CONOM, 6(1), 3-18.
http://real.mtak.hu/74975
37. Thakur, A., Beck, R., Mostaghim, S., & Großmann, D. (2020). Survey into predictive key performance indicator
analysis from data mining perspective. 25th IEEE International Conference on Emerging Technologies and Factory
Automation (ETFA), 476-483. https://doi.org/10.1109/ETFA46521.2020.9212111
38. Thawornwong, S., & Enke, D. (2004). The adaptive selection of financial and economic variables for use with artificial
neural networks. Neurocomputing, 56, 205-232. https://doi.org/10.1016/j.neucom.2003.05.001
39. Thomsett, M. C. (1998). Mastering Fundamental Analysis. Dearborn Financial Publishing Inc.
40. Tsai, Ch.-F., & Hsiao, Y.-Ch. (2010). Combining multiple feature selection methods for stock prediction: Union,
intersection, and multi-intersection approaches. Decision Support Systems, 50(1), 258-269.
41. Uddin, M. B. (2009). Determinants of the market price of stock: a study on bank leasing and insurance companies
of Bangladesh. Journal of Modern Accounting and Auditing, 5(7), 1-7. https://silo.tips/download/determinants-of-
market-price-of-stock-a-study-on-bank-leasing-and-insurance-comp
42. Venkatesh, C. K. (2012). Fundamental analysis as a method of share valuation in comparison with technical analysis.
International Journal of Applied Financial Management Perspectives, 1(1), 79-81.
43. Wewege, L., & Thomsett, M. C. (2019). The Digital Banking Revolution: How Fintech Companies Are Transforming
the Retail Banking Industry Through Disruptive Financial Innovation. De Gruyter.
44. Yiwen,Y., Guizhong, L., & Zongping, Z. (2000). Stock market trend prediction based on neural networks, multi-
resolution analysis and dynamical reconstruction. In Proceedings of the IEEE/IAFE/INFORMS 2000 conference on
computational intelligence for financial engineering (pp. 155-156). https://doi.org/10.1109/CIFER.2000.844615
45. Young, M. G. (2010). The complete guide to selling stocks short: Everything you need to know explained simply.
Florida: Atlantic publishing group.
Received 7.04.2021
Received in revised form 12.05.2021
Accepted 22.05.2021
Available online 10.07.2021
Csesznik, Z., Gáspár, S., Thalmeiner, G., & Zéman, Z. / Economic Annals-XXI (2021), 190(5-6(2)), 119-127
127
