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.

Strategic Alliances, Innovation Capability, Cost Reduction, Customer Loyalty and Competitive Advantage in B2B Alliances

Disruptive business environment such as the Covid-19 pandemic and the recent high volatility in commodity prices has changed the way businesses were conducted. The heavy equipment industry is one of many industries affected by such an environment, especially those who are related to the mining industry where the volatility of the commodity prices has a significant impact on their business performance. Alliances are commonly formed by heavy equipment distributors and their customers to create a mutual benefit to sustain their performance. Strategic alliances have attracted substantial attention from industry as well as academia as a way to stay competitive. They mostly focus on the partner-to-partner alliances in serving their customers. Consumer behaviour has changed due to changes in the environment that make firms' strategic focus more on human-centric business approaches. This study looks at the roles of the partner-to-customer alliances, innovation capability, and cost reduction toward customer loyalty and competitive advantage. Data was collected from 335 respondents from the firms that have entered into alliances. This study finds strategic alliances have the highest association with cost reduction, followed by their association with innovation capability. They enhance customer loyalty through innovation capability. Cost reduction is not a lever to develop customer loyalty in the partner-to-customer relationship. The study also confirms that operational efficiencies are necessarily the source of competitive advantage, but strategic alliances are. © 2022, Academic Conferences and Publishing International Limited. All right reserved.

Structure, Stability, Persistence and Entropy of Stock Networks During Financial Crises

We investigate the network structures of stocks in SET100, NASDAQ100, and FTSE100 from 2006 to 2022, using the correlation distance and the time-space average of correlations as a threshold for connectivity of two stocks. Structure, stability, multifractality, and entropy of the networks are investigated to compare their behaviors before and after financial crises. The results show that during high volatility periods, such as the global financial crisis in 2008 and the COVID pandemic in 2020, the network characteristic path length decreases, while the clustering coefficient increases, suggesting that the network has shrunk in size, and stocks become tightly linked, similar to trends of price and return behaviors observed in many stocks during financial crises. Furthermore, the minimal level of network entropy implies that the market network stability decreases, and each sector has lost its ability to perform independently. We also find that the persistence of the network structure and the network entropy in SET increase during a period of high volatility as evident by a significant increase of the Holder exponent, while results from NASDAQ and FTSE do not exhibit such pronounced behavior, possibly due to having higher market fluctuation. Network features of SET and FTSE show recovery of same values after the 2008 crisis faster than NASDAQ, and in less than 100 trading days;however, they exhibit slower recovery, except for the network entropy, from the COVID-19 pandemic. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Frequency connectedness and cross-quantile dependence among medicare, medicine prices and health-tech equity

We investigate the dynamic connectedness among health-tech equity and medicine prices (producer and consumer) and Medicare cost indices for the US market. In doing so, we apply Cross-Quantilogram Dynamic Connectedness based on Time-Varying Parameter Vector Autoregression (TVP-VAR) approaches to analyse historical high-frequency time-series data. TVP-VAR results show that health-tech equity is the highest volatility transmitter while Medicare price is the highest volatility receiver. We also find medicine producer price is the net volatility contributor while the retail price of medicine is the net volatility receiver. The Cross-Quantilogram analysis confirms a strong bivariate quantile dependence between respective markets at a higher quantile of each market. Cross-quantilogram demonstrates a higher level of connectedness among the markets when considering medium and long memory. We observe health-tech equity turned to be a profound volatility contributor, while medicine price (both producer and retail prices) and Medicare appeared to net volatility receiver during the time of COVID19 Pandemic. The financial performance of health-tech equity returns elevates the price volatility of medicine and eventually Medicare cost, which imply that equity return should be incorporated forming medicine prices. © 2022 Elsevier Ltd

Forecasting the stock price of vaccine manufacturers in China Using Machine Learning and Econometrics Model

Due to the sudden outbreak of COVID-19, there is a high volatility in stock price of vaccine manufacturers in China (Between December 15, 2020 and December 13, 2021, average monthly volatility of these companies is 986). The aim of this paper is to compare the price prediction result of four algorithms: Multivariable Regression Model (MLR), Auto Regressive Integrated Moving Average Model (ARIMA), Back Propagation Neural Network Model (BP-NN), Random Forest Regression (RF), and decide which one has a better performance. Data from December 2020 to December 2021 is collected from Wind and the 8 stocks is selected in leading companies in vaccine industry. It turns out that BP-NN Model gives the best result in predicting stock price of vaccine manufacturers, measured using commonly used indicator, i.e., root-mean-square error (RMSE) and R Square (R2). So next time in the similar situation, BP-NN can be seen as a powerful tool to help us make decision. This paper would help investors build an optimal strategy in selecting stocks in terms of pharmaceutical industry. © 2022 SPIE.

Czech Stock Market Volatility before and during the Covid-19 Crisis

This paper deals with the analysis of the Czech stock market characterized by the Prague PX stock returns using the weekly data between January 1, 2017 and January 21, 2021 in order to investigate the impact of the Covid-19 pandemic. Two different approaches were applied, the asymmetric EGARCH model and the two-state Markov switching model. Both approaches confirmed the time-varying behaviour of stock returns and corresponding volatility during the analysed period reflecting the higher volatility not only during the Covid-19 period, but during the last quarter of 2018 attributable to the global economic slowdown, as well. Since the EGARCH model enabled to capture the volatility persistence and higher impact of negative shocks in comparison to positive shocks of the same magnitude, with the presented Markov switching model we were able to identify the probabilities with which each state occurred at each point in time. © Proceedings of the 14th International Conference on Strategic Management and its Support by Information Systems 2021, SMSIS 2021.