Tatay Tibor
7801658744
Publications - 18
Consumer Expenditure-Based Portfolio Optimization
Publication Name: International Journal of Financial Studies
Publication Date: 2025-06-01
Volume: 13
Issue: 2
Page Range: Unknown
Description:
This study examines whether portfolio optimization can be effectively based on annual changes in the harmonized index of consumer prices (HICP) data. Specifically, we assess whether asset allocation based on consumer expenditure can generate superior returns compared to static or equal-weighted asset allocation. To explore this, we use consumer expenditure data from HICP statistics categorized by COICOP. Our findings indicate that this strategy outperforms a buy-and-hold benchmark by 13.32% in terms of the Sharpe Ratio and exceeds an annual equal-weighted rebalancing strategy by 3.11%. Additionally, both the Calmar and Sterling Ratios demonstrate improved performance, further reinforcing the robustness of this approach. Furthermore, a hypothetical scenario where sector weights from the end of the given year—though not yet available during the year—are used suggests even greater improvements in performance. A high-sample bootstrap simulation confirms that the observed performance differences are not random but reflect the independent effectiveness of asset allocation based on consumer expenditure trends. This result strengthens the validity of our backtesting findings, indicating that the examined strategy could generate excess returns compared to passive portfolio managment and fixed-weight rebalancing approaches. The result of the study is therefore the development of an effective portfolio rebalancing strategy.
Open Access: Yes
DOI: 10.3390/ijfs13020099
Evaluating Fiscal and Monetary Policy Coordination Using a Nash Equilibrium: A Case Study of Hungary
Publication Name: Mathematics
Publication Date: 2025-05-01
Volume: 13
Issue: 9
Page Range: Unknown
Description:
Effective coordination between fiscal and monetary policy is crucial for macroeconomic stability, yet achieving it presents significant challenges due to differing objectives and institutional setups. This study evaluates the strategic interaction between fiscal and monetary authorities in Hungary from 2013 to 2023, employing the Nash equilibrium framework under the assumption of non-cooperative behavior. By modeling the authorities as independent players optimizing distinct payoff functions based on key economic indicators (interest rates, government spending, inflation, output gap, fiscal deficit, and public debt), the analysis estimates the best response strategies and computes the resulting Nash equilibrium. The key findings reveal persistent deviations between actual policies and the computed equilibrium strategies. Specifically, actual fiscal policy was consistently more expansionary (average actual deficit −2.6% to 7.6% GDP vs. equilibrium recommendations ranging from 8.5% surplus to −3.0% deficit) than the Nash equilibrium indicated, particularly during periods of economic growth. Monetary policy often lagged in equilibrium recommendations, maintaining low interest rates (e.g., 0.9% actual vs. 11.5% equilibrium in 2019) before implementing sharp increases (13% actual vs. approx. 3.5–3.8% equilibrium in 2022–2023) that significantly overshot the equilibrium. These misalignments underscore potential suboptimal outcomes arising from independent policymaking, contributing to increased public debt and heightened inflationary pressures in the Hungarian context. This study highlights the potential benefits of aligning policies closer to mutually consistent strategies, suggesting that improved coordination frameworks could enhance macroeconomic stability, offering insights relevant to Hungary and similar economies.
Open Access: Yes
DOI: 10.3390/math13091427
Eurozone inflation in times of crises: an application of cluster analysis
Publication Name: Regional Statistics
Publication Date: 2025-01-01
Volume: 15
Issue: 3
Page Range: 579-600
Description:
This study investigates whether homogeneous clusters can be identified among Eurozone countries based on the main HICP (harmonized index of consumer prices) sub-indicators between the first quarter of 2019 and the last quarter of 2023. We use hierarchical cluster analysis to explore how different Eurozone member countries can be grouped according to the different components of the HICP that reflect differences in the main causes of inflation. We point out that the factors discussed in the inflation theory literature that affect different groups of economic agents in different ways can also be interpreted geographically within the Eurozone. Baltic countries tend to follow inflation paths that are different from those of other member states, but outliers also exist among the most advanced economies in the EU. Diverging inflation patterns have much to do with economic convergence, but the dispersion of monthly inflation rates suggests that administrative pricing and policy considerations, particularly energy policy, may be responsible for most of the divergence in inflation and will largely determine the emergence of clusters from 2022 onwards. In light of the results of our study, we conclude that there may be significant differences in the adjustments of individual countries compared to the policy measures that are optimal from the European Central Bank’s perspective.
Open Access: Yes
DOI: 10.15196/RS150308
INVESTIGATING THE ROLE OF ACTIVATION FUNCTIONS IN PREDICTING THE PRICE OF CRYPTOCURRENCIES DURING CRITICAL ECONOMIC PERIODS
Publication Name: Virtual Economics
Publication Date: 2024-12-31
Volume: 7
Issue: 4
Page Range: 64-91
Description:
Accurate cryptocurrency price forecasting is crucial due to the significant financial implications of prediction errors. The volatile and non-linear nature of cryptocurrencies challenges traditional statistical methods, revealing a gap in effective predictive modelling. This study addresses this gap by examining the impact of activation functions on neural network models during critical economic periods, specifically aiming to determine how optimising activation functions enhances accuracy in neural network models, including RNN, GRU, LSTM, and hybrid architectures. Using data from January 2016 to June 2022—encompassing stable periods, the COVID-19 pandemic, and the onset of the 2022 Ukraine conflict—we analysed price trends under various market conditions. Our methodology involved testing three activation functions (ReLU, sigmoid, and Tanh) across these models. Both univariate and multivariate analyses were conducted, with the latter incorporating additional metrics such as opening, highest, and lowest prices. The results indicate that optimising activation functions enhances prediction accuracy. Among the models, GRU demonstrated the highest accuracy, whereas RNN was the least efficient. Multivariate models outperformed univariate ones, highlighting the benefits of incorporating comprehensive data. Notably, the Tanh activation function led to the greatest improvements, particularly in underperforming models such as RNN. These findings underscore the critical role of activation function selection in enhancing the predictive power of neural networks for cryptocurrency markets. Optimising activation functions can lead to more reliable forecasts, facilitating better trading decisions and risk management. This study highlights activation functions as key parameters in neural network modelling, encouraging further exploration. Future research could investigate different economic periods and cryptocurrency behaviours to assess model robustness. Additionally, examining a broader range of cryptocurrencies may reveal whether the benefits of activation function optimisation are consistent across various assets. Incorporating external factors such as macroeconomic indicators or social media sentiment could further enhance models and improve forecasting accuracy.
Open Access: Yes
The Impact of Rebalancing Strategies on ETF Portfolio Performance
Publication Name: Journal of Risk and Financial Management
Publication Date: 2024-12-01
Volume: 17
Issue: 12
Page Range: Unknown
Description:
This research explores the efficacy of rebalancing strategies in a diversified portfolio constructed exclusively with exchange-traded funds (ETFs). We selected five ETF types: short-term U.S. Treasury bonds, U.S. equities, global commodities, U.S. real estate investment trusts (REITs), and a multi-strategy hedge fund. Using a 10-year historical period, we applied a unique simulation model to generate random portfolios with varying asset weights and rebalancing tolerance bands, assessing the impact of rebalancing premiums on portfolio performance. Our study reveals a significant positive correlation (r = 0.6492, p < 0.001) between rebalancing-weighted returns and the Sharpe ratio, indicating that effective rebalancing enhances risk-adjusted returns. Support vector regression (SVR) analysis shows that rebalancing premiums have diverse effects. Specifically, equities and commodities benefit from rebalancing with improved risk-adjusted returns, while bonds and REITs demonstrate a negative relationship, suggesting that rebalancing might be less effective or even detrimental for these assets. Our findings also indicate that negative portfolio rebalancing returns combined with positive rebalancing-weighted returns yield the highest average Sharpe ratio of 0.4328, highlighting a distinct and reciprocal relationship between rebalancing effects at the asset and portfolio levels. This research highlights that while rebalancing can enhance portfolio performance, its effectiveness varies by asset class and market conditions.
Open Access: Yes
DOI: 10.3390/jrfm17120533
Optimising Portfolio Risk by Involving Crypto Assets in a Volatile Macroeconomic Environment
Publication Name: Risks
Publication Date: 2024-04-01
Volume: 12
Issue: 4
Page Range: Unknown
Description:
Portfolio diversification is an accepted principle of risk management. When constructing an efficient portfolio, there are a number of asset classes to choose from. Financial innovation is expanding the range of instruments. In addition to traditional commodities and securities, other instruments have been added. These include cryptocurrencies. In our study, we seek to answer the question of what proportion of cryptocurrencies should be included alongside traditional instruments to optimise portfolio risk. We use VaR risk measures to optimise the process. Diversification opportunities are evaluated under normal return distributions, thick-tailed distributions, and asymmetric distributions. To answer our research questions, we have created a quantitative model in which we analysed the VaR of different portfolios, including crypto-diversified assets, using Monte Carlo simulations. The study database includes exchange rate data for two consecutive years. When selecting the periods under examination, it was important to compare favourable and less favourable periods from a macroeconomic point of view so that the study results can be interpreted as a stress test in addition to observing the diversification effect. The first period under examination is from 1 September 2020 to 31 August 2021, and the second from 1 September 2021 to 31 August 2022. Our research results ultimately confirm that including cryptoassets can reduce the risk of an investment portfolio. The two time periods examined in the simulation produced very different results. An analysis of the second period suggests that Bitcoin’s diversification ability has become significant in the unfolding market situation due to the Russian-Ukrainian war.
Open Access: Yes
Navigating Inflation Challenges: AI-Based Portfolio Management Insights
Publication Name: Risks
Publication Date: 2024-03-01
Volume: 12
Issue: 3
Page Range: Unknown
Description:
After 2010, the consumer price index fell to a low level in the EU. In the euro area, it remained low between 2010 and 2020. The European Central Bank has even had to take action against the emergence of deflation. The situation changed significantly in 2021. Inflation jumped to levels not seen for 40 years in the EU. Our study aims to use artificial intelligence to forecast inflation. We also use artificial intelligence to forecast stock index changes. Based on the forecasts, we propose portfolio reallocation decisions to protect against inflation. The forecasting literature does not address the importance of structural breaks in the time series, which, among other things, can affect both the pattern recognition and prediction capabilities of various machine learning models. The novelty of our study is that we used the Zivot–Andrews unit root test to determine the breakpoints and partitioned the time series into training and testing datasets along these points. We then examined which database partition gives the most accurate prediction. This information can be used to re-balance the portfolio. Two different AI-based prediction algorithms were used (GRU and LSTM), and a hybrid model (LSTM–GRU) was also included to investigate the predictability of inflation. Our results suggest that the average error of the inflation forecast is a quarter of that of the stock market index forecast. Inflation developments have a fundamental impact on equity and government bond returns. If we obtain a reliable estimate of the inflation forecast, we have time to rebalance the portfolio until the inflation shock is incorporated into government bond returns. Our results not only support investment decisions at the national economy level but are also useful in the process of rebalancing international portfolios.
Open Access: Yes
Euro area economic growth between 2010 and 2019 in the light of secular stagnation theory
Publication Name: Public Finance Quarterly
Publication Date: 2023-09-29
Volume: 69
Issue: 3
Page Range: 72-88
Description:
Achieving economic growth remains an important issue for economic policy today. Growth in developed economies has slowed considerably in recent decades. In our study, we examine economic growth in the euro area between 2010 and 2019 in the light of secular stagnation theory. The concept of secular stagnation was developed by Hansen after the Great Depression of 1929-33. According to this theory, the causes of secular stagnation are low population growth and weak technological development. The concept was brought back into the economic discourse after 2010 by Summers. Following the 2008 crisis, euro area economies should have adjusted to a higher growth rate. Instead, growth remained below 2% for all but one year, below potential output for most of the decade. Investment rates have barely risen despite euro interest rates falling to near zero. The euro areas population barely grew despite a net migration surplus, putting a brake on employment growth. The available data suggest that neither employment growth nor productivity growth have boosted economic growth. The low level of economic growth and the evolution of the underlying factors are consistent with the theoretical assumptions described by Hansen and his followers.
Open Access: Yes
Evaluating the Effectiveness of Modern Forecasting Models in Predicting Commodity Futures Prices in Volatile Economic Times
Publication Name: Risks
Publication Date: 2023-02-01
Volume: 11
Issue: 2
Page Range: Unknown
Description:
The paper seeks to answer the question of how price forecasting can contribute to which techniques gives the most accurate results in the futures commodity market. A total of two families of models (decision trees, artificial intelligence) were used to produce estimates for 2018 and 2022 for 21- and 125-day periods. The main findings of the study are that in a calm economic environment, the estimation accuracy is higher (1.5% vs. 4%), and that the AI-based estimation methods provide the most accurate estimates for both time horizons. These models provide the most accurate forecasts over short and medium time periods. Incorporating these forecasts into the ERM can significantly help to hedge purchase prices. Artificial intelligence-based models are becoming increasingly widely available, and can achieve significantly better accuracy than other approximations.
Open Access: Yes
Portfolio composition and the zero lower bound–evidence from the eurozone countries
Publication Name: Statisztikai Szemle
Publication Date: 2023-01-01
Volume: 101
Issue: 9
Page Range: 793-818
Description:
Between 2008 and 2020 it has been a common practice among main central banks to keep the policy rate at or around zero. Apart from the expected macroeconomic consequences described partly by liquidity trap theories and structural macroeconomic models discussing the effectiveness of economic policy at the zero lower bound (ZLB), moderate interest rates have a notable influence on the portfolio optimising decisions of economic actors as well. The paper thus endeavours to reveal the wealth effect at the ZLB. Firstly, it compares how the various monetary aggregates and sectoral portfolios changed in the USA and in the eurozone between 2000 and 2020 contrasting the empirical facts with the theoretical assumptions and the experience of the Japan’s lost decade. Secondly, it examines the impact of the common monetary policy at the ZLB on the portfolio structure of individual countries of the eurozone. Hierarchical cluster analysis is applied using Eurostat sectoral financial asset statistics for selected years between 2005 and 2019. After choosing the best asset-to-GDP variables of sectoral financial asset holdings, countries are separated in different clusters based on Squared Euclidean distance and variables are standardised to z-scores. The analysis revealed that low interest rates cause significant portfolio rearrangements in the eurozone as a whole. Moreover, there is much greater diversity between individual member states originally than the way monetary policy influenced differences in the portfolio composition of economic sectors, even some convergence between core and periphery countries is observable.
Open Access: Yes
Inhomogeneous Financial Markets in a Low Interest Rate Environment—A Cluster Analysis of Eurozone Economies
Publication Name: Risks
Publication Date: 2022-10-01
Volume: 10
Issue: 10
Page Range: Unknown
Description:
In the present paper, we investigate the financial homogeneity of the euro area economies by contrasting eurozone countries’ responses to monetary policy steps to the theoretical assumptions of the liquidity trap phenomenon. Our assumption is that the euro area economies are not completely homogeneous. Hence, in a zero-interest rate environment, the asset holding decisions of economic agents exhibit detectable differences across countries. We verify our assumptions using Eurostat data. We use the financial asset stocks of the euro area countries to cluster the countries concerned. Previous literature has not examined changes in the ratio of financial assets to GDP, nor differences in structural changes in the total stock of financial assets under the zero lower bound. The paper uses k-centers cluster analysis based on Euclidean distance for detecting changes in the portfolio holdings of eurozone economic actors owing to economic crises and monetary policy responses. The results confirm that euro area financial markets are fragmented. There are significant differences across asset markets of different Eurozone countries, both during and after the crisis. Despite some similarities in the portfolio rearrangement across countries, the ECB’s monetary policy does not have a uniform impact on euro area financial markets, and notable differences prevail in the financial asset structures of the economies concerned.
Open Access: Yes
The Impact of Changes in Financial Supervision on the Profitability of the Hungarian Banking Sector
Publication Name: Economies
Publication Date: 2022-07-01
Volume: 10
Issue: 7
Page Range: Unknown
Description:
Since 2013, the central bank has been responsible for supervision in Hungary. In addition to the regulatory change, a law was published in the same year that started the process of abolishing the savings co-operative system. This paper investigates the impact of these two significant changes on the profitability of the Hungarian banking sector between 2003 and 2019 using dynamic panel model estimates. The supervisory change has reduced the profitability of credit institutions and tighter supervision has been implemented. The transformation of the savings co-operative system was in fact an integration that led to the disappearance of savings co-operatives by 2019. Competition in the market has been weakened, which has increased the profitability of the remaining financial institutions. The results were robust in terms of the multiple specifications and profitability ratio.
Open Access: Yes
Mezogazdasagi nyugdijak finanszirozasa az europai kontinensen
Publication Name: Public Finance Quarterly
Publication Date: 2022-01-01
Volume: 67
Issue: 1
Page Range: 82-98
Description:
No description provided
Open Access: Yes
Financing of Agricultural Pensions on the European Continent
Publication Name: Public Finance Quarterly
Publication Date: 2022-01-01
Volume: 67
Issue: 1
Page Range: 83-99
Description:
Supporting agriculture in Europe is important for many reasons: on the one hand, to secure food supplies, and on the other, to ensure the sustainability of rural lifestyles. But in recent decades, rural populations have also been affected by population ageing. Different agricultural pension schemes have been set up in European countries, taking into account the specificities of the agricultural sector. Pension funds have tended to be more important where the role of small farms was significant and the pension system was of the fully Bismarckian type. In general, they were not introduced where a 'kolkhoz system' existed in East-Central Europe before 1990. In our study we looked at the different forms that have been implemented. We have reviewed the changes that have taken place in recent decades and found that in some countries, states have supplemented contributions to pension payments by up to 75-85%. Our methodology involves document analysis and comparative assessment. We argue that it is worthwhile to encourage farmers to continue production on smaller farms by providing special sectoral support, career funding and pensions in order to meet social and environmental objectives.
Open Access: Yes
Sharing communities – Community currency in the sharing economy
Publication Name: Society and Economy
Publication Date: 2021-03-01
Volume: 43
Issue: 1
Page Range: 38-59
Description:
For the further development and more efficient operation of the sharing economy, a fast and inexpensive peer-to-peer payment system is an essential element. The aim of this study is to outline a prototype that ensures the automation and decentralization of processes through smart contracts without blockchain technology. The model has been built based on the narrative that a community currency created through smart contracts can promote genuine practices of sharing as opposed to the profit-oriented approach that most of the currently operating sharing economy platforms have. Features of the model, such as ease of use, high-speed transactions without transaction cost are benefits that can provide a more efficient alternative to the traditional or to the cryptocurrency-based centralized sharing economy platforms.
Open Access: Yes
A családi otthonteremtési kedvezmény költségvetési terheinek előreszámítása, 2020–2040
Publication Name: Statisztikai Szemle
Publication Date: 2019-02-01
Volume: 97
Issue: 2
Page Range: 192-212
Description:
Decrease in the willingness of childbearing is an international phenomenon that afflicts Hungary just like any other country. Following the consolidation after the 2007/2008 crisis, new types of economic policy tools have been introduced in Hungary to improve birth rates. In consent with the arguments of former international research, the study assumes that although the factors affecting birth rates are wider than fiscal incentives, the government is able to have a considerable effect on achieving the required rate of reproduction via home settlement subsidies, and for this purpose, it has to ensure fiscal sustainability. The paper aims at providing an outlook for the period 2020–2040, in respect of the possible fiscal obligations of the family home settlement benefit that is an important pillar of the Hungarian family subsidising regime. Demographic data and the regulation for family home settlement benefit serve as the model computation framework. The calculations demonstrate that the family subsidising regime imposes sustainable commitments to the fiscal budget, and may change the birth rate trends favourably.
Open Access: Yes
Analyzing the impact of geographical diversification on portfolio performance
Publication Name: Teruleti Statisztika
Publication Date: 2025-01-01
Volume: 15
Issue: 2
Page Range: 321-340
Description:
The portfolio theory, which originated in the 1950s, pointed out that portfolio diversification allows investors to reduce risk. However, in addition to sector diversification, geographical diversification has been considerably less emphasized in equity investment evaluation. Our study contributes to this area. The calculations were conducted over two periods: 2008–2013 and 2014–2019. We constructed our portfolio using only exchange-traded funds (ETFs). We created two portfolios: one geographically diversified and the other focused exclusively on European markets. The geographically diversified portfolio comprised the IEV (iShares Europe ETF), EWH (iShares MSCI Hong Kong ETF), and EWZ (iShares MSCI Brazil ETF) portfolios. For our analysis, we used an approach based on the Monte Carlo simulation. The simulation calculated the Sharpe ratio of the portfolios, annualizing the metrics using the 252 trading day approach. We performed 10,000 iterations to ensure the robustness and reliability of our model. In the first period (2008–2013), we found that the geographically diversified portfolio showed higher volatility and generally lower risk-adjusted returns than the non-geographically diversified portfolio focused on Europe. Conversely, in the second period (2014–2019), the geographically diversified portfolio outperformed the non-geographically diversified portfolio in terms of risk-adjusted returns, suggesting that geographic diversification is preferable in certain market environments, particularly during periods of economic growth. In conclusion, investors should explore the potential of geographic diversification.
Open Access: Yes
DOI: 10.15196/RS150206
Navigating AI-Driven Financial Forecasting: A Systematic Review of Current Status and Critical Research Gaps
Publication Name: Forecasting
Publication Date: 2025-09-01
Volume: 7
Issue: 3
Page Range: Unknown
Description:
This systematic literature review explores the application of artificial intelligence (AI) and machine learning (ML) in financial market forecasting, with a focus on four asset classes: equities, cryptocurrencies, commodities, and foreign exchange markets. Guided by the PRISMA methodology, the study identifies the most widely used predictive models, particularly LSTM, GRU, XGBoost, and hybrid deep learning architectures, as well as key evaluation metrics, such as RMSE and MAPE. The findings confirm that AI-based approaches, especially neural networks, outperform traditional statistical methods in capturing non-linear and high-dimensional dynamics. However, the analysis also reveals several critical research gaps. Most notably, current models are rarely embedded into real or simulated trading strategies, limiting their practical applicability. Furthermore, the sensitivity of widely used metrics like MAPE to volatility remains underexplored, particularly in highly unstable environments such as crypto markets. Temporal robustness is also a concern, as many studies fail to validate their models across different market regimes. While data covering one to ten years is most common, few studies assess performance stability over time. By highlighting these limitations, this review not only synthesizes the current state of the art but also outlines essential directions for future research. Specifically, it calls for greater emphasis on model interpretability, strategy-level evaluation, and volatility-aware validation frameworks, thereby contributing to the advancement of AI’s real-world utility in financial forecasting.
Open Access: Yes
