Optimizing parameters in algorithm trading using map reduce on Indian stock exchange (Sensex)

In modern electronic stock exchanges there is an opportunity to analyze event driven market microstructure data. This data is highly informative and describes physical price formation which makes it possible to find complex patterns in price dynamics. It is very time consuming and hard to find this kind of patterns by handcrafted rules. However, modern machine learning models are able to solve such issues automatically by learning price behavior which is always changing. The present study presents profitable trading system based on a machine learning model and market microstructure data. Data for the research was collected from Moscow stock exchange MICEX and represents a limit order book change log and all market trades of a liquid security for a certain period. Logistic regression model was used and compared to neural network models with different configuration. According to the study results logistic regression model has almost the same prediction quality as neural network models have but also has a high speed of response which is very important for stock market trading. The developed trading system has medium frequency of deals submission that lets it to avoid expensive infrastructure which is usually needed in high-frequency trading systems. At the same time, the system uses the potential of high quality market microstructure data to the full extent. This paper describes the entire process of trading system development including feature engineering, models behavior comparison and creation of trading strategy with testing on historical data.

Abstract: Stock market forecasting remains a major concern to investors, financial institutions, and traders. Most classical forecasting techniques such as statistical modelling and technical analysis generally fail to account for the complexity and non-linearity of financial markets. Recently, neural networks, a new-age branch of machine learning, have emerged as a powerful weapon for better forecasting in the stock market. Neural networks, especially deep learning models such as Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM), are most suited to learning complex patterns from the historical data and reveal hidden correlations or relationships between different variables which have not been captured by the traditional models. The article discusses the role of neural networks in predicting stock market trends and the applications of these models in financial forecasting. The fundamentals of neural networks are explored, their special applications in stock market prediction, and the advantages they confer over traditional techniques. The objective of this article is to also provide insights into key obstacles, including data quality, overfitting, and interpretability, which can impinge upon the effective use of neural networks in finance. Case studies and simulated situations help present neural networks' use, where they are positioned to enhance stock market prediction output with accuracy and reliability. It seems that future directions that research in this field will take would involve integration with different alternative data sources, with quantum computing anticipated to change the landscape of financial prediction models. The insights provided... Keywords: Neural Networks, Stock Market Predictions, Machine Learning, Financial Forecasting, Trend Analysis, Deep Learning, Predictive Analytics, Data Sciences, and Algorithmic Trading.

At the end of 2019, the COVID-19 pandemic that originated from Wuhan - China has become a serious global problem. China implemented a policy of isolation, social distancing, and mass vaccination among the population, and simultaneously its stock market recorded a remarkable growth in 2020 and 2021. Using the time-series data in the period from January 22, 2020, to March 24, 2021, the method of non-linear autoregressive distributed lags (NARDL) model is used to assess the impact of the pandemic on the Shanghai stock market. The research results show that there has been no impact of the pandemic on the Shanghai stock market both in the short and long terms. As for the impact of cryptocurrencies, there is an impact of cryptocurrencies on the stock market in the short term, specifically, a decrease in the price of the bitcoin-related cryptocurrency has significantly increased the Shanghai stock market. Further, there has been no impact between bitcoin-related cryptocurrencies and the stock market in the long term.

PurposeIn any stock market, volatility is a significant factor in strengthening their asset pricing. The upsurge in volatility in the stock market can activate and bring changes in the financial risk. According to financial conventional theory, the stakeholders (investors) are selected to be balanced and variations in pertinent risk are also to be anticipated due to the outcome of the drive-in basic factors in Indian stock markets. The hypothesis shows that there are actions in systematic and unsystematic risks that are determined by volatility. It is allied to sentiment-driven in the trader movement.Design/methodology/approachThe paper used the methodology of generalized autoregressive conditional heteroskedasticity-in mean GARCH-M and exponential GARCH-M (E-GARCH-M) methods on the Indian stock market. The data have been covered from 2000 to 2019.FindingsFinally, the study suggests that due to the unfitness of the capital asset pricing model (CAPM), the selection has enhanced with sentiment is an important risk factor.Practical implicationsThe investor sentiment and stock return volatility statement are established by using the investor sentiment amalgamated stock market index built.Originality/valueThe outcome of the study shows that there is an important association between stakeholder (investor) sentiment and stock return, in case of volatility behavioural finance can significantly explain the behaviour of stock returns on the Indian Stock Exchange.

An Empirical Investigation of Co-Integration Between Sensex and the Selected World Stock Markets

The global stock market has experienced a profound transformation over the past few decades due to rapid advancements in Information Technology (IT). Traditional stock market systems, once dominated by manual trading floors, paper-based documentation, and delayed information dissemination, have been replaced by highly automated, technology-driven platforms. Information Technology now forms the backbone of modern stock market operations, enabling real-time trading, high-speed data processing, electronic clearing and settlement, and enhanced market surveillance. This research paper examines the role of Information Technology in shaping modern stock market practices, with particular emphasis on trading efficiency, transparency, investor participation, decision-making processes, and associated technological risks. The study adopts a descriptive and empirical research design to analyze how IT-enabled systems—such as electronic trading platforms, online brokerage services, mobile trading applications, algorithmic trading systems, and digital data analytics tools—have redefined stock market functioning. Primary data were collected through a structured questionnaire administered to 104 respondents, including individual investors, students, salaried employees, and businesspersons with exposure to stock market activities. The questionnaire was designed to assess awareness levels, usage patterns, perceived benefits, and perceived risks related to IT-based stock trading systems. Secondary data were sourced from academic journals, textbooks, stock exchange publications, and authoritative financial websites to establish a strong theoretical and conceptual foundation. The findings of the study indicate that awareness of Information Technology in the stock market is generally high among respondents; however, the depth of understanding varies considerably. Online trading platforms and mobile trading applications are perceived as the most important technological systems, highlighting the growing importance of accessibility and convenience in modern trading practices. A significant proportion of respondents acknowledge that IT has led to substantial improvements in trading speed and operational efficiency, allowing transactions to be executed within seconds. At the same time, a notable segment of investors perceives electronic trading systems as complex, indicating challenges related to digital literacy and platform usability. The study further reveals mixed perceptions regarding the role of real-time data and digital analytics in investment decision-making. While many respondents believe that technology-based tools support better and faster investment decisions, others associate continuous data flow with confusion, impulsive behavior, or increased risk. Awareness of algorithmic and automated trading exists at a basic level, but detailed understanding remains limited, suggesting a gap between technological advancement and investor knowledge. Cybersecurity threats, system failures, and technical errors emerge as the most significant risks associated with IT-driven stock market systems. The increasing dependence on digital infrastructure has heightened concerns regarding data security, system reliability, and market stability. Nevertheless, technological advancements have also strengthened regulatory oversight through automated surveillance systems, improved transparency, and faster settlement cycles. The study concludes that Information Technology has fundamentally reshaped modern stock market practices by enhancing efficiency, transparency, and inclusivity. However, the effective utilization of technology depends on continuous investor education, simplified system design, robust cyber security frameworks, and adaptive regulatory mechanisms. The paper contributes to existing literature by offering an integrated analysis of technological, behavioral, and operational dimensions of modern stock markets, particularly from the perspective of an emerging economy. It provides practical insights for policymakers, stock exchanges, brokerage firms, and investors seeking to balance technological innovation with market stability and investor protection.

Fluctuations in the oil market can significantly influence various sectors of the economy, such as the stock markets of countries that rely heavily on oil revenues. Oil prices are one of the key influential external factors affecting the stock exchange index of oil-dependent Iran. This paper investigates the spillover effects of oil prices on Iran’s stock exchange index weekly from March 2009 to March 2020. Using a time-series wavelet decomposition approach, a series of OPEC oil prices and Iran’s total stock market index were decomposed into various time scales (4 levels) to analyze oil market spillover into the stock market using the multivariate GARCH TBEKK model. The results confirmed that volatility spillover from the oil to the stock market occurred in all the time scales (short, medium, and long term). However, the spillover in the long term is more pronounced than over the short, demonstrating that stock market volatility is strongly influenced by long-term exogenous oil price fluctuations. Hence, oil market shocks are one of the influential factors affecting stock market turbulence in Iran.

The capital market represents a significant segment of the financial system because it directs free financial resources and has a substantial impact on the development of the company, the economy on the one hand, and on the other hand it affects attracting domestic and foreign investors. The capital market in the Federation of Bosnia and Herzegovina belongs to a group of developing markets, characterized by small market capitalization and liquidity on the one hand, while on the other hand, this market is characterized by relative openness, greater political instability and less connection with developed markets. The primary goal of this research is to determine the degree of relationship and openness of the capital market in the Federation of Bosnia and Herzegovina with the capital markets of the EU countries and developed countries. The results of the Pearson correlation test showed that the most substantial connection with the capital market in the Federation of B&H was recorded with the capital markets in Austria (stock exchange index: ATX5), Hungary SE (stock exchange index: Budapest SE), France (stock exchange index: CAC40), Italy (stock exchange index: FTSEMIB), Turkey (stock exchange index: BIST All share) and USA (stock exchange index: S&P 500). The weakest correlation was recorded with the capital markets of Slovenia, Croatia, and the United Kingdom. Also in this paper will be carried out the Granger causality test with the help of the software package SPSS 16.0. The primary goal of the Granger test is to determine which prices can affect the prices of the capital market in the Federation of B&H and whether the prices on the capital market in B&H can affect prices in other markets. The survey covers the period from January 5, 2015, to December 29, 2017. Data are collected on a daily basis from the stock market of the observed markets.

The emergence of financial technology (FinTech) has transformed the global stock market by introducing innovative tools, platforms, and processes that enhance efficiency, transparency, and accessibility.This study explores the impact of FinTech on stock market dynamics, focusing on areas such as algorithmic trading, robo-advisory services, blockchain technology, and artificial intelligence.The research highlights how FinTech innovations improve market efficiency, reduce transaction costs, and empower retail investors.However, the integration of technology also brings challenges, including regulatory complexities, cybersecurity threats, and potential market volatility.By examining existing literature and analyzing real-world data, this paper provides insights into the role of FinTech in reshaping stock market behavior and its implications for future market development. Behavioral Analysis:o Assessing behavioral changes in investors through sentiment analysis of surveys, particularly regarding trust in automated systems like robo-advisors and algorithmic trading. Tools and Techniques: Software for Quantitative Analysis: R, Python (

The paper attempts to establish the linkages and relationship among the returns of these developed stock exchanges and examines the effect of the stock index of one country on the stock index of other country. The daily index returns of all the five stock exchanges are taken from 2007 to 2016. Long-term relationship has been tested by Johansen co-integration test to show long run association among developed stock exchange indices. ADF, unit root test and Granger causality have been applied to find out the cause and effect relationship among the nifty index and leading stock exchanges indices. There is a unidirectional causality relationship with Japanese, UK and Hong Kong stock markets, Indian stock market influence the Japanese and Hong Kong markets but Indian stock market is influenced by both the USA and UK stock markets. However long run association was not found among nifty and rest of the stock indices.

The purpose of the current research is to conduct the empirical analysis and develop adequate econometric instruments for estimation of the relationship between monetary indicators and stock exchange indices in order to determine the effective instruments for stock exchange market development in the short and long runs. During the research the following methods have been used: general scientific methods of system analysis and synthesis; generalization, systematization and grouping of data; modern economic and mathematical instruments, in particular, methods of vector autoregression.Study results. The conducted statistical analysis and the realization of developed econometric VAR/ VECM models using the real data allowed us to estimate the potential capability of state regulators to influence the development of stock exchanges in different groups of countries as well as to develop the most effective monetary instruments of stock exchange stimulation while taking into account internal and external risks in the short and long runs.The results of this research paper can be used when making management decisions by state regulators on the ways of stimulation of stock exchanges development in different groups of countries, in particular Ukraine.Conclusions. Based on the conducted research using the system of developed VAR/VECM models, it was empirically proven that the central bank and other regulators can actually influence stock exchange indices using monetary instruments, but this influence is only significant on the markets of developed countries (e.g., the USA). However, in developing countries the stock exchange index does not depend on short-term changes of monetary indicators, which decreases the power of regulators to affect the stock exchange indices. At the same time, stock exchange indices are significant factors that influence monetary indicators not only in developed countries (the USA) but also in developing ones (Ukraine, Poland). Taking into consideration the results of the current research, it can be deduced that the economy of Ukraine is still in the transition phase and is characterized by significant political and economic risks, while the monetary policy of the regulator is rather an ineffective instrument to control and regulate the capital markets. In addition, the development of stock exchange markets has a positive impact on macroeconomic indicators of the developing economy. That is why the development of the effective and liquid stock market is a highly important element of Ukrainian state economic policy, which can become one of the main factors of its economic growth in mid- and long runs.Aricle received 16.04.2018

This research explores critical challenges facing the U.S. stock market, specifically focusing on the impacts of algorithmic trading-induced market volatility and cybersecurity threats. Algorithmic trading, which utilizes high-speed computer systems to make trades, has increased market efficiency but also introduced risks of extreme price fluctuations and flash crashes. In parallel, the digitalization of financial markets has heightened exposure to cybersecurity threats, posing risks to trading integrity and data security. To address these issues, this study proposes two targeted solutions. For the issue of market volatility driven by algorithmic trading, the research recommends implementing circuit breakers and trading halts. These mechanisms can prevent severe market disruptions by temporarily pausing trading during extreme price movements, allowing the market to stabilize and preventing panic-driven selloffs. For the cybersecurity challenges, the study suggests enhancing information sharing and fostering collaborative defense strategies among financial institutions and regulatory bodies. By encouraging greater collaboration, the financial sector can more effectively identify and counteract cybersecurity threats, reducing vulnerabilities across the market.

The aim of the article: The main aim of the article is to analyze the relationship between the stock market situation and the real economy, measured by the strength of the correlation between the rate of return on the stock market and the rate of GDP growth in European capital markets. The next objective is to answer the question whether the stock market index changes are ahead of, and if so, by how much, GDP changes. The author’s hypothesis stipulates that the stock exchange situation precedes the change in economic activity and serves as its forecast. Methodology: The empirical research work was carried out on the basis of quarterly data value of the stock index and the GDP between 2010 and the first quarter of 2021 for 20 European countries. For indices and GDP, the quarterly dynamics of the rate of return and GDP were calculated. Data on the value of the stock exchange index was taken from the website www.stooq.pl, while data on GDP was taken from Eurostat. Subsequently, the analysis concerned the correlation relationships between the variables on the basis of the Pearson correlation coefficient. The correlation between the variables was calculated without delay, as well as with a delay of one, two or three quarters of the returns on stock indices. Results of the research: Changes in the value of the stock exchange index is in most cases positively correlated with the change in GDP and the correlation is pronounced, but it is low and moderate. The only market for which a significant correlation was observed, was the Polish market. At the same time, it can be stated that the rates of return on the stock exchange index precede a change in GDP by one or three quarters. No changes were observed for the analyzed countries for two quarters.

Stock forecasting has long drawn people’s attention because the stock market is a crucial source of financing for publicly traded corporations and a sizable investment market. To fully use the evidence from dissimilar typical prices and recover the stock forecasting effect, a Blockchain-based secure stock value forecasting model TL-EMD-LSTM-MA (TELM) is projected. Other methods are selected for prediction according to the oscillation frequencies of the details, and the high-frequency components use the depth of the transfer learning method to train the stacked LSTM. Deep transferable learning-trained stacked LSTMs incorporate data from several equities and have a deeper understanding of the marketplace or commerce, which can significantly lower forecasting mistakes. Furthermore, it is possible to more accurately estimate the low-frequency components and the overall trend of the stock by employing the average movement approach. 500 stocks in the stock market are shown, as well as indices such as the Stock Exchange Index and Stock Exchange Component Index, the outcomes demonstrate that compared with other models, TELM has the least prediction error and the highest goodness of fit. Finally, simulate the stock trading process based on the stock closing price predicted by TELM, and the results show that TELM investment has low risk and high returns.

Trading Systems are beneficial for financial investments due to the complexity of nowadays markets. On one hand, finance markets are influenced by a great amount of factors of different sources such as government policies, natural disasters, international trade, political factors etc. On the other hand, traders, brokers or practitioners in general could be affected by human emotions, so their behaviour in the stock market becomes nonobjective. The high pressure induced by handling a large volume of money is the main reason of the so-called market psychology. Trading systems are able to avoid a great amount of these factors, allowing investors to abstract the complex flow of information and the emotions related to the investments. In this paper we compare two trading systems based on Evolutionary Computation. The first is a GA-based one and was already proposed and tested with data from 2006. The second one is a grammatical evolution approach which uses a new evaluation method. Experimental results show that the later outperforms the GA approach with a set of selected companies of the spanish market with 2012 data.