Turkish Stock Market Research Articles

Can cryptocurrencies be a hedging tool? Evidence from the Turkish stock market

ABSTRACT The study examines the hedge properties of BTC, ETH, and BNB for the Istanbul Stock Exchange 100 Index (XU100). Investors who add cryptocurrencies to XU100-only portfolios reduce risks by 12.10% to 18.60%. Results show that during global events like COVID-19 and the Russia-Ukraine war, the hedge effectiveness of cryptocurrencies is low. However, during Turkey-specific events such as the Pastor Brunson currency shock, the swap crisis, the dismissal of Central Bank Governor Naci Ağbal, irrational interest rate cuts, the announcement of the currency-protected deposit system, and the February 6 earthquake, the hedging properties of cryptocurrencies against the XU100 index significantly improve.

An algorithmic approach to portfolio construction: A Turkish stock market case

The goal of building a diversified portfolio is to mitigate risks and manage risk-reward tradeoffs. Diversification is also crucial for ensuring the long-term success of a portfolio. Although passive investment has been on the rise in most developed markets, it has not gained wider acceptance in some emerging markets, such as Türkiye. This study proposes an approach to construct a diversified portfolio that serves as a passive investment tool in the context of the Turkish stock market. Despite the long history of equity markets in Türkiye, almost all available passive investment alternatives are prohibitively expensive, unlike those in developed markets. We design a simple methodology that addresses the essential components of building a successful portfolio while avoiding excessive fees. Additionally, we propose a dynamic balancing strategy that algorithmically adjusts the weight of each stock in the portfolio. We test this approach with historical data, demonstrating that it can achieve reasonable returns with minimal effort. Even when its performance does not beat the benchmark, the percentage deviation is still below the management fees charged for alternative investments.

Integrating PCA with deep learning models for stock market Forecasting: An analysis of Turkish stocks markets

Financial data such as stock prices are rich time series data that contain valuable information for investors and financial professionals. Analysis of such data is critical to understanding market behaviour and predicting future price movements. However, stock price predictions are complex and difficult due to the intense noise, non-linear structures, and high volatility contained in this data. While this situation increases the difficulty of making accurate predictions, it also creates an important area for investors and analysts to identify opportunities in the market. One of the effective methods used in predicting stock prices is technical analysis. Multiple indicators are used to predict stock prices with technical analysis. These indicators formulate past stock price movements in different ways and produce signals such as buy, sell, and hold. In this study, the most frequently used ten different indicators were analyzed with PCA (Principal Component Analysis. This study aims to investigate the integration of PCA and deep learning models into the Turkish stock market using indicator values and to assess the effect of this integration on market prediction performance. The most effective indicators used as input for market prediction were selected with the PCA method, and then 4 different models were created using different deep learning architectures (LSTM, CNN, BiLSTM, GRU). The performance values of the proposed models were evaluated with MSE, MAE, MAPE and R2 measurement metrics. The results obtained show that using the indicators selected by PCA together with deep learning models improves market prediction performance. In particular, it was observed that one of the proposed models, the PCA-LSTM-CNN model, produced very successful results.

Do High-Frequency Trading Affect Bubble Formation in Stock Markets? Evidence from Emerging Stock Market

This study examines the factors that affect bubble formation in the Turkish stock market, Borsa Istanbul (BIST), which is a major emerging market where high-frequency trading (HFT) is a relatively recent phenomenon. The study uses daily stock price data from the period from March 11 2020 to December 31 2020. The data was obtained from Borsa Istanbul. The study finds that HFT transactions play a significant role in bubble formation. HFT transactions can create excessive volatility and manipulation in the market with their high trading volumes and quick trading capabilities. This can increase the risk of bubble formation. The study highlights the importance of regulation and supervision to mitigate the effects of HFT in financial markets. Regulations aimed at increasing transparency in the market can help investors make more informed decisions.

Momentum trading: How it differs among investor segments

ABSTRACT This study explores the momentum trading behaviours across different investor segments in the Turkish stock market. The empirical analysis confirms the positive return of the momentum strategy both in absolute terms and relative to the market benchmark, and the results support distinctive trading patterns among different investor segments. Specifically, foreign investors follow momentum trading, while domestic individuals lean towards contrarian trading. Further analysis shows that domestic individual investors exhibit a propensity to sell stocks with unrealised capital gains and to increase holdings of stocks with unrealised capital loss consistent with the disposition effect. Nevertheless, the trading behaviour of domestic individual investors could not be explained solely by the disposition effect. In contrast, foreign investors increase ownership share in stocks with unrealised capital gains but their momentum trading behaviour is confirmed even after controlling for disposition effect. These findings contribute to the broader understanding of investor trading behaviour within an emerging market context and provide valuable insights into the applicability of results from developed markets.

Portfolio optimization and risk management through Hierarchical Risk Parity and Logic Learning Machine: a case study applied to the Turkish stock market

This study explores an innovative approach to portfolio optimization, bridging traditional Modern Portfolio Theory (MPT) with advanced Machine Learning techniques. We start by recognizing the significance of Markowitz's model in MPT and quickly proceed to focus on the Hierarchical Risk Parity (HRP) method. HRP overcomes some of the limitations of Markowitz's model, particularly in managing complex asset correlations, by offering a more refined risk management strategy that ensures balanced risk distribution across the portfolio. The paper then introduces an innovative Machine Learning approach that employs the Logic Learning Machine (LLM) method to enhance the explainability of the Hierarchical Risk Parity strategy. Such integration is considered the core research part of the study, given that its application makes the output of the model more accessible and transparent. A case study based on the Turkish stock market has been provided as an example. The combination of traditional financial theories with modern Machine Learning tools marks a significant advancement in investment management and portfolio optimization, emphasizing the importance of clarity and ease of understanding in complex financial portfolio models.

Financial Decisions and Value-at-Risk: Empirical Evidence from BIST 100 Companies

This study examines the relationship between financial decisions and the value-at-risk (VaR) of companies operating in the Turkish stock market. The study contains semi-annual data of non-financial BIST 100 Index companies spanning from January 2010 to June 2023. Companies’ VaR are calculated using Monte-Carlo simulation, bootstrap, delta-normal, and historical simulation methods and included in separate econometric models as dependent variables. Financial decisions are represented through financial ratios in line with the basic principles of corporate finance and included as explanatory variables in econometric models. The study employs a five-stage panel data methodology. 
 Findings reveal that the impact of financial decisions regarding working capital management, capital structure, dividend pay-out, and growth policies on companies’ VaR differ according to the VaR calculation method. Notably, findings show that financial decisions explain the changes in VaR calculated by Bootstrap method with the highest success rate, aligning with existing finance literature. Prudent financing policies and flexible investment strategies in working capital management, enhanced profitability and financial performance, and sales growth exhibit dampening effects on VaR. Conversely, heightened leverage and long-term borrowings, decisions to pay-out dividends, and growth in foreign investments have increasing effects on VaR. Furthermore, the study identifies the Covid-19 pandemic as exerting a negative influence on VaR.

The Effects of Macroeconomic Variables on the BIST 100 Index: ARDL and NARDL Approaches

The objective of this research is to analyse the signal, magnitude, and significance of both symmetric and asymmetric effects of interest rate, taxes, exchange rate, oil price, and gold price on the Turkish stock market (BIST100). The autoregressive distributed lag (ARDL) technique was used in both linear and non-linear formats. The F-Bounds test of the linear ARDL test suggests that the variables do not exhibit long-term integration. Nevertheless, the F-bounds test of the nonlinear ARDL (NARDL) test confirms the presence of cointegration among the variables. Therefore, the research heavily relies on the NARDL model. The empirical evidence indicates the long-term influence of the exchange rates rate, gold price, and interest rate on the BIST100 index is asymmetric. Additionally, the asymmetrical effects of interest rates, taxes, exchange rates, oil prices, and gold prices in the short term have an impact on the BIST100.

Forecasting Stock Prices via Deep Learning During COVID-19: A Case Study from an Emerging Economy

In this study we apply a Deep Learning Technique to predict stock prices for the 30 stocks that compose the BIST30, Turkish Stock Market Index before and after the onset of Covid-19 crises. Specifically, we utilize the Bi-Directional Long-Short Term Memory (BiLSTM) model which is a variation of the Long-Short-Term Memory (LSTM) model to predict stock prices for the BIST30 stocks. We compare the performance of the model to other commonly used machine learning models like decision tree, bagging, random forest, adaptive boosting (Adaboost), gradient boosting, and eXtreme gradient boosting (XGBoost), artificial neural networks (ANN), and other deep Leaning models like recurrent neural network (RNN), and the Long-Short-Term Memory (LSTM) model. The BiLSTM model seems to have better performance compared to conventional models used for predicting stock prices and continues to have superior performance in the Covid19 period. The LSTM model seems to have a good overall performance and is the next best model.

FOURIER CAUSALITY AND VOLATILITY SPILLOVER PERSPECTIVES TO ANALYZE THE EFFECT OF TERRORISM ON TURKISH AND EUROPEAN STOCK MARKETS

Terrorism has become a curse for most of the underdeveloped economies. Even relatively developed regions like Europe and Turkey are struggling to combat it. Besides the economic and political consequences, terrorist activities also have psychological cost that may reflect in stock market. This study investigates the causal effects of systematic shocks on mean returns and volatility of the general and 14 sectoral indices in Europe and Turkey using contemporary causality tests like Fourier Toda-Yamamoto Causality test (Nazlioglu et al., 2016), Fourier Standard Granger Causality test (Enders and Jones, 2015), and Causality in Variance (Hafner and Herwartz, 2006). Tourism related sectors turn out to be fragile whereas financial sector have significant resilience to terrorist attacks. Moreover, the spillover analysis shows that the Turkish stock market turns out to be more fragile to terrorist attacks in Europe than the other way around.

THE IMPACT OF 2023 KAHRAMANMARAŞ EARTHQUAKES ON REAL ESTATE RELATED SECTORS: AN EVENT STUDY ANALYSIS

Kahramanmaraş earthquakes devastatingly hit the northern Syria and 11 provinces of Türkiye, causing thousands of deaths, injuries and property losses. The magnitude of the earthquakes and the extent of their impacts were huge enough to affect the entire Turkish economy. Real estate industry has been one of the most affected sectors as thousands of buildings were collapsed or damaged by the quake. This study aims to explore the impacts of Kahramanmaraş earthquakes on real estate related sectors in the Turkish stock market: Construction, cement-concrete, iron-steel, real estate investment trusts, and insurance. Using an event study methodology, our short-run analyses indicated that all given sectors were affected by the earthquakes. According to our findings, abnormal returns varied among the sectors: The construction materials sectors had positive abnormal returns while the insurance sector did abnormal returns on the opposite way. The findings are vital for market participants, policymakers and governments.

Is ‘Herding’ Peculiar to Certain Stocks? A Perspective from the Turkish Stock Market

We test the existence of daily/weekly herding behavior in the Turkish stock market between June 2013 and October 2020 on the stocks that remained listed on the benchmark stock index over the analysis period. Rather than performing the test on a set of stocks belonging to firms with different characteristics as in the literature, we conduct it on subsets of stocks we form based on foreign ownership ratio, firm size (measured by total assets), and prominent financial indicators (price-to-earnings and market-to-book ratios). Our analysis provides no evidence of herding behavior but yields important insights. Specifically, it demonstrates that financial indicators have no bearing on herding behavior, but investor type and firm size may. A slight indication of herding tendency emerges in stocks with a relatively higher investment from local investors but disappears in those with a comparatively higher investment from foreign investors. This finding suggests a potential market knowledge disparity between local and foreign investors, with the less expert being the local group. Moreover, a faint sign of herding tendency also appears in stocks that belong to small firms, possibly due to a heightened uncertainty inherent in such stocks.

STATISTICAL ANALYSIS BY WAVELET LEADERS REVEALS DIFFERENCES IN MULTI-FRACTAL CHARACTERISTICS OF STOCK PRICE AND RETURN SERIES IN TURKISH HIGH FREQUENCY DATA

The price and return time series are two distinct features of any financial asset. Hence, examining the evolution of multiscale characteristics of price and returns sequential data in time domain would be helpful in gaining a better understanding of the dynamical evolution mechanism of the financial asset as a complex system. In fact, this is important to understand their respective dynamics and to design their appropriate predictive models. The main purpose of the current work is to investigate the multiscale fractals of price and return high frequency data in Turkish stock market. In this regard, the wavelet leaders computational method is applied to each high frequency data to reveal its multi-fractal behavior. In particular, the method is applied to a large set of Turkish stocks and statistical results are performed to check for (i) presence of multi-fractals in price and return series and (ii) differences between prices and returns in terms of multi-fractals. Our statistical results show strong evidence that high frequency price and return data exhibit multi-fractal dynamics. In addition, they show evidence of distinct fractal characteristics on different scales between price and return series. Furthermore, our statistical results show evidence of differences in local fluctuation characteristics of price and return time series. Therefore, differences in local characteristics are useful to build specific predictive models for each type of data for better modeling and prediction to generate profits. Besides, we found evidence that both long-range correlations and fat-tail distributions contribute to the multifractality in Turkish stocks. This finding can be attributed to the major role played by international investors in increasing the volatility of Turkish stocks.

Testing the Adaptive Market Hypothesis in Equity Markets in Global Financial Crisis Periods: An Application on Borsa Istanbul Indices

We aim in this study to investigate the existence of the Adaptive Market Hypothesis in the Turkish stock market during the global crisis periods. In other words, it has been investigated whether there are periods in the stock market in Turkey is both efficient and inefficient. For this purpose, Borsa Istanbul's main index (XU100) and selected sector indices (XBANK, XGIDA, XTEKS, XTRZM) were tested in the crisis environments, the Asian Financial Crisis, the American "Dotcom" crisis, the Mortgage crisis, the European debt crisis and finally the Covid-19 crisis. Automatic Portmanteau and Wild Bootstrap Automatic Variance Ratio tests were used in the research. According to the results obtained, findings compatible with the Adaptive Market Hypothesis were reached in all Borsa Istanbul indices within the scope of the research. It has been observed that there may be fluctuations in market efficiency at different frequencies and durations in relation to the nature of the crisis and the source of its output. It is thought that the study is original and will contribute to the literature for the following reasons; the Adaptive Market Hypothesis for the Turkish stock market has been tested for all crisis periods in the recent history and the effects of the crises on the sectors are also examined in terms of effectiveness.

Multi-Scale Sample Entropy Analysis of the Turkish Stock Market Efficiency

This study evaluates the market efficiency of the market index and five main sector indices in the Turkish stock market: BIST 100 (XU100), BIST Industrials (XUSIN), BIST Services (XUHIZ), BIST Transportation (XULAS), BIST Financials (XUMAL), and BIST Technology (XUTEK) for the pre-and post-COVID-19 pandemic, covering the period from January 2017 to July 2022. Market efficiency is calculated using a multiscale entropy-based method for the scales of 1 to 20 business days. Entropy can yield a relative degree of efficiency, by contrast with previous methods that dealt with the efficiency question in all-or-nothing form. On a daily scale, during the pre-COVID-19 pandemic period, the XUHIZ, XU100 and XULAS indices exhibit the highest efficiency. However, in the post-COVID-19 pandemic period, the XUMAL and XU100 indices demonstrate the highest efficiency. The findings suggest that the efficiency of all indices has declined due to the COVID-19 pandemic, with the XULAS index showing the most significant decrease in informational efficiency. A general tendency of reduced informational efficiency levels is found as the time scale increases in both periods. Therefore, the indices are partially efficient for certain time scales, indicating that they are not fully efficient.

How Vulnerable is the Turkish Stock Market to the Credit Default Swap? Evidence from the Markov Switching GARCH Model

How Vulnerable is the Turkish Stock Market to the Credit Default Swap? Evidence from the Markov Switching GARCH Model

The effect of prospect theory value on asset returns on the Borsa Istanbul

The goal of this study is to test the validity of the prospect theory in the Borsa Istanbul (BIST) over the sample period September 2009 to December 2019. The prospect theory values of the stocks are generated from their historical return distributions following the method by Barberis et al. (2016). Panel data analysis is implemented in six different models with market and nonmarket factors for three different data sets of stocks listed on the BIST. We employed control variables, such as Fama and French (2015) five-factor model (FF5M) factors as well as past return and skewness indicators, in the models in addition to the prospect theory value and test whether prospect theory can predict subsequent stock returns. The results show that the prospect theory value has a statistically significant effect on the asset returns and its impact is seen in particular on small-cap stocks in the Turkish stock market.

Profitability of insider trading in Turkey

This study presents the first comprehensive evidence of insider trading patterns and abnormal profits in the Turkish stock market using almost 65,000 insider transactions for the period of 2008–2019. Our findings show that insiders earn a significant 6.58% abnormal profit during the one year following insider trading. Officers, directors, and institutional investors earn even more. Both purchases and sales are profitable. Top executives, major shareholders, and institutional investors earn significant dollar profits. Additionally, uninformed investors can beat the market by mimicking the portfolios of insiders, while evidence shows that regulatory changes do not reduce insiders’ profits. Finally, this study provides important trading implications for investors and regulatory implications for policymakers everywhere.

The aggregate and sectoral time-varying market efficiency during crisis periods in Turkey: a comparative analysis with COVID-19 outbreak and the global financial crisis

This study aims to examine the time-varying efficiency of the Turkish stock market’s major stock index and eight sectoral indices, including the industrial, financial, service, information technology, basic metals, tourism, real estate investment, and chemical petrol plastic, during the COVID-19 outbreak and the global financial crisis (GFC) within the framework of the adaptive market hypothesis. This study employs multifractal detrended fluctuation analysis to illustrate these sectors’ multifractality and short- and long-term dependence. The results show that all sectoral returns have greater persistence during the COVID-19 outbreak than during the GFC. Second, the real estate and information technology industries had the lowest levels of efficiency during the GFC and the COVID-19 outbreak. Lastly, the fat-tailed distribution has a greater effect on multifractality in these industries. Our results validate the conclusions of the adaptive market hypothesis, according to which arbitrage opportunities vary over time, and contribute to policy formulation for future outbreak-induced economic crises.

Petrol Fiyatları ile Seçilmiş Makroekonomik Değişkenlerin Hisse Senedi Piyasasına Asimetrik Etkileri: Türkiye Örneği

This paper investigates the asymmetric impacts of crude oil prices and other selected macroeconomic variables on the Turkish stock market for the period between 2005:01-2021:06 through the combination of the NARDL model and the quantile regression approach. The findings support the existence of cointegration between the stock market and oil prices. The variations in oil prices have asymmetric impacts in the long run. A positive shock by 1% decreases stock returns by 0.67%, while oil price declines have no significant impact. Quantile regressions show that the effects of oil price shocks are more visible at the low levels of the stock market.