•Reservoir computing models are proposed to predict seven stock market indices.•Random, small-world, and scale-free network topologies are studied.•Proposed models achieve competitive results ...compared to other deep learning models.
Prediction of the financial market price is critical for financial decision-making and market policy-making. Recently, various machine learning and deep learning methods have been adopted to predict financial markets’ movements using historical time series of prices. However, accurate prediction of financial prices is still a long-standing challenge that always calls for new approaches. In this study, a novel machine learning model of reservoir computing is developed to predict stock market indices. The performance of the proposed new model is systematically evaluated using the time series of daily closing prices of seven major international stock market indices including S&P500 Index, New York Stock Exchange Composite, Dow Jones Industrial Average, Nasdaq Composite Index, Financial Times Stock Exchange 100 Index, Nikkei 225 Index, and Shanghai Stock Exchange Index between January 4, 2010, and December 31, 2018 covering 2,272 trading days. The results show that our model outperforms the widely used deep learning methods of long short-term memory and recurrent neural network in most cases. To further evaluate the predictive capability of our model, we compare our model to the other two newly reported deep learning methods in recent studies. Comparative results also show that our model is competitive to those deep learning methods in predicting stock market indices. Our study contributes to the literature by developing novel reservoir computing models for financial market predictions. Meanwhile, our results also provide practical implications for financial practitioners of potential financial applications of reservoir computing in financial time series analysis and predictions.
The sovereign green bond market has been growing rapidly worldwide since its debut in 2016. The study investigates the empirical response of the stock and credit default swap (CDS) market to green ...bond issuance by 10 EU countries during the period 2016–2021. We document that the issuance of a green bond is regarded by the investors as reflecting as value‐enhancing and risk‐reducing behavior by EU countries. The issuance of sovereign green bond provides a strong signal of the country's involvement to a low‐carbon economy by increasing the social and reputational benefits. This effect is even more evident during the pandemic crisis. The reaction of stock and CDS market is driven by several factors such as bond and country characteristics. Overall, our findings suggest that the sovereign issuance of green bonds acts as mitigation mechanism for country risk.
The coronavirus pandemic, erupted in 2019, re-emphasized the importance of dealing with risk and uncertainty. In addition to difficulties caused in public and health sectors, the negative ...consequences of COVID-19 outbreak are more and more obvious also in economy. The rapidly spread of virus from China to Europe and U.S., seriously tests the countries’ ability to deal with such an unexpected situations, both health-wise and economically. As the same time, measures adopted by governments like travel restrictions have further amplify the difficulties in some aspects. In response to growing uncertainty, individuals have suddenly changed their consumer behaviour, manifested in excessive food purchases which caused certain food products shortage. Companies have restrained production and spending. Some categories of services are particularly affected, restaurants and hotel units temporarily fully suspended their activities. There are also serious transport restrictions, airlines cancelled several flights. The news of the outbreak of the novel coronavirus, the rapid spread worldwide, and the measures taken by governments, the panic reactions of individuals and companies, negatively impact the economic and financial stability. The negative effects caused by the coronavirus affect relatively quickly the financial markets, which show terrible volatilities. On March 18, 2020, the stock market prices declined more than 30% compared to the peak price value of recent years, which can be considered significant. Since the outbreak of the coronavirus pandemic, several articles deals with the impact of virus-induced uncertainty on volatility. The results related studies highlights the correlation between COVID-19 cases, deaths and different stock indices price volatility. Based on these, the aim of this article is to examine the relationship between the main stock indices, namely BUX and BET of two neighbouring countries in Central and Eastern Europe (Romania and Hungary) and the COVID-19 cases in European Union. In order to investigate this relationship we used simple linear regression. The results show that in both countries’ stock indices case there is medium-strong correlation between BUX (R=0,6651), BET (R=0,6001) and COVID-19 European Union’s cases. By investigation of stock indices changes in the analysed period we can conclude that the time of reaction of stock markets and the intensity of stock prices changes is quite different in case of BUX (36,27%) and BET (31,12%).
This paper aims to examine the influence of the Ukraine invasion by Russia on Turkish markets, namely the Istanbul stock market index, Turkish real estate market index, Turkish gold market and ...Turkish foreign exchange market. This study used daily frequency data between February 24 and June 14, 2022. The variables used are BIST100, Turkey real estate index (XGMYO), Turkish gold commodity (XAU/TRY), Turkish foreign currency such as EURO/TRY, GBP/TRY, USD/TRY, TRY/UAH, TRY/RUB, and macro-economic variable RFR/TRY. The study employed Johansen cointegration, Impulse Response Functions and Markov-regime switching for the analysis. The findings established a long-run co-integration relationship among the Turkish markets. The finding also indicated that the shock from the Ukraine invasion by Russia has a positive effect on developed foreign currencies and a negative effect on currencies from emerging countries such as Turkey. The finding revealed that BIST100, XGMYO, and XAU/TRY shifted to regime 2 during the Ukraine invasion by Russia. The lack of need for more commodities such as wheat, gas and oil from the Turkish market prevented focusing on them, which may attract global attention. Despite this, the significance of this finding remains relevant in Turkey. Therefore, future research may focus on other markets with sufficient trading data for wheat and gas in Russia or Ukraine and any other countries of their study. This study established that Ukraine's invasion by Russia has a worldwide impact on the global markets. The effect is felt globally as a consequence, has been experienced across different developed and emerging markets due to the large market share of Russia on essential commodities such as gas and oil. Turkish foreign exchange markets experienced more storms during the Ukraine invasion by Russia even more than it was during the COVID-19 pandemic.
•Russia-Ukraine invasion impacts positive and negative effects on developed and emerging currencies.•Russia-Ukraine invasion has a worldwide impact on the global markets.•Russia-Ukraine invasion on Turkish exchange markets severe than the COVID-19 pandemic.
Stock market forecasting has long been a focus of financial time series prediction. In this paper, we investigate and forecast the price fluctuation by an improved Legendre neural network. In the ...predictive modeling, we assume that the investors decide their investing positions by analyzing the historical data on the stock market, so that the historical data can affect the volatility of the current stock market, and a random time strength function is introduced in the forecasting model to give a weight for each historical data. The impact strength of the historical data on the market is developed by a random process, where a tendency function and a random Brownian volatility function are applied to describe the behavior of the time strength, here Brownian motion makes the model have the effect of random movement while maintaining the original fluctuation. Further, the empirical research is made in testing the predictive effect of SAI, SBI, DJI and IXIC in the established model, and the corresponding statistical comparisons of the above market indexes are also exhibited.
Modern data analysis tools have to work on high-dimensional data, whose components are not independently distributed. High-dimensional spaces show surprising, counter-intuitive geometrical properties ...that have a large influence on the performances of data analysis tools. Among these properties, the concentration of the norm phenomenon results in the fact that Euclidean norms and Gaussian kernels, both commonly used in models, become inappropriate in high-dimensional spaces. This papers presents alternative distance measures and kernels, together with geometrical methods to decrease the dimension of the space. The methodology is applied to a typical time series prediction example.
Celem artykułu jest sprawdzenie, czy siła powiązań handlowych z Rosją i Ukrainą istotnie różnicuje reakcję giełd papierów wartościowych na militarną agresję Rosji na Ukrainę 24 lutego 2022 r. Zakres ...podmiotowy badania stanowią wszystkie kraje G20 oraz Unii Europejskiej. W badaniu skoncentrowano się na jednodniowej zmianie indeksu giełdowego w pierwszym dniu inwazji oraz zmianie indeksu giełdowego w okresie od 23 lutego do 7 marca 2022 r. Data 7 marca 2022 r. odnosi się do najwyższego poziomu niepewności giełdowej w następstwie wybuchu analizowanego konfliktu zbrojnego. Na podstawie analizy skupień metodą k-średnich wyodrębniono trzy klastry reprezentujące kraje o podobnym udziale w handlu z Rosją i Ukrainą. Następnie, wykorzystując test Kruskala-Wallisa oraz test rang Wilcoxona, zweryfikowano, czy istnieją istotne różnice w reakcjach giełd między wyodrębnionymi grupami krajów. Zaobserwowano, że poziom powiązań handlowych kraju ze stronami konfliktu istotnie różnicuje reakcje indeksów giełdowych. Największe spadki wartości notują wiodące indeksy giełdowe z krajów najbardziej powiązanych gospodarczo z Rosją i Ukrainą. Wyniki badań wskazują na to, że poziom relacji gospodarczych między krajami może mieć istotny wpływ na reakcję indeksów giełdowych na wybuch międzynarodowych konfliktów zbrojnych, w szczególności w okresie globalizacji rynków finansowych.
This paper assesses whether the strength of trade ties with Russia and Ukraine differen tiates the reaction of stock markets to the outbreak of the Russian invasion of Ukraine on 24 February 2022. Both the G20 and the EU are studied. The focus is on the stock market index change on the first day of the invasion, and the stock market index change between 23 February and 7 March 2022, where 7 March refers to the highest level of stock market uncertainty following the outbreak of the conflict. We distinguish clusters representing countries with a similar share of trade with Russia and Ukraine and then, based on cluster data and the Kruskal-Wallis and Wilcoxon rank-sum pairwise comparison tests, assess whether there are significant differences in stock market reactions between selected groups of countries. We reveal that the level of a country’s trade links with the belligerents of the conflict significantly impacts changes in its stock market indices. In dices from those countries whose ties to Russia and Ukraine are strongest have decrea sed the most. This study therefore implies that the scale of economic relations between countries might play an important role in the magnitude of the stock market reaction to the outbreak of an international military conflict, particularly these days when financial markets are globally integrated.
The year 2020, so far, has been relentlessly wreaking havoc on the very concept of life and work as we know them. This unprecedented event has been unfolding multiple worst-case scenarios on all ...fronts of our society and has eclipsed almost every other natural disasters of the modern world and pushing humanity on the verge of tipping point. Up to now, more than 29 million people have been infected and more than 1000 thousand have lost their lives because of COVID-19. So far, this epidemic has not only taken human lives but also snatched the livelihood of millions of people worldwide. Because of this epidemic, the world has been experiencing a kind of regressive mindset, where countries are looking inward, and all kinds of political, social, and economic relations are in a very confused state on account of this ongoing assault on them. Consequently, this epidemic has triggered a high level of skepticism in investors about the certainty of the rapid healing of the social and economic condition which is hindering the quick and healthy recovery of financial markets in most of the pandemic ridden countries of the world. The purpose of this study was to examine the causal relationship among various factors such as crude oils price, exchange rate, and stock market performance during Covid-19 in the context of financial market performance in India. Several methodologies have been applied during this study such Johansen co-integration test, vector autoregression model, and Granger causality test. The results have supported a significant causality among crude oil prices and the exchange rate on stock market performance.
In econophysics, the analysis of the return distribution of a financial asset using statistical physics methods is a long-standing and important issue. This paper systematically conducts an analysis ...of composite index 1 min datasets over a 17-year period (2005−2021) for both the Shanghai and Shenzhen stock exchanges. To reveal the differences between Chinese and mature stock markets, we precisely measure the property of the return distribution of the composite index over the time scale Δt, which ranges from 1 min to almost 4000 min. The main findings are as follows: (1) The return distribution presents a leptokurtic, fat-tailed, and almost symmetrical shape that is similar to that of mature markets. (2) The central part of the return distribution is described by the symmetrical Lévy α-stable process, with a stability parameter comparable with a value of about 1.4, which was extracted for the U.S. stock market. (3) The return distribution can be described well by Student’s t-distribution within a wider return range than the Lévy α-stable distribution. (4) Distinctively, the stability parameter shows a potential change when Δt increases, and thus a crossover region at 15 <Δt< 60 min is observed. This is different from the finding in the U.S. stock market that a single value of about 1.4 holds over 1 ≤Δt≤ 1000 min. (5) The tail distribution of returns at small Δt decays as an asymptotic power law with an exponent of about 3, which is a widely observed value in mature markets. However, it decays exponentially when Δt≥ 240 min, which is not observed in mature markets. (6) Return distributions gradually converge to a normal distribution as Δt increases. This observation is different from the finding of a critical Δt= 4 days in the U.S. stock market.