Opening Price Research Articles

Stock Prediction based on BP Neural Network

In this paper, using Wind database, the stock code 600276 is selected as the main research object, and the daily K data from 15 October 2018 to 14 October 2022 is selected. The variables in the article are Open Price, Close Price, High Price, Low Price, Volume, and Amount. Firstly, the data is normalized and then a BP neural network model is used for training. In the model after several training sessions, the reciprocal 20 pieces of data in the "opening price" variable are selected as the data for the prediction set to observe the training. Finally, the results of the test set of real stock price tests are introduced and the predicted results are visualized. It is concluded that when the hidden layer nodes of the neural network are fewer, the structure of the neural network is too simple, then its learning ability and classification ability will be reduced, but if the hidden layer nodes are too much, the structure of the neural network is too complex, the network is overloaded, and the efficiency will be reduced, and the ability of the promotion will be deteriorated. Therefore, neural network training should ensure the classification ability of the neural network on the one hand and the promotion ability of the neural network on the other hand.

Distinctive Assessment of Neural Network Models in Stock Price Estimation

INTRODUCTION: Due to its potential to produce substantial returns and reduce risks, stock price prediction has garnered a lot of attention in the financial markets. OBJECTIVES: A comparison of neural network models for stock price prediction is presented in this research report. METHODS: Through this study, I aim to compare, on the basis of the precision and accuracy, the performance of different neural network models for stock price prediction. LSTM model along with RNN model accuracy in predicting the next day’s stock price i.e., which model can predict closest to the actual value. RESULTS: It is found that LSTM works better than RNN in predicting a value closer to the actual open price stock value. CONCLUSION: A comparison between the models shows LSTM is the more accurate model.

Multiple Stock Prediction Based on Linear and Non-linear Machine Learning Regression Methods

In contemporary times, the pressing issue of global environmental pollution has prompted the exploration of alternative energy sources by various industries, aiming to mitigate the adverse environmental impacts caused by traditional energy production. Correspondingly, investors in the financial market have increasingly redirected their capital towards the new energy sector. Within this context, the present research endeavors to employ machine learning techniques for the prediction of Tesla's stock price. This study leverages multiple linear regression, polynomial regression, and lag models to construct models based on the datasets of TSLA, MPC, and UNG stock prices spanning the period of 2019-2020. By discerning potential patterns among these variables, the objective is to anticipate the future trajectory of TSLA stock price. According to machine learning methods, Tesla's stock price can be predicted, and the daily price of Tesla is influenced by the opening price, high price, low price and trading volume of the stock on that day. In addition, the share prices of energy companies related to Tesla also have an impact on Tesla's share price on that day. Specifically, Tesla's stock price is influenced by Natural Gas Company (UNG), which has an opposite relationship. Although common sense economics says that the crude oil market will be closely related to the new energy market. However, the results of this study demonstrated that Tesla's stock price is less influenced by Crude Oil Company (MPC).

Comparison of Decision Tree Regression with Linear Regression Based on Prediction of Apple Stock Price

Machine learning has been increasingly used in stock price prediction with outstanding success. Decision tree regression models and linear regression models are both important models for predicting stock prices. The paper use decision tree regression and linear regression models to predict the opening price, closing price, high price and low price of Apple's stock price data respectively. The prediction effects of the two models are evaluated by the indicators of goodness of fit, mean square error, root mean square error and mean absolute error, and the prediction effects of the two models are compared. This experimental concludes that the decision tree regression model has better and more advantageous prediction results compared to the linear regression model. This study has guiding significance for machine learning in predicting stock prices when choosing a basic model or a combination of models for prediction.

Analyzing the Impact of Financial News Sentiments on Stock Prices—A Wavelet Correlation

This study investigates the complex interplay between public sentiment, as captured through news titles and descriptions, and the stock prices of three major tech companies: Microsoft (MSFT), Tesla (TSLA), and Apple (AAPL). Leveraging advanced analytical methods including Pearson correlation, wavelet coherence, and regression analysis, this research probes the degree to which stock-price fluctuations can be attributed to the polarity of media sentiment. The methodology combines statistical techniques to assess sentiment’s predictive power for stock opening and closing prices, while wavelet coherence analysis unveils the temporal dynamics of these relationships. The results demonstrate a significant correlation between sentiment polarity and stock prices, with description polarity affecting Microsoft’s opening prices, title polarity influencing Tesla’s opening prices, and a positive impact of title polarity on Apple’s closing prices. However, Tesla’s stock showed no significant coherence, indicating a potential divergence in how sentiment affects stock behavior across companies. The study highlights the importance of sentiment analysis in forecasting stock-market trends, revealing not only direct correlations but also lagged influences on stock prices. Despite its focus on large-cap tech firms, this research provides a foundational understanding of sentiment’s financial implications, suggesting further investigation into smaller firms and other market sectors.

Prediction of Opening Price of Shanghai Stock Exchange 380 Index Based on ARIMA Model

This paper first introduces the relevant theoretical knowledge about time series analysis, then makes an empirical analysis and finally summarizes it. This paper selects 97 data of the opening price of Shanghai Stock Exchange 380 Index from June 1, 2023 to October 30, 2023, fits the ARIMA model and tests the validity of the model. Finally, the opening price of the next three trading days is predicted by using the fitted model and compared with the real value to test the prediction effect.

Volatility Prediton based on Multiple-factor Model

Generally, due to unpredictable and vulnerable features of the stock market, traditional statistical methods with single factor cannot explain the movements of stock prices well. In this paper, multi-factor model of quantitative stock selection is applied to predict stock price index to perceive the fluctuation of stock in multiple aspects and improve the accuracy of prediction. This study also combines machine learning measurements with historical data fitting effects. The data used for analysis is all collected from Tushare website, and the stock data are from the 2015 to 2022 data of Shanghai Pudong Development Bank and China Merchants Bank, and the selected factors include price-to-earnings ratio, price-to-book ratio, volume ratio, total equity and so forth. Ordinary least square linear regression and random forest nonlinear approaches are utilized to predict the stock price. According to the analysis, the accuracy of random forest is higher than OLS in stock price prediction. Among all the factors, the opening price, the highest price and the lowest price have relatively large impacts on the closing price of the next day. However, when selecting different factors, stocks and train-testing periods, the obtained regression models are different. Therefore, the determination of the correlation coefficient is not invariable and needs to be analyzed on a case-by-case basis. Overall, these results shed light on the superiority of machine learning model and the significant contribution of some factors on stock price prediction.

Forecasting Stock Market Volatility via Causal Reasoning

Abstract Studies have shown that Internet financial news has become an important reference for investors in investment behavior. In order to simulate trading experiments that mimic the real stock market, this paper develops a stock volatility prediction model based on causal reasoning. It also gathers and cleans news and stock market data from the Internet, such as opening price, closing price, and change. The findings of the study indicate that the level of stock market volatility can be significantly influenced by online financial news. The proposed model can analyze the effects of news and stock market data in an explainable manner.

Newspapers tone and the overnight-intraday stock return anomaly

We examine the associations between newspapers tone and stock market indices by translating newspapers coverage into human sentiment gauge. Our tone has positive effects on overnight stock returns and negative effects on both intraday returns and conditional volatility. The positive effect of the tone is highly significant on days of sharp price declines and when the tone is calculated using general newspapers. That positive effect, apparently thru opening prices, partly explains the overnight-intraday anomaly. The impact of negative events' coverage is about double the impact of positive events’ coverage. This asymmetry is greater when distinguishing between general and business newspapers.

An improved LSTM stock price prediction model based on multiple basis function expansion and two-layer Bagging algorithm

Using neural network technology to predict the time series data of stock prices is a hot issue in the field of computational science. For example, Long Short-Term memory network technology (LSTM) has been widely used in stock price prediction. However, if the original stock opening price series information is not enough to predict the future trend, the effect of LSTM model may not be ideal. In addition, improper selection of the step size will also make the prediction effect of the LSTM model poor. This paper proposes an improved LSTM model based on multi-view basis function expansion and Bagging algorithm. On the one hand, under a fixed step size, the intra-day price information of the stock is extracted by using a variety of basis function expansion forms as prior information, and then the Bagging algorithm is used to establish the relationship between the basis expansion coefficients and the prediction residual of the original LSTM model to predict the residual, thereby increasing the prediction accuracy. On the other hand, the problem of LSTM step size selection is adaptively solved by using the idea of model average instead of the model selection method, and the specific method is to combine the weighted average of LSTM models with different time lengths. The actual data analysis shows that the proposed method improves the prediction accuracy of the original LSTM model, and the t-test shows that the proposed method has significant robustness.

Relationship between the Reduction of Opening Price Auction-process Time and Effect of Price Discovery

On April 29, 2019, the KOSPI market of Korea Exchange reduced the opening price auction-process time from 1 hour (08:00-09:00+) to 30 minutes (08:30-09:00+) for the first time in more than 20 years. We examine whether this event was useful in improving price discovery in the market. Using the real-time indicative prices before and after the event, we analyze the price-discovery effect via unbiased regression analysis and the price-discovery speed with weighted price contribution (WPC). We derive the following results. First, the opening price-discovery effect after the event was at least the same as that during the second-half 30 minutes before the event, and the measure of reducing time was somewhat useful to improve the market’s operational efficiency. Second, the slope of the WPC inverse J-shaped pattern was much steeper after the event, implying that the speed of the opening price discovery improved too much and quickly so that about five minutes before opening was needed to be hastily adjusted. Third, analyses by liquidity level revealed that most were similar to those of the overall market analysis, but they were less effective in the price-discovery effect and speed of the group with the lowest liquidity (Q1).

Stock index forecasting based on multivariate empirical mode decomposition and temporal convolutional networks

Modeling and forecasting of stock indexes is an important and challenging work in the field of financial research, which is of great significance for investors to reduce risk on investment and improve investment returns. However, the basic data of the stock index includes five indicators, namely, opening price, highest price, lowest price, closing price and trading volume (COHLV), each of which contains some information related to the future trend. And these indicators are affected by different factors such as politics, economy, psychology and so on, so they have nonlinear, high noise and other complex characteristics. These reasons make the existing methods cannot effectively improve the accuracy of stock index forecasting. In order to solve this problem, we propose a hybrid stock index forecasting model named MEMD-TCN, which is based on multivariate empirical mode decomposition (MEMD) and temporal convolutional networks (TCN). The novelty of the proposed model focuses on decomposition of multivariate time series and using only fully convolutional layers to forecast stock index. The proposed model first uses MEMD to decompose the data of COHLV to obtain subsequences of different fluctuation frequencies of each time series, then inputs subsequences of the same frequency into TCN to predict the subsequences of closing price in the next period. Ultimately, the forecasted values for the closing price are obtained by reconstructing the prediction results of all the subsequences of closing price. To evaluate the performance of the proposed MEMD-TCN model, stock index of several countries that can reflect the overall changes of the market are used. The experimental results verify the notable effectiveness and necessity of the decomposition of multivariate time series. Meanwhile, the results demonstrate the significant superiority of the proposed MEMD-TCN model on accuracy and stability.

Predicting Crude Oil Future Price Using Traditional and Artificial Intelligence-Based Model: Comparative Analysis

Crude oil is an imperative energy source for the global economy. The future value of crude oil is challenging to anticipate due to its nonstationarity in nature. The focus of this research is to appraise the explosive behavior of crude oil during 2007–2022, including the most recent influential crisis COVID-19 pandemic, to forecast its prices. The crude oil price forecasts by the traditional econometric ARIMA model were compared with modern Artificial Intelligence (AI)-based Long Short-Term Memory Networks (ALSTM). Root mean square error (RMSE) and mean average percent error (MAPE) values have been used to evaluate the accuracy of such approaches. The results showed that the ALSTM model performs better than the traditional econometric ARIMA forecast model while predicting crude oil opening price on the next working day. Crude oil investors can effectively use this as an intraday trading model and more accurately predict the next working day opening price.

A hybrid multicategory framework for generating automated trading systems

AbstractThis work proposes a framework for producing automatic trading systems that suggest making trading decisions in financial markets. The trading systems thus generated utilize multicategory classifiers. A collection of important technical indicators are considered as input features for the underlying multicategory classifiers. The proposed trading systems also have an option to use random forest (RF) algorithms for feature selection. The trading range breakout strategy is used to train the proposed trading systems thus generating “BUY/SELL/WAIT” trading signals on daily open prices. The performances of the proposed trading systems are evaluated over five future indices. Empirical findings suggest that the day trading systems based on the proposed multicategory SVM classifiers along with the RF technique outperform the day trading systems built using the multicategory classifiers taken from the literature. The trading range breakout strategy‐based systems are found to be superior to the traditional BUY‐HOLD strategy and that of RF‐PSVM (BUY/SELL) based strategy.

Stock Price Prediction using Deep Recurrent Model

In this paper, we aim to predict the stock trend using previous stock data. In specific, we perform LSTM training on the stock data of 2017 and 2018 by using the Sandp500 data as the base. The data includes the stock date, opening price, closing price, the highest price of the day, the lowest price of the day, and volume. Through these data we conducted 100 epoch training. After training, our LSTM can correctly predict the learning curve without any delay influence, with a satisfying performance. And we got the visual graph and chart to prove that the result is effective. The MSE value decreased from the original 3.026 to 0.238. This shows that the error of the result is small and the reliability is high. After LSTM training, it can help stock investment companies and related institutions and individuals to better avoid risks and provide individuals with high-credibility investment advice.

Intraday trend prediction of stock indices with machine learning approaches

In recent years, as research at the intersection of machine learning and finance has grown, predicting stock price movements has become a particularly intriguing issue. Current research focuses primarily on using historical data of the previous day to predict stock movements for the following day, whereas fewer studies use the trading day’s opening data to predict market movements for the current day. We predict intraday price movements of the SSE-50 (Shanghai Securities 50 Index) using stock market opening data as input. Specifically, decision tree, extreme gradient boosting (XGBoost), random forest, support vector machines (SVM), and long-short-term memory are developed to predict the movements of the SSE-50 index utilizing opening price data of various time intervals. We also design three trading strategies when different time frequencies of data are used. At the same time-frequency, the results demonstrate that SVM with Gaussian and linear kernels outperform others. The forecasting accuracy at 10-min frequency approaches 70%, which is close to the results at longer time intervals, indicating that intraday trend can be determined by opening price fluctuations and the first 10-min data contains sufficient information to predict the trend for the entire trading day. In addition, trading methods based on the forecast of daily, weekly, and monthly SSE-50 price movement outperform buy-and-hold strategies. Daily trading performs better than the other two strategies. The outcomes of this research can expand the use of machine learning in quantitative trading and enrich intraday trading techniques further.

Stock Price Prediction based on Long Short-Term Memory Model

The stock market is a place that brings investors opportunity to gain profit. Meanwhile, the stock market also brings investors high risks, which requires machine learning methods to improve the accuracy of prediction. This paper uses the Long Short-Term Memory (LSTM) model to predict stock prices. In the study, the daily stock historical data of Sinopec, Moutai and SPD Bank in the past 21 years are used as samples, including the date, the trade volume, the highest price, the lowest price, and the opening and closing prices. After the LSTM model has been trained, the three companies' predictions of opening price have achieved good results, and the predicted opening price curve and the actual opening price curve seem to be quite consistent. In terms of evaluation indicators, MAPE of the three companies is less than 1%. These results can provide some help for investors to predict stocks and shed light on guiding further studies.

Evaluation of Nexus Between Short-Run Return Measures of IPOs in India

Purpose : This study aimed to provide a better understanding of the initial performance of initial public offerings (IPOs) on the day of listing by separating the gains on the listing day into primary and secondary market returns. An industry-wise evaluation of different return measures was done, and a year-on-year analysis was also conducted to understand more about the underpricing anomaly of IPOs. Methodology : The short-run IPO performance was analyzed using market-adjusted average returns (MAAR), focusing on the role of different factors in determining underpricing. The initial returns were divided into primary and secondary returns, and a sectoral analysis was conducted to evaluate the behavior of IPOs on the first day of trading. The quantitative analysis considered the returns from the issue date to the listing day opening price and compared the listing day opening and closing prices of all sample IPOs. Findings : The sectoral analysis revealed a reversal of the level of underpricing during the secondary market, which explains the listing day performance of IPOs under different industries over the last decade. According to the findings of this study, the subscription rate is a major determinant of short-run IPO performance. Practical Implications : To improve the short-run performance of IPOs, issuers should focus on increasing their subscription rates. This study recommended that corporations should publish credible, accurate, and adequate information and invite active participation from shareholders. Originality : Unlike prior research on IPOs, this study separated listing day gains into primary and secondary market returns, carried out an industry-wise evaluation of different return measures, and analyzed IPO behavior on the first day of trading to provide improved insights into the underpricing anomaly of IPOs.

Pre- and Post-COVID-19: The Impact of US, UK, and European Stock Markets on ASEAN-5 Stock Markets

This study investigates the relationship between closing–opening prices of stocks in the US, UK, and European markets and the prices of stocks in the five Association of Southeast Asian Nations (ASEAN-5) markets, a group consisting of five founding members, namely, Indonesia, Malaysia, the Philippines, Singapore, and Thailand. In particular, this study examines the impact of US, UK, and European stock market movements on ASEAN-5 stock markets before and during the COVID-19 pandemic. An autoregressive distributed lag (ARDL) bounds testing approach was employed on two independent data sets, representing prices of stocks before and during the COVID-19 pandemic. The results reveal that among the ASEAN-5 markets, only the Philippines had a cointegration relationship with the US, UK, and European markets before the crisis. However, almost all ASEAN-5 markets moved in tandem with the US, UK, and European markets during COVID-19, except for Thailand. These empirical findings also indicate that the stock markets in the two regions tended to co-move during the COVID-19 pandemic, implying a contagion effect. Further, the causality results also provide substantial evidence of contagion between markets during the pandemic. These results imply that the stock markets in ASEAN-5 are susceptible at the opening bell to the behaviour of US, UK, and European stocks. Therefore, investors or traders in ASEAN-5 should participate in foreign markets (other than the US, UK, and Europe) that do not exhibit cointegration relationships to better mitigate and manage risk at the opening bell, especially during a global crisis.

Investment strategy via analyst report text mining

The recommendation of the analyst report is not only limited to a small number of ratings, but also biased toward a buy opinion with the absence of sell opinion. As an alternative to this, this paper aims to extract analysts' textual opinions embedded in the report body through text analysis and examine the profitability of investment strategies. Analyst opinion about a firm is measured by calculating the frequency of positive and negative words in the report text through the Korean sentiment lexicon for finance (KOSELF). To verify the usefulness of textual opinions, the author constructs a calendar-time based portfolios by the analysts' textual opinion variable of each stock. When opinion level is used, investment strategy has no significant hedged portfolio return. However, hedged portfolio constructed by opinion change shows significant return of 0.117% per day (2.57% per month). In addition, the hedged return increases to 0.163% per day (3.59% per month) when the opening price is used instead of closing price. This study show that the analysts’ opinion extracted from text analysis contains more detailed spectrum than recommendation and investment strategies using them give significant returns.