Machine Learning and Deep Learning based Stock Market Prediction considering Covid-19 as a Feature

India's capital markets are witnessing intense uncertainty due to global market failures. Since the outbreak of COVID-19, risk asset prices have plummeted sharply. Risk assets declined half or more compared to the losses in 2008 and 2009. The high volatility is likely to continue in the short term;as a result, the Indian markets have declined sharply. In this paper, we have used different algorithms such as Gated Recurrent Unit, Long Short-Term Memory, Support Vector Regressor, Decision Tree, Random Forest, Lasso Regression, Ridge Regression, Bayesian Ridge Regression, Gradient Boost, and Stochastic Gradient Descent Algorithm to predict financial markets based on historical data available along with economic and financial features during this pandemic. According to our findings, deep learning models can accurately estimate financial indexes by utilizing non-linear transaction data. We found that the Gated Recurrent Unit performs better than the existing model. © 2023 IEEE.

Performance of Conventional and Sustainable Index in Pre and During the COVID-19 Pandemic: A Comparative Analysis

Purpose: There has been a significant increase in the demand for ESG (environmental, social, and governance) investment by investors in recent years. Investors are recognizing that companies that prioritize ESG factors in their operations are more likely to be sustainable and resilient in the long term. The purpose of this study was to examine whether the ESG-responsible firms are performing better than the other firms in the pre-COVID and during the COVID periods. The paper also tried to investigate the impact of COVID-19 cases on the index movement. Methodology: The study employed the descriptive analysis on the financial data of NSE NIFTY 500 and NIFTY 100 Enhanced ESG index. The EGARCH model was applied to estimate the effect of COVID-19 on the volatility of the NIFTY 100 Enhanced ESG index. Findings: The results showed that there was no leverage effect in the ESG index in both periods. That means that the ESG Index can act as a cushion during the pandemic period. The ESG Index outperformed the conventional market index, thus acting as a COVID-19 safe asset class. This gives an opportunity to investors and fund managers to diversify their risk by acting sustainably responsible for society. Practical Implications: This study compared the performance of ESG-indexed firms with that of other firms in the pre-COVID and during COVID time period to check whether there was any difference between them. This study provided empirical evidence for practitioners, policymakers, and academicians in support of ESG investment as it showed that the ESG Index performed better than the conventional index during the COVID period. Originality: This study used secondary data to study the performance of the EGS firms in the pre and during COVID period in order to compare with the other firms. In the context of India, this study may be the first one to compare the performance of the ESG firms with the normal firms in the pre and during the COVID period. © 2023, Associated Management Consultants Pvt. Ltd.. All rights reserved.

How do the sectoral indices react to COVID-19? Evidence from an emerging economy

The study empirically examines the impact of the COVID-19 on different sectoral indices of the National Stock Exchange (India) using the event study method and a generalised autoregressive conditional heteroskedasticity (GARCH) model. We provide evidence of positive impacts on the auto, oil and gas, healthcare, and pharma sectors. While the bank, financial services, and private bank sectors are the most adversely impacted sectors, the PSU bank, media, and reality sectors are the least impacted, and the rest are moderately impacted sectors. The overall impact of COVID-19 was negative until the implementation of nationwide lockdowns and the announcement of stimulus packages. The GARCH results exhibit more substantial evidence for the negative impact of the pandemic on the FMCG, IT, metal, oil and gas, and PSU bank sectors. We also find a more favourable impact on FMCG, pharma, and healthcare sectors in India.

A study on the impact of COVID-19 on the financial health of Indian companies

Unexpected lockdown of the country for more than four months has led to a huge reduction of economic activity and adversely affected the profitability and liquidity of companies. The studyaims to assess the potential damage caused by COVID-19 to the financial health of Indian companies. NSE NIFTY 50 companies were selected as a sample for the study and Altman Z-Score model was used to measure their financial health at the end of December 2019, March 2020 and June 2020. Paired sample t-test was used to test significant changes in financial healthduring the period of study. The study witnessed adverse impact of COVID-19 on the financial health of selected companies. Oil, Gas, Metals, Power, Construction, Fertilisers, Pesticides, Services and Telecom are the sectors which are adversely affected by the pandemic. Copyright © 2022 Inderscience Enterprises Ltd.

Impact of COVID-19 Pandemic on Indian Stock Market Sectors

The start of the COVID-19 pandemic and official lockdown announcements had created uncertainty in global business operations. For the first time, the Indian stock market has significantly impacted. India is one of the most important rising economies in the world and has seen the value of its crucial stock indices plummet by about 40%. There are several studies on the impact of the pandemic on the stock market, but very few studies have focused on a comparative analysis of the first and second COVID-19 pandemic waves. The Fama French model of an event study is used to analyze the response of various sectoral indices during the pandemic. Although all industries were briefly damaged, the financial industry was the hardest hit. Industries such as pharmaceuticals, consumer products, and information technology had favorable or minor effects in both waves. The second wave had an insignificant impact compared to the first one, clearly indicating optimism and normality in the market despite the looming pandemic threat. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Stock Market Prediction during COVID Using Stacked LSTM

In the field of computation, the art of predicting the stock market has always been a tough nut to crack for researchers. This is because stock prices are highly influential values. The prices depend on many factors, ranging from physical to physiological, rational and irrational, from geopolitical stability to the sentiments of the investors - all play a crucial role. Investors anticipate market conditions in the future for a successful investment. Hence considering the past stock prices as an embodiment of the factors mentioned above, we propose a stacked long-short-term-memory (LSTM) model to predict the closing index of stock prices during this highly uncertain pandemic period using root mean square error (RSME) as the performance indicator. The model is optimized to improve the prediction accuracy in order to achieve high performance stock forecasting. The dataset considered is from NIFTY 50 scaling across four sectors, namely - auto, bank, healthcare and metal from a duration of 30th January 2020 to 31st March 2022. This paper aims to consider the historical data to analyze future patterns and insights. © 2022 IEEE.

The Impact of Covid-19 on Index Returns of the Country: International Testament

This study analyse the impact of Covid-19 on Index returns of the Country. For this study four countries are taken including two developed countries i.e. USA and Germany, two developing countries i.e. India, China for the time period between 1st March - 30th October 2020. This time period reflects the first wave of covid-19 pandemic and how economy affected due to corona outbreaks on different countries. It also examines the impact of confirmed cases and recovers case on index return with the help of regression analysis. In routine data of confirmed cases and recovered case study analyse their impact on index returns and it was found that both the variables are having their impact on index returns of the particular Country. Overall, our study recommends that stock market is the most sensible market and due to that index returns of the particular country also affected highly in response to covid-19 infection. It may differ depending upon the time due to covid-19 outbreaks. Copyright © 2022 Wolters Kluwer Medknow Publications. All rights reserved.

Causal Relationships of the Stock Market with other Asset Classes: An Indian Perspective

The recent decade has seen a rapid rise in risk assets. Stocks, commodities, and cryptocurrencies have exploded to the upside. Global central banks have maintained interest rates at record low levels following the COVID-19 crisis. This has further acted as tailwinds for risky assets. With asset classes being increasingly interlinked with each other, useful information can be gained by studying these inter-relationships. This paper looks at the interrelationships between the Indian stock market Nifty index and some key asset classes such as Gold, Crude oil, short-term and long-term Indian government bond yields, the USD/INR exchange rate, and the cryptocurrency Bitcoin for the period January 2011 to December 2020. Co-integration analysis suggests the absence of long-run relationships between the Nifty and the asset classes studied. Granger causality analysis reveals bi-directional causality between Nifty and USD/INR and Crude oil returns. Gold returns, Bitcoin returns, and changes in short and long-term government bond yields uni-directionally granger-caused Nifty returns. Impulse response analysis reveals that shocks in each of the independent variables caused a shock in the Nifty that persisted for 1 to 3 weeks. Traders in the Nifty can monitor these shocks and accordingly fine-tune their strategies for possible moves in the Nifty. © 2022 ACM.

Impact of COVID-19 on the NSE Nifty and the gross domestic product: Evidence from India

The purpose of this research is to look into the relationship between the NSF. Nifty and the Gross Domestic Product. During the Covid-19 epidemic, changes in the relationship between the NSF. Nifty and the GDP are investigated. For the years 2000-2001 to 2020-2021 and Q4:2018-19 to Q1:2021-22 of Gross Domestic Product (GDP) and NSF. Nifty, both annual and quarterly data are used. Unit root tests, Johansen cointegration tests, the Vector error correction model (VECM), the Wald test, the Granger Causality test, and the Karl-Pearson coefficient of correlation were all utilized. The Johansen cointegration test indicates that the NSE Nifty and GDP have a long-run relationship. Similarly, the results of the vector error correction model demonstrate that the NSE Nifty Index has a positive impact on GDP. According to the results of the Granger causality test, the NSF. Nifty is the most important indicator of GDP during the Covid-19 period. From the time of the Pre-Covid-19 pandemic until the time of the Covid-period, the strength of the link has grown stronger.

Impact of COVID-19 on the Performance of Indian Stock Market: An Empirical Analysis

The outbreak of COVID-19 epidemic had not only brought destruction to the human lives but also destabilized the financial markets across the world. Although there were some studies conducted on the impact of COVID-19 on the financial markets in the developed economies, very few studies were conducted on the developing economies like India. Hence, this study intends to measure the impact of COVID-19 on the Indian stock market, especially on NIFTY50, and all the major sectorial indices of National Stock Exchange (NSE). The study also makes an attempt to analyze the impact of COVID-19 on the Indian stock market in various time periods (lockdown, pre-lockdown, and full sample time periods). For this purpose, the researchers have used EGARCH and regression models to measure the sectoral impact of COVID-19 on NIFTY. The study finds asymmetrical reactions on positive and negative shocks in the Indian stock market.The β2 coefficient, which explains asymmetric volatility, is significant and positive for FMCG, realty, oil and gas, and consumer durables, suggesting the presence of asymmetric effect, but has no leverage effect. It implies that positive news has greater effects on volatility than negative news. In other words, investors are more prone to positive shocks than negative shocks with the same magnitude. While β2 is found to be significant and negative for NIFTY, bank, information technology, and financial services, which clearly depicts the presence of leverage effect. It suggests the presence of asymmetrical reactions on unfavorable shocks in these indices.

COVID-19 AND INDIAN ECONOMY: IMPACT ON MICRO, SMALL AND MEDIUM ENTERPRISES (MSME) SECTOR

The role of MSMEs as a power source of economic growth of the country is highly acknowledged. It plays a notable role in ensuring equitable development in the country. However, most of the small and medium industries which were considered as the backbone of Indian economy are striving hard to keep their business functioning in this lackluster time of crisis. The outbreak of COVID-19 and the subsequent country-wide lockdown made the MSME sector as the worst affected sector. The pandemic-triggered uncertainty around the future flow of income and the declining purchasing power among consumers have endangered the survival of MSMEs. The article mainly focuses on exploring the ramifications of country-wide lockdown due to global pandemic upon the small and medium scale industries of the country. Also, the study tries to connect the listed stock price trends of MSMEs during covid outbreak for analysing the performance of the sector for the period. The analysis shows that the worst economic sentiments are reflected in the price movements of listed small and medium enterprises. It also explores how the stimulus packages declared by central government can revive the sector. The study comes up with a couple of suggestions, such as digitalization, to safeguard and galvanize the sector during this challenging time. © 2022 by Nova Science Publishers, Inc.

Effect of COVID-19 Pandemic on NSE Nifty Energy Index

The research intends to assess the efficiency of NSE Energy Index-listed firms throughout the COVID-19 before and post pandemic phases, which run from 2019 to 2021. The primary goal of this article was to examine the price movement of corporations in the petroleum, gas, and electricity sectors by employing statistical methods such as descriptive statistics, ADF, and the GARCH (1,1) model, during the period of study. When comparing the post-COVID-19 pandemic era to the pre-COVID-19 pandemic period, certain firms experienced excessive volatility. The energy market’s investor sentiment was significantly higher on the tail events, suggesting that anxious investors raced to put options and paid an exorbitant premium to shield them against unprecedented danger in the energy market. © 2022, Econjournals. All rights reserved.

Modelling Market Indices, Commodity Market Prices and Stock Prices of Energy Sector using VAR with Variance Decomposition Model

The study aims to examine the existence of a correlation between the stock prices of the energy sector, commodities prices of the energy sector, and market indices. The study uses an empirical approach to develop various VAR (Vector Autoregression) with Variance Decomposition Models for each company under the energy sector indexed in NIFTY50 by considering daily prices for 3 years. For a comparative study, the data have been divided into two parts. The first part is considered pre-COVID era, i.e., from July 1, 2018, to December 31, 2019, and the second part is considered post-COVID era, i.e., from January 1, 2020, to June 30, 2021. While observing the estimates of VAR of different companies, it can be said that crude oil is significant in most of the models during pre-COVID whereas, during post COVID, lag term of crude oil and NIFTYENGERGY are significant. On the other hand, while observing the estimates of variance decomposition in all the VAR models, the first lag term of the particular company’s share price is strongly endogenous. In comparison, the other independent variable, i.e., lag term of the price of crude oil and natural gas, values of NIFTY50 and NIFTY ENERGY are strongly exogenous to the stock prices of the energy sector. © 2022, Econjournals. All rights reserved.

A Regression Based Approach to Predict the Indian Stock Market Trend Amid COVID-19

Corona Virus Disease (COVID-19) has triggered a global disaster by affecting over 200 countries in a short period of time. It has had a significant impact on both social and economic activities all over the world. Panic selling has been prompted by investors' herd behaviour. As a result, stock markets worldwide have plummeted. The market data is nonlinear and chaotic. Predicting the behaviour of the market in current circumstances is a challenging task.. In this work, improved quality of input data and enhanced feature engineering mechanism is adapted to predict the stock market trend amid COVID-19. Here both classical, as well as ensemble regression models are used to investigate the impact of predictors. The models are evaluated using R- squared metric. The findings of this study highlight that the opening price of the market and total positive cases in India significantly impact the closing price of the Nifty50 index. Furthermore, the linear regression model performed better than other models and achieved an R-squared value of 0.999 for both training and test sets. © 2021 IEEE.

Relationship Between Stock Volatility and Macro-Economic Variables During COVID 19 and Its Impact on Indian Economy

Stock prices/indices have always played a very crucial role in any economy and in recent times it has also become an important parameter in defining the financial matrix of any country along with conventional measures such as interest rates, exchange rates, GDP growth rates etc. The effects of the COVID-19 pandemic on economies are an ongoing study which includes through various simulations and forecasts. The financial markets have obviously been impacted and its manifestation can be seen in data trends since the first lockdown from March 2020 to June 2021. The uncertainty created by the pandemic has caused fluctuations in macroeconomic variables and has increased volatility in the developed as well as emerging stock markets. In India some of these factors are even mutually dependent and the interaction among them is worth studying. Hence, this paper is an attempt to study the relationship between macroeconomic variables viz. GDP growth rate, exchange rate, etc. and volatility in stock exchange during the first lockdown period (24 May to 31 June 2020) in India. NIFTY 50 has been selected as the stock exchange under this study and the monthly data of all the variables as on 1 May to 31 June 2020 were collected from secondary sources. These data were analysed using linear regression analyses and it was found that there is a strong and significant relationship between the macro-economic variables and volatility of stocks of NIFTY 50 stock exchange even during the pandemic. The impact of stock volatility on Indian economy due to the pandemic was studied on other macro-economic variables based on data collected during the pandemic.

Nifty Price Prediction from Nifty SGX using Machine Learning, Neural Networks and Sentiment Analysis

This paper investigates various Machine learning techniques such as Linear Regression, Decision Tree Regressor, Random Forest Regressor, and a neural network Multilayer Perceptron (MLP Regressor) to predict the opening price of the Nifty 50 index (on Indian National Stock Exchange (NSE)) based on the previous day's closing price of the Singapore Exchange (SGX) Nifty index (which is traded on the Singapore Stock Exchange). The models use various parameters such as closing price of SGX Nifty, India volatility index (India VIX) and exchange value (of Singapore Dollar (SGD) to Indian Rupee (INR)) along with sentiment analysis based off thousands of tweets that included the hashtag "#Nifty50". The accuracy and errors for each model are calculated and compared. The impact of COVID-19 on the accuracy of model prediction is also analyzed. It is observed that the artificial neural network and linear regression offer the highest accuracy of 0.999, and the random forest regressor offers the lowest accuracy. COVID-19's effect on the market is seen to impact the accuracy of model prediction, and the accuracy of prediction during the second wave is the lowest due to high market volatility averaged over a short period of time. © 2021 IEEE.

Multivariate economic analysis of the government policies and COVID-19 on financial sector

The sudden pandemic outbreak of COVID-19 has led to disruption in trade, travel and commerce by halting manufacturing, industries, and all other sundry activities. Global markets plummeted, leading to erosion of around US $6 trillion within just one week during February 2020. During the same week, the S&P 500 index alone experienced a loss of more than US $5 trillion in the USA, while other top 10 companies in the S&P 500 suffered a loss of more than US $1.4 trillion. This manuscript performs multivariate analysis of the financial markets during the COVID-19 period and thus correlates its impact on the worldwide economy. An empirical evaluation of the effect of containment policies on financial activity, stock market indices, purchasing manager index and commodity prices are also carried out. The obtained results reveal that the number of lockdown days, fiscal stimulus and overseas travel bans significantly influences the level of economic activity.