Industrial Stock Prices Research Articles

Predicting Economic Trends and Stock Market Prices with Deep Learning and Advanced Machine Learning Techniques

The volatile and non-linear nature of stock market data, particularly in the post-pandemic era, poses significant challenges for accurate financial forecasting. To address these challenges, this research develops advanced deep learning and machine learning algorithms to predict financial trends, quantify risks, and forecast stock prices, focusing on the technology sector. Our study seeks to answer the following question: “Which deep learning and supervised machine learning algorithms are the most accurate and efficient in predicting economic trends and stock market prices, and under what conditions do they perform best?” We focus on two advanced recurrent neural network (RNN) models, long short-term memory (LSTM) and Gated Recurrent Unit (GRU), to evaluate their efficiency in predicting technology industry stock prices. Additionally, we integrate statistical methods such as autoregressive integrated moving average (ARIMA) and Facebook Prophet and machine learning algorithms like Extreme Gradient Boosting (XGBoost) to enhance the robustness of our predictions. Unlike classical statistical algorithms, LSTM and GRU models can identify and retain important data sequences, enabling more accurate predictions. Our experimental results show that the GRU model outperforms the LSTM model in terms of prediction accuracy and training time across multiple metrics such as RMSE and MAE. This study offers crucial insights into the predictive capabilities of deep learning models and advanced machine learning techniques for financial forecasting, highlighting the potential of GRU and XGBoost for more accurate and efficient stock price prediction in the technology sector.

Monitoring of high-dimensional and high-frequency data streams: A nonparametric approach

ABSTRACT High-dimensional and high-frequency data streams (HHDS) have become widely available with the prevalence of data-acquisition technologies. Because HHDS have the characteristics of high dimensionality and temporal correlation, traditional statistical process control (SPC) techniques cannot be used directly to address the problem of monitoring HHDS. Most extant monitoring methods commonly assume that the process observations are independent or can be described by some parametric models and face the challenge posed by high-dimensional data. Little research has been conducted on the robust monitoring of HHDS that can simultaneously accommodate high dimensions and high frequencies. Therefore, in this paper, we propose a novel nonparametric approach for monitoring HHDS, based on data decorrelation, dimension reduction, and SPC. Specifically, process observations are first sequentially decorrelated and standardized using Cholesky decomposition, and then the k -nearest neighbors classification algorithm is applied to transform uncorrelated high-dimensional data into one-dimensional data. Finally, the traditional cumulative-sum procedure is used for online monitoring, based on an empirical log-likelihood ratio test. Numerical studies have shown that our monitoring scheme is sufficiently reliable and efficient for the online monitoring of HHDS. An illustrative example about the Dow Jones 30 industrial stock prices is presented to further validate the proposed approach.

Changes in Banking Industry Stock Prices: The Role of Risk, Good Governance, Earnings, and Capital

This research, with direct implications for banking professionals and investors, aims to empirically test and analyze the RGEC components, which consist of risk profile, good corporate governance, earnings and capital, and their influence on banking stock prices listed on the Indonesian Stock Exchange (BEI). The sample for this research was determined using a purposive sampling technique, resulting in a total sample of 21 companies over 3 periods, namely 2016-2018. The data analysis technique used is Partial Least Square (PLS). The research results, which have immediate relevance for investment strategies, show that earnings proxied using ROA positively affect stock prices, while risk profile, good corporate governance, and capital do not. This indicates that earnings are still a strong signal for investor investment decisions. Therefore, the company must succeed in maintaining and increasing its earnings to become an investment choice for investors. However, even though good corporate governance and capital do not influence stock prices, it doesn’t mean that banking companies should ignore their governance and capital. These two factors are essential in maintaining good performance.

An Empirical Analysis on the China’s Medical Industry under Covid-19 Based on Fama-French model

The global financial markets have been seriously affected by the Covid-19 pandemic, causing widespread and deep-reaching effects since the latter part of 2019. The medical industry, being one of the fundamental sectors, has not been spared from its effects. This empirical study focuses on Chinese A-share medical industry companies as a sample and the Fama-French three-factor and five-factor models were evaluated to determine their effectiveness pre- and post-pandemic, aiming to investigate how the epidemic has impacted the stock prices of China’s medical industry. The results indicate that the epidemic has significantly affected the Chinese A-share medical industry, and the Fama-French model’s capability of explaining market returns has diminished following the outbreak of the epidemic. These findings provide guidance for investors and policymakers to make informed decisions regarding investments and policies related to the medical industry, as well as insights into examining the effectiveness of China’s medical industry stock price. These results also provide ideas and methods for related research in other fields.

Clustering and Financial Performance Analysis of Indonesian Coal Mining Industry Stock Prices

In the comprehensive study of the Indonesian coal mining industry, a rigorous exploration and clustering approach was applied to historical stock price data and financial metrics from coal companies listed for over a decade. Data sourced from Yahoo Finance underwent an automated download process, ensuring consistency and efficiency. The research utilized robust clustering techniques, including K-means, Hierarchical, and Correlation Clustering, to discern the stock price movements during the dynamic market conditions of 2022 and 2023. Financial performance analysis, focusing on key metrics such as ROA, NPM, and EPS, highlighted the unique financial dynamics of companies like PTIS, IATA, and AIMS. The study's results provide a multifaceted understanding of the coal industry's financial trends, emphasizing varied company responses to market conditions and revealing significant financial performance divergences among key players. This research not only offers invaluable insights into the coal industry's financial landscape but also presents an innovative methodology poised to transform financial analytics in the sector.

Impact of International Oil Prices on Chinese Renewable Energy, Agriculture, and Industrial Stock Prices

Impact of International Oil Prices on Chinese Renewable Energy, Agriculture, and Industrial Stock Prices

Technology Industry Stock Price Prediction Based on OLS, Random Forest, and Extreme Gradient Boosting

Contemporarily, the marriage of artificial computer intelligence and the financial stock market has gained increasing interest in recent years. In recent years, forecasting stock prices has also been a more prevalent topic of conversation. Investors lack a coherent knowledge of the model mechanism and prediction results behind stock price forecasts. Hence, this paper will examine Apple, Microsoft, and Amazon, the three largest technology businesses. The three models OLS, Random Forest, and XGBoost were used to predict and evaluate historical data from the past five years. The OLS model has a superior performance structure when dealing with data sets with low data frequency, and its anticipated outcomes are also more accurate, according to the research. In addition, different machine learning models are employed for diverse data sets to produce predictions, hence enhancing the accuracy and dependability of the future predictions. Overall, these results shed light on guiding further exploration of investor investments in stocks and researcher studies theories and models.

Modeling Supply Chain Firms’ Stock Prices in the Fertilizer Industry through Innovative Cryptocurrency Market Big Data

Due to the volatility of the markets and the ongoing crises (COVID-19, the Ukrainian war, etc.), investors are keen to exploit any potential chances to make profits. For this reason, the idea of harvesting data from cryptocurrency market users takes an innovative step. Potential investors in supply chain firms in the fertilizer industry need to know whether the observation of data originating from the cryptocurrency market is capable of explaining their stock price variation. The authors identify the innovative utilization of cryptocurrency markets’ user analytical data to model and predict the stock price of supply chain firms in the fertilizer industry stock price. The main aim of this research is to evaluate the contribution of cryptocurrency market big data as a predicting factor for the stock price of fertilizer market firms. Such a finding improves the knowledge and decision-making of potential investors in the fertilizer market. Moreover, this study seeks to highlight the benefits of utilizing cryptocurrency market big data for other financial purposes, apart from stock price prediction. The analytical data was derived from cryptocurrency websites and applications and was then processed through statistical analysis (correlation and linear regressions), Fuzzy Cognitive Maps (FCM), and Hybrid Modeling (HM) modeling. The hybrid model’s simulation showed that analytical data from the cryptocurrency markets tend to explain and predict the stock price of supply chain firms in the fertilizer industry. Such data refer to Bitcoin’s website organic keywords and traffic costs, as well as paid traffic costs from cryptocurrency trade websites/apps. A rise in Bitcoin and cryptocurrency trade websites’ organic and paid traffic costs tend to increase supply chain firms in the fertilizer industry’s stock prices, while Bitcoin’s website organic keywords variation decreases accordingly.

정보전이지수를 이용한 원자재가격과 산업별 주식수익률의 연계성에 대한 Covid-19과 러우전쟁의 영향 분석

This paper analyzes the effect of commodity prices on the industrial stock market. The commodities selected to represent raw materials are crude oil, copper, and corn. Kospi and six industrial stock price indices including foods, chemical, steel, machinery, electronic, and transport are analyzed. The exchange rate is also included in the model. Test period is 1,257 trading days from September 5, 2017 to December 23, 2022. Spillover effect is measured with Diebold and Yilmaz (2009, 2012)’s index. Major findings are as follows. First, the influential markets to stock and foreign exchange markets are copper and crude oil markets. Second, the stock market which was a contributor to information before Covid-19 changed role to the recipient of information during the Covid-19 and Russo-Ukraine war period. Third, the effect of crude oil and corn on Kospi returns caused by the Covid-19 is increased. And the effect of copper is increased during the Russo-Ukraine war period. Fourth, the stock returns of electronic, chemical and steel industries have high connectedness with the commodity market compared to that of foods, machinery and transport industries. Fifth, the total spillover index appears high in all industries during the Covid-19 and Russo-Ukraine war period compared to pre-Covid-19 period.

The Impact of the Covid-19 Pandemic Crisis on the Performance of Pharmaceutical Companies' Stock Price Case Study of Pharmaceutical Companies in Indonesia

This thesis analyzes the impact of the COVID-19 pandemic on the performance of pharmaceutical company stock prices, in which research was conducted on pharmaceutical company stocks in Indonesia. The impact of the COVID-19 pandemic felt by the community is a decrease in income. The decrease in income has also been felt by investors and owners of industries in various manufacturing sectors. Some companies have even closed factories and laid off their workers. Thus this also affects the stock market of the manufacturing industry in Indonesia. In this study, we will analyze the effect of the increase in the rate of positive daily cases and the death rate from COVID- 19 on the performance of pharmaceutical companies' stock prices. The selection of the research sample of 5 (five) pharmaceutical industry stock prices is based on the size of the market capitalization value that is included in the top 10 pharmaceutical industries in Indonesia. In analyzing the performance of pharmaceutical stock prices, the most appropriate GARCH model will be selected by comparing the symmetric model (SGARCH) to the a-symmetric model (TGARCH and EGARCH) and the most appropriate model is the Exponential General Autoregressive Conditional Heteroskedastic (EGARCH) model. Daily positive (dailycase) and daily cases of death (deathcase) have a positive coefficient value, which means that the impact of the COVID-19 pandemic has had a significant effect on the price of these pharmaceutical stocks.

Game Industry in Long-term Uncertain Situation: A Normalized Covid-19 Pandemic Perspective

An unprecedented pandemic of Covid-19 hit the world and impacted the stock price of the game industry in China and overseas. How largely the game industry stock price is impacted, and the prediction of the future trends is being studied in this paper. To have a better understanding of data and to make sure predictions are accurate, this article employs VAR and ARMA-GARCH models. It is found that the relationship between the game industry and Covid-19 in the beginning stage is highly and positively related in China and overseas markets, but then the relationship turns to be negative. In the long run, the impact of Covid-19 on the game industry turned negligible, and the relationship became stable. It is also found that investors do not seem to learn from their previous experiences, and the earning yield of the game industry is repeated over and over in history, but the time for the recurrence of history has been shortened.

New Energy Vehicles Industry Stock Price Prediction Based on ARIMA: Tesla, NIO and BAIC BluePark

Stock price prediction plays a main role and serve as a key for quantitative analysis and investment in financial field. With the boosted of various state-of-art statistical approaches as well as computing strategies, various forecasting scenarios have been proposed. Among numerous prediction schemes, ARIMA is one of widely implemented and explored models. On this basis, this study presents extensive process of predicting stock price based on the ARIMA model. The stock prices of Tesla, NIO and BAIC BluePark in new energy vehicles industry are collected from investing.com and money.com and used for prediction. The parameters of ARIMA model which is p, q and d ranging from 0 to 4. According to the analysis, it is feasible for short-term forecasting in new energy vehicles industry and is competitive with other forecasting models in helping both institutions and individuals’ investment. To be specific, the predicted stock price is close to the actual data and institutions and individuals can make profitable decisions based on the results. Overall, these results shed light on guiding further exploration of price forecasting of underlying assets.

Cyclical and Non-Cyclical Industry Stock Price Reaction towards Movement Control Order (MCO), Economic Stimulus Package and Vaccine Agreement Announcements: The Case of Covid-19

This study carries out empirical analyses using a market-model event study from 26 March 2020 to 20 November 2020. There are three major events highlighted in this article that explain the cyclical and noncyclical stock performance during the COVID-19 outbreak: (a) the implementation of the nationwide Movement control order series (MCOs); (b) the announcement of the economic stimulus package; and (c) the signing of the vaccine agreements. Empirical results are summarized into three main insights: (a) the 10-day event window (CAR −9,0), which entailed the first MCO, was marked by the closure of both public and private non-essential entities, further suspension of events and recreational activities, which negatively affected nationwide economics activities; (b) the 3-day event window (CAR −1,1), which entailed the announcement of the economic stimulus package, resulted in most industries reacting with positive returns except for the oil equipment and services industry; and (c) event window day-293 (CAR +131, +161), which entailed the announcement of the distribution and implementation of COVID-19 vaccines, whereby industries related to the healthcare segments such as equipment and services (+0.0694) and pharmaceuticals and biotechnology (+0.0671) showed positively significant returns at least at the 10% level. Finally, future research could enlighten ownership patterns in Malaysia due to Malaysian companies exhibiting a concentrated ownership structure.

Valuation Analysis of New Energy Vehicle Industry Stock Price Based on HP-ARIMA Method

In recent years, new energy vehicles have become one of the mainstream trends in the global auto market. By analyzing the valuation of the stock price of the new energy automobile industry, the actual value of its stock can be found, thus providing a specific reference for investors. Based on this, this paper investigates the fluctuation of daily average stock prices using the HP-ARIMA method, and performs predictive analysis, robustness test and heterogeneity analysis on the given data. After separating the short-term fluctuations and long-term trends of daily average stock prices based on the HP filtering method, the predictions were made by the ARIMA model. The predicted results were tested for robustness by OLS regression and Tobit model, respectively, and the following findings were obtained: (1) Through the analysis of HP filtering method, the cyclical fluctuation of the stock price of the new energy automobile industry is relatively large, and upstream enterprises affect the middle and downstream enterprises to a certain extent. (2) The prediction analysis by ARIMA shows that the prediction accuracy of upstream enterprises' share prices is relatively high, and the prediction results have good robustness. (3) The regression analysis shows that the fit is good for upstream and downstream enterprises, and the change trend shows a positive correlation, while the midstream enterprises show the opposite trend.

Crude oil futures to manage the price risk of textile equities: An empirical evidence from India

The textile sector in India is the oldest manufacturing sector. As the raw materials for this sector are sourced from the petrochemical industries, the earnings of Indian textile companies are dependent on the crude oil price. The crude price in the international market has become more volatile and hence, the equity price of Indian textile companies has become more volatile. This study aims to develop two price risk management strategies for Indian textile equities. Using the vector autoregressive (VAR) model, a price forecast model, further the possibility of cross hedge for textile equities with the help of crude futures is examined using the Granger causality test and Pearson correlation statistics. The results of the study showed that crude futures price in India is one of the price determinants of textile industry stock prices.

The effects of drought on stock prices: An industry-specific perspective

In this study, we examine the effect of drought on industry stock prices using a balanced panel of monthly data for 15 industries classified by China Securities Regulatory Commission in 2012. By combining the results of ordinary least squares (OLS) estimation and quantile regression models, we present a comprehensive evaluation of the relationship between drought and industry stock prices. The OLS regression results generally show that drought is negatively correlated with industry stock prices. However, quantile regression reveals that the effect of drought changes from positive to negative from the lowest to the highest stock price quantile. In addition, drought resistance capacity varies by industry. We further use threshold regression to determine the effects of investor sentiment on the relationship between drought and stock prices and identify two different regimes: low sentiment and high sentiment. In the low sentiment regime, drought has a significant negative effect on industry stock prices, while in the high sentiment regime, drought has a significant positive impact on industry stock prices.

How do stock price indices absorb the COVID-19 pandemic shocks?

To assess the resiliency of stock price indices during the COVID-19 crisis, this study provides a distinctive perspective; that is, we evaluate the ability of stock price indices to absorb COVID-19 shocks. We construct the measures of absorptive intensity and duration to identify a stock price’s absorptive capacity. We then employ the Granger causality test and a topology network approach to investigate the interactions of absorptivity among stock price indices. Our results show that stock price absorptivity varies over time and across countries and industries. The US and the Brazil stock indices have relatively high absorptive intensity while short duration. The health care industry shows distinctive trend in absorptive intensity from the other industries. The intensity of the non-cyclical industries such as utilities and consumer staples is high, while the cyclical industries such as banking, real estate, and energy have lower absorptive intensity. Moreover, the utilities, consumer staples, and financials industries are the main resiliency transmitters.

Examining the Impact of Quantitative and Qualitative Easing on the Link between Consumer Sentiment and Stock Prices: Evidence from Nikkei's Industry Stock Price Data

Examining the Impact of Quantitative and Qualitative Easing on the Link between Consumer Sentiment and Stock Prices: Evidence from Nikkei's Industry Stock Price Data

Sequential detection of common transient signals in high dimensional data stream

AbstractMotivated from sequential detection of transient signals in high dimensional data stream, we first study the performance of EWMA and MA charts for detecting a transient signal in a single sequence in terms of the power of detection under the constraint of false detecting probability in the stationary state. Satisfactory approximations are given for the false detection probability and the power of detection. Comparison of EWMA, MA, and CUSUM charts shows that both charts are quite competitive. A multivariate EWMA procedure is considered by using the squared sum of individual EWMA processes and a fairly accurate approximation for the false detection probability is also given. To increase the power of detection, we use the Min‐δ procedure by truncating the estimated weak signals. Dow Jones 30 industrial stock prices are used for illustration.

How and What Influences from COVID-19 Have Impacted Stock Prices and Exchange Rates? the Case of Japan

This study reports the empirical analyzes of the COVID-19 on stock prices and exchange rates of Japan. Newly confirmed cases and death cases have significantly positive impacts on Japanese stock prices. One reason is that Japanese stock prices recently move together with U.S. stock prices. Under this situation, the U.S. could recover from the damage of COVID-19 ahead of other countries and its stock prices have increased hugely, so the effects on Japanese stock prices have been quite large. The rising of the U.S. stock prices have had a big influence so as to deny the adverse effects by COVID-19 in Japan. The other reason is that although the stock prices of tourism, food service, and so on were damaged in Japan, other industry stock prices have been increasing. The coefficients of declaration of the state of emergency/anti-infection measures are positive which denotes that the stock market may have taken the measure favorably. However, they are positive, but they are also insignificant. For the exchange rates, the newly confirmed case is significant and positive which means that it promotes depreciation of the Japanese Yen. It seems natural because if the situation of COVID-19 becomes serious, market participants consider investment in Japan as risky. Finally, both of the cases of confirmed cases and death cases of COVID-19 are negatively and significantly related with the flow of people. The coefficient of declaration of the state of emergency/anti-infection measures is negative, however, they are not significant to the flow of people.