Short-term Stock Price Research Articles

Short-Term Stock Price Prediction by Supervised Learning of Rapid Volume Decrease Patterns

Short-Term Stock Price Prediction by Supervised Learning of Rapid Volume Decrease Patterns

Short-Term Stock Price Prediction Based on CAE-LSTM Method

Artificial intelligence methods are important tools for mining information for forecasting in the stock market. Most of the literature related to short-term stock price prediction focuses on the technical data, but in the real market, many individual investors make investment decisions more from stock price shape characteristics rather than specific stock price values. Compared with traditional measurement methods, deep neural networks perform better in processing high-dimensional complex data such as images. This paper proposes a model that combines CAE (convolutional autoencoder) and LSTM (long short-term memory) neural network, uses CAE to extract stock price image feature data, and combines technical data to predict short-term stock prices. The results show that the CAE-LSTM model, based on stock price image morphological feature data and technical data, performs well in short-term stock price prediction and has good generalization ability. The root mean square error of the CAE-LSTM model decreased by about 4% from that of LSTM. CAE-LSTM models have better predictive power than LSTM models that only use technical indicator data as valid inputs.

The long game of innovation and value creation

PurposeThe purpose of the paper is to emphasize the performance benefits of a long-term innovation and value creation perspective. This paper responds to the recent concept of the imagination premium method for valuing companies. It offers four key takeaways to create a long-term innovation-focused orientation for future value creation.Design/methodology/approachThe research is based on both consulting experience and insight from several studies of executives that were supported by the U.S. Conference Board.FindingsThe research differentiates how high versus low innovators create long-term perspectives and value. High innovators have explicit processes that support innovation, leadership that focuses on long-term performance, resources committed to long-term projects and innovation and knowledge management systems that transfer knowledge throughout the organization.Research limitations/implicationsThe research offers strategic directives aimed at creating long-term value but acknowledges that there are other means to accomplish such objectives.Practical implicationsThis paper offers strategies for executives to create an innovation-focused organizational culture that drives lasting long-term value.Social implicationsFocusing on long-term innovation prioritizes larger social, environmental and business objectives over superficial short-term stock price changes, leading to greater value-creation.Originality/valueThis paper advocates that leadership play the long game and adopt a longer-term view of innovation due to its long-term competitive, employee engagement, sustainability and performance benefits.

The effect of controlling person's illegalities on stock price returns: Evidence from Elman neural network model.

Controlling persons are the ultimate decision-makers of listed companies. Their illegalities have impacts on investors’ wealth, firm development, and capital market’s quality. Against this backdrop, we provide a quantitative analysis of the short-term stock price reaction to the criminal detention announcements of controlling persons throughout 2007–2019. We applied the Elman neural network (ENN) model into the classical event study methodology and demonstrated that the combination of them helps to improve the estimation accuracy of the stock price reaction. The results show that the stock price has a significant negative reaction to the criminal detention announcements of listed companies’ controlling persons on the announcement day, and the average reaction level is -6.67%. Additionally, the crisis communication measures of the firms could diminish the negative impact of such mandatory disclosure information on their stock price, but the effect is limited. Finally, the 31 companies in our sample cause a total loss of RMB 21.1 billion in market capitalization on the announcement day alone. The above results indicate that the impact of listed companies’ controlling persons on the capital market is tremendous, although the number of this group is small. Our work enriches the listed companies’ illegalities research and provides a reference for investors’ investment choices and follow-up decision making of regulatory authorities. It also provides some guidance for most of the researchers to further explore the application of data mining techniques in nonlinear problems.

Modeling of Hyperparameter Tuned Hybrid CNN and LSTM for Prediction Model

The stock market is an important domain in which the investors are focused to, therefore accurate prediction of stock market trends remains a hot research area among business-people and researchers. Because of the non-stationary features of the stock market, the stock price prediction is considered a challenging task and is affected by several factors. Anticipating stock market trends is a difficult endeavor that requires a lot of attention, because correctly predicting stock prices can lead to significant rewards if the right judgments are made. Due to non-stationary, noisy, and chaotic data, stock market prediction is a huge difficulty, and as a result, investors find it difficult to invest their money in order to make a profit. In order to predict stock market movements, a number of strategies have been established. Earlier studies based on statistical models and machine learning techniques have been focused on short term stock price prediction. In this aspect, this study designs a novel hyperparameter tuned hybrid convolutional neural network with long short term memory (HPT-HCLSTM) for stock price prediction. The proposed HPT-HCLSTM technique encompasses three different processes namely pre-processing, prediction, and parameter optimization. The HPT-HCLSTM technique employs the HCLSTM technique for the prediction of stock prices. In addition, teaching and learning based optimization (TLBO) algorithm is applied for the hyperparameter optimization of the HCLSTM technique and thereby results in minimal error values. In order to demonstrate the enhanced prediction performance of the HPT-HCLSTM technique, a wide range of simulations were carried out and the results highlighted the better performance of the HPT-HCLSTM technique under several aspects. The HPT-HCLSTM technique is found to be a proper tool for forecasting stock prices. the HPT-HCLSTM technique has showcased better performance with the increased R2 value of 0.9154.

Research on Short-Term Stock Price Trends Based on Machine Learning

With the increasing emphasis on economic development, China’s economy is growing steadily and significantly, and the stock market is becoming more diversified and richer in products and derivatives, resulting in a larger and larger base of investors in the Chinese stock market over the years, with more significant changes in the investment environment of the primary stock market. In the analysis and research around stocks, the fitting and prediction of stock price changes have been one of the keys in the field of stock analysis, however, the current models and solutions for stock price fitting and prediction have not been well received, and are lacking in terms of realistic operability and applicability. In recent years, machine learning and its related models and methods have been widely used in the financial field, which has also promoted the development of stock price fitting forecasting. In order to further improve the accuracy of stock price fitting prediction, this paper introduces the multi-factor prediction model in traditional quantitative stock analysis into the stock price fitting prediction method and improves the general stock price fitting prediction method. This paper finds that the screening of factors that can significantly affect stock prices can indeed be accomplished by using the methodological properties of GBDT and FFM.

STOCK PRICE PREDICTION USING MARKOV CHAINS ANALYSIS WITH VARYING STATE SPACE ON DATA FROM THE CZECH REPUBLIC

The article describes empirical research that deals with short-term stock price prediction. The aim of this study is to use this prediction to create successful business models. A business model that outperforms the stock market, represented by the Buy and Hold strategy, is considered to be successful. A stochastic model based on Markov chains analysis with varying state space is used for short-term stock price prediction. The varying state spate is defined based on multiples of the moving standard deviation. A total of 80 state space models were calculated for the moving standard deviation with 5-step lengths from 10 to 30 in combination with the standard deviation multiples from 0.5 to 2.0 with the step of 0.1. The efficiency of the business models was verified for 3 long-term, liquid stocks of the Czech stock market, namely the stocks of KB, CEZ, and O2 within a 14-year period – from the beginning of 2006 to the end of 2019. Business models perform best when they use a state space defined on the length of a moving standard deviation between 15 and 30 in combination with multiples of the standard deviation between 1.1 and 1.2. Business models based on these parameters outperform the passive Buy and Hold strategy. In fact, they outperform the Buy and Hold strategy for both the entire period under review and the yielded five-year periods (including transaction fees). The only exception is the five-year periods covering 2015 for O2 stocks. After the end of the uncertainty period caused by unclear intentions of the new majority stockholder, the stock price rose sharply. These results are in conflict with the efficient markets theory and suggest that in the period under review, the Czech stock market was not effective in any form.

Application of Sobolev-Volterra projection and finite element numerical analysis of integral differential equations in modern art design

Abstract The article uses the Spss statistical analysis software to establish a multiple linear regression model of short-term stock price changes in domestic agricultural listed companies. It uses a stable time series based on the ARMA model for stable agricultural value-added, fiscal expenditure and market interest rates. The regression method is used to study its impact on the stock price index. Compared with the existing stock forecasting methods, this method has simple data collection and no specific requirements for data selection, and the prediction results have a high degree of fit. Therefore, this method is suitable for most stocks.

Stock price analysis based on the research of multiple linear regression macroeconomic variables

Abstract The article uses SPSS statistical analysis software to establish a multiple linear regression model of short-term stock price changes of domestic agricultural listed companies. The article uses a stable time series based on the ARMA model for stable agricultural value-added, fiscal expenditure and market interest rates. The regression method is used to study its impact on the stock price index. Compared with the existing stock forecasting methods, this method has simple data collection and no specific requirements for data selection, and the prediction results have a high degree of fit. Therefore, this method is suitable for most stocks.

Stock market forecasting using intrinsic time-scale decomposition in fusion with cluster based modified CSA optimized ELM

Stock price prediction is a significant index which helps to achieve maximum benefit with minimum risk by increasing the decision making capability of financial investigators and investors. However, the problem of short term stock price prediction is a complex task due to its uncertainty, discontinuity, and random nonlinear nature. In this paper, a prediction model is proposed to predict random nonlinear stock market price using Intrinsic Time-Scale Decomposition (ITD), Cluster based Modified Crow Search Algorithm (CMCSA), and Optimized Extreme Learning Machine (OELM). ITD is adopted to decompose the non-stationary stock price data into some Proper-Rotation-Components (PRCs) and a residual component. ITD is used to convert non-stationary stock price data to stationary data which are simpler and steady for analysis. The CMCSA is proposed by modifying Crow Search Algorithm (CSA) with better capability to select optimal weight and biases of ELM. Thereafter, the optimized ELM is used to predict the PRCs and residual component individually which are then incorporated to predict closing price of short term stocks. The effectiveness of proposed CMCSA is tested and validated by solving benchmark problems. The experimental study indicates that the proposed ITD-CMCSA-OELM model outperforms the CMCSA-OELM, CSA-OELM, DE-OELM (Differential Evolution optimized ELM) and ANN models.

Testing the weak form of efficient market hypothesis for socially responsible and Shariah indexes in the USA

PurposeBy testing the weak form of efficient market hypothesis (EMH) this study aims to forecast the short-term stock prices of the US Dow and Jones environmental socially responsible index (SRI) and Shariah compliance index (SCI).Design/methodology/approachThis study checks the validity of the weak form of EMH for both SCI and SRI prices by using different parametric and non-parametric tests, i.e. augmented Dickey-Fuller test, Philip-Perron test, runs test and variance ratio test. If the EMH is invalid, the research further forecasts short-term stock prices by applying autoregressive integrated moving average (ARIMA) model using daily price data from 2010 to 2018.FindingsThe research confirms that a weak form of EMH is not valid in the US SRI and SCI. The historical data can predict short-term future price movements by using technical ARIMA model.Research limitations/implicationsThis study provides better guidance to risk-averse national and international investors to earn higher returns in the US SRI and SCI. This study can be extended to test the EMH of Islamic equity in the Middle East and North Africa region and other top Islamic indexes in the world.Originality/valueThis study is a new addition to the existing literature of equity investment and price forecasting by comparing and investigating the market efficiency of two interrelated US SRI and SCI.

STOCK PRICE PREDICTION USING STATISTICAL, MACHINE LEARNING AND DEEP LEARNING MODELS

Forecasting stock price is a challenging topic for the researchers by the way of statistics or in newer version by the way of Machine Learning and Deep learning. There are researches that prove that the direction of time series for a stock price can be predicted with a good accuracy. Design of this kind of predictive models requires choice of appropriate variables, right models and methods, and tuning the parameters. In this research, the goal is applying different algorithms and approaches for stock price prediction then compare and evaluate them together. This research also aims to apply these models for short-term stock price prediction. The daily stock price data is used, from tsetmc for five biggest Iranian companies active in the Tehran stock Exchange. For each stock, the data is gathered from January 1, 2018 to January 1, 2021 to train, test and evaluate the algorithms. For evaluating performance of all models, three measures are used for performance evaluation including The Mean Absolute Error (MAE), The Mean Squared Error (MSE), and The Root Mean Squared Error (RMSE). Statistical, Machine learning and deep learning approaches that used are include Auto-Regressive Integrated Moving Average (ARIMA), Random Forest (RF), Support Vector Machines (SVM), and Long Short-Term Memory (LSTM) Networks. Results for applying those models are tested and evaluated and the LSTM model has the best performance concerning other approaches and prove outperformance.

Short-term stock price reversals after extreme downward price movements

We studied the intraday effects of return overreactions around extreme negative one-minute interval returns of Nasdaq100 constituents based on nanosecond data. An extreme negative one-minute interval return is defined as the lowest return that occurs once in 1,000 one-minute intervals. We document that 31% of such an extreme one-minute interval's return is reversed in the subsequent trading minute. The relative magnitude of the reversal after extreme negative one-minute interval returns is particularly high for the 20% most liquid and the 20% largest firms of our sample.

Short Term Stock Price Prediction in Indian Market: A Neural Network Perspective

In recent times there has been an increasing level of debate whether patterns do exist in equity market movements and whether they can be predicted. In order to overcome the shortcomings of traditional time series models, we have focused our study on the application of non-parametric paradigms like stacked multi-layer perceptrons (MLP), long short term memory (LSTM), gated recurrent unit (GRU), bidirectional long short term memory (BLSTM) and gated bidirectional recurrent unit (BGRU) on three NSE listed banks to predict short term stock price, and compared their performance with a shallow neural network benchmark. We have predicted equity ‘Close Prices’ five minutes into the future, using a sliding window approach and have observed that average error in predictions of MLP, LSTM, GRU, BLSTM and BGRU models, varied between 0.09% and 0.1%, indicating their superior performance with regard to benchmark baseline of 0.88%. We have used the aforementioned predictions to determine price trends, which successfully outperformed the random walk baseline accuracy of 50%. JEL Classification: C45, C58, G11, G14

Uncertainty about Managerial Horizon and Voluntary Disclosure

I examine the relation between investors’ uncertainty about managerial horizon and corporate voluntary disclosure. I argue that investors’ uncertainty about the manager’s short-term stock price concern works as a disclosure friction that allows for a partial disclosure equilibrium. When investors are uncertain about managers’ horizons, short-horizon managers can withhold bad news by pooling with long-horizon managers who are not motivated to disclose regardless of the content of the news, as they are largely indifferent to short-term stock prices. Based on this theoretical framework, I hypothesize that reducing investors’ uncertainty about managerial horizon reduces this disclosure friction, thereby pressuring short-horizon managers to provide more voluntary disclosure. I use the executive compensation disclosure mandate as an empirical setting that reduced investors’ uncertainty about managerial horizon. Employing a difference-in-differences research design, I find a significant increase in voluntary disclosure for treated firms relative to control firms, largely driven by firms with short-horizon managers.

Prediction of Short-Term Stock Price Trend Based on Multiview RBF Neural Network.

Stock price prediction is important in both financial and commercial domains, and using neural networks to forecast stock prices has been a topic of ongoing research and development. Traditional prediction models are often based on a single type of data and do not account for the interplay of many variables. This study covers a radial basis neural network modeling technique with multiview collaborative learning capabilities for incorporating the impacts of numerous elements into the prediction model. This research offers a multiview RBF neural network prediction model based on the classic RBF network by integrating a collaborative learning item with multiview learning capabilities (MV-RBF). MV-RBF can make full use of both the internal information provided by the correlation between each view and the distinct characteristics of each view to form independent sample information. By using two separate stock qualities as input feature information for trials, this study proves the viability of the multiview RBF neural network prediction model on a real data set.

Short-Term Stock Price Forecasting Based on an SVD-LSTM Model

Stocks are the key components of most investment portfolios. The accurate forecasting of stock prices can help investors and investment brokerage firms make profits or reduce losses. However, stock forecasting is complex because of the intrinsic features of stock data, such as nonlinearity, long-term dependency, and volatility. Moreover, stock prices are affected by multiple factors. Various studies in this field have proposed ways to improve prediction accuracy. However, not all of the proposed features are valid, and there is often noise in the features—such as political, economic, and legal factors—which can lead to poor prediction results. To overcome such limitations, this study proposes a forecasting model for predicting stock prices in a short-term time series. First, we use singular value decomposition (SVD) to reconstruct the features of stock data, eliminate data noise, retain the most effective data features, and improve the accuracy of prediction. We then model the time-series stock data based on a long short-term memory (LSTM) model. We compare our proposed SVD-LSTM model with four state-of-the-art methods using real-world stock datasets from two Chinese banks: Ping an Bank and Shanghai Pudong Development Bank. The experimental results show that the proposed method can improve the accuracy of stock price predictions.

An Economic Forecasting Method Based on the LightGBM-Optimized LSTM and Time-Series Model.

Stock price prediction is very important in financial decision-making, and it is also the most difficult part of economic forecasting. The factors affecting stock prices are complex and changeable, and stock price fluctuations have a certain degree of randomness. If we can accurately predict stock prices, regulatory authorities can conduct reasonable supervision of the stock market and provide investors with valuable investment decision-making information. As we know, the LSTM (Long Short-Term Memory) algorithm is mainly used in large-scale data mining competitions, but it has not yet been used to predict the stock market. Therefore, this article uses this algorithm to predict the closing price of stocks. As an emerging research field, LSTM is superior to traditional time-series models and machine learning models and is suitable for stock market analysis and forecasting. However, the general LSTM model has some shortcomings, so this paper designs a LightGBM-optimized LSTM to realize short-term stock price forecasting. In order to verify its effectiveness compared with other deep network models such as RNN (Recurrent Neural Network) and GRU (Gated Recurrent Unit), the LightGBM-LSTM, RNN, and GRU are respectively used to predict the Shanghai and Shenzhen 300 indexes. Experimental results show that the LightGBM-LSTM has the highest prediction accuracy and the best ability to track stock index price trends, and its effect is better than the GRU and RNN algorithms.

Stock Trend Prediction Algorithm Based on Deep Recurrent Neural Network

With the return of deep learning methods to the public eye, more and more scholars and industry researchers have tried to start exploring the possibility of neural networks to solve the problem, and some progress has been made. However, although neural networks have powerful function fitting ability, they are often criticized for their lack of explanatory power. Due to the large number of parameters and complex structure of neural network models, academics are unable to explain the predictive logic of most neural networks, test the significance of model parameters, and summarize the laws that humans can understand and use. Inspired by the technical analysis theory in the field of stock investment, this paper selects neural network models with different characteristics and extracts effective feature combinations from short‐term stock price fluctuation data. In addition, on the basis of ensuring that the prediction effect of the model is not lower than that of the mainstream models, this paper uses the attention mechanism to further explore the predictive K‐line patterns, which summarizes usable judgment experience for human researchers on the one hand and explains the prediction logic of the hybrid neural network on the other. Experiments show that the classification effect is better using this model, and the investor sentiment is obtained more accurately, and the accuracy rate can reach 85%, which lays the foundation for the establishment of the whole stock trend prediction model. In terms of explaining the prediction logic of the model, it is experimentally demonstrated that the K‐line patterns mined using the attention mechanism have more significant predictive power than the general K‐line patterns, and this result explains the prediction basis of the hybrid neural network.

Limit Order Book and Short-term Stock Price Movement Predictability: Evidence from Tehran Stock Exchange

هدف: دفتر سفارشات محدود یکی از ابزارهای بازارهای مالی است که با نشان‌دادن حجم و قیمت پیشنهادی سفارشات خرید و فروش، به کشف قیمت دارایی کمک می‌کند. در این پژوهش با بررسی دفتر سفارشات محدود در بورس اوراق بهادار تهران به دو پرسش پاسخ داده می‌شود: 1. آیا اطلاعات موجود در دفتر سفارشات محدود رفتار قیمت سهام در آیندۀ کوتاه‌مدت را پیش‌بینی می‌کند؟ 2. آیا افزایش پله‌های در معرض نمایش عموم از سه پله به پنج پله در بورس اوراق بهادار تهران به معامله‌گران برای کشف قیمت سهام کمک می‌کند؟ روش: در راستای هدف فوق، از سه رگرسیون مختلف استفاده می‌شود که هر یک به شیوۀ متفاوتی اطلاعات حجم و قیمت سفارشات دو سمت عرضه و تقاضا را اندازه‌گیری و با این اطلاعات توانایی پیش‌بینی رفتار کوتاه‌مدت قیمت سهم را آزمون می‌کنند. نتایج: براساس نتایج حاصل، در بورس اوراق بهادار تهران، دفتر سفارشات محدود حاوی اطلاعاتی است که با آن حرکت قیمت سهام در آیندۀ کوتاه‌مدت پیش‌بینی می‌شود؛ همچنین افزایش پله‌های در معرض نمایش عموم از سه پله به پنج پله در بورس اوراق بهادار تهران به معامله‌گران برای افزایش شفافیت قبل از معامله و کشف قیمت کمک می‌کند.