Search

We show current market practices relating to odd-lot quotes create a large "inside" market where better prices routinely exist relative to the National Best Bid or Offer. We show that odd-lot quotes play a price discovery role, and these quotes provide valuable information to traders with access to proprietary data feeds. Using a XGBoost machine learning algorithm that uses odd-lot data to predict future prices, we demonstrate a simple and profitable trading strategy. We argue the SEC's proposed round-lot redefinition reduces—but does not eliminate—the high incidence of superior odd-lot quotes within the NBBO. [ABSTRACT FROM AUTHOR]

Accurate stock price forecasting is essential for making smart investing choices. In the context of the Egyptian stock market, this study examines the predictive capabilities of several machine learning and deep learning models for stock price prediction. Five different datasets with historical stock price information from significant Egyptian companies are used in the study methods such as Random Forest, Linear Regression, LSTM, and Bi-LSTM which were employed and evaluated using performance metrics including Mean Squared Error (MSE), Mean Absolute Error (MAE), and R-Squared. Among these, the Bi-LSTM model consistently delivered the most accurate price forecasts due to its superior ability to capture complex patterns and relationships inherent in stock market data. Additionally, statistical models ARIMA and GARCH were implemented for comparative purposes, but the machine learning and deep learning models outperformed these traditional approaches. This study contributes to a deeper understanding of stock price behavior in the Egyptian market, providing valuable insights for financial analysts and investors. [ABSTRACT FROM AUTHOR]

The stock market is regarded as volatile, complex, tumultuous, and dynamic. Forecasting stock performance has proven to be a challenging endeavour due to its increasing need for investment and growth prospects. At the forefront of machine learning, deep learning models facilitate the straightforward and efficient exploration and identification of optimal stocks, the hybrid forecasting models (LSTM and ARIMA) are used in the prediction of stock increase. This paper incorporated the MCDM technique to determine the optimal stocks for investment. The Analytic Hierarchy Process (AHP) is used to assign weights to various financial factors. These weights are then used by the Technique for Order Preference by Similarity to Ideal solution (TOPSIS) technique, which is a component Multi Criteria Decision Making method (MCDM), to compute and rank the optimal stocks for investment. Stock analysis involves considering numerous criteria and sub-criteria, which might lead to an unsuitable answer. To address this uncertainty, we utilize Neutrosophic Treesoft sets, which primarily handle numerous criteria, sub-criteria, and an increased number of sub-sub-criteria. Given a larger number of criteria, we will be capable of providing a precise solution to the problem. Furthermore, the definitions of fuzzy treesoft sets and neutrosophic treesoft sets have been presented for the first time. A plotly graph is generated to compare the real and projected stock prices for all the equities. All these are implemented using the program language python, which seems to be simple and easily understandable when compared to the other programming languages like Julia, MATLAB and so on. This hybrid methodology facilitates the forecast of stock prices, the ranking of stocks based on several financial and non-financial factors using AHP and TOPSIS, and the visualization of the outcomes. [ABSTRACT FROM AUTHOR]

This paper proposes a new approach to making stock price movement prediction better serve the trading strategy by embedding the strategy into deep learning. The trading strategy is incorporated into the model's training loss function to obtain a higher return under the given trading strategy. To better embed the strategy into the learning model, we also adopt the data of the same day as a batch instead of fixed-size data as a batch. In other words, each parameter update is based on one day's data. We used the data from the Chinese stock market for an empirical experiment, and according to the characteristics of the Chinese stock market, we made some special treatments. The empirical experiment results show that this method improves the trading strategy's performance compared with the benchmark. [ABSTRACT FROM AUTHOR]

Since the beginning of stock trading, investors and researchers have tried to find effective ways to predict the direction of stock prices on the next day. However, predicting stock prices is a hard task because there exist many factors that may affect the next day's stock prices. Recently, investors and researchers have adopted machine learning techniques with technical indicator analysis to make prediction. But the prediction accuracy is unsatisfactory. Thus, this study aims to examine the problem of stock price prediction with time series and proposes an effective way to filter out the datasets, which consists of three key steps: First, a time series model with long-short-term memory (LSTM) was used to identify the possible problems and solve them in the process of stock price prediction. Second, the results of LSTM were adopted to influence the stock trend prediction by a variety of machine learning techniques, including random forest, support vector machine, light gradient boosting machine (LightGBM). Third, a novel method was proposed to select suitable datasets through buying or selling. Hereby, FTSE TWSE Taiwan 50 Index stocks were used as training and testing datasets, respectively. Some important days were selected for prediction and decision making. The experimental results show that the highest prediction accuracy of 86% and the average prediction accuracy of 82% have been obtained. Consequently, when comparing to other existing methods, the accuracy of predicting stock price trend with our proposed approach has been significantly improved. Reference No.: 2024-UAAI-0010R1/243667820 Subject Area: Intelligent Investment System [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel approach to improving forecasts of stock market indexes by considering common stock prices as hierarchical time series, combining clustering with forecast reconciliation. We propose grouping the individual stock price series in various ways including via metadata and using unsupervised learning techniques. The proposed approach is applied to the Dow Jones Industrial Average Index and the Standard & Poor 500 Index and their component stocks, and the results obtained with different grouping approaches are compared. The results empirically demonstrate that the combined use of clustering and reconciliation improves the forecast accuracy of the stock market indexes and their constituents. [ABSTRACT FROM AUTHOR]

As an important reflection of the national economy system, stock market is closely related to the development of a country, which has received widespread attention of researchers in the economics. With the daily trading of the stock market, stock price forecasting has gradually been one of the common concerns in the economic analysis. Compared with traditional forecasting task, the stock price is interval data which can be handled by interval data regression or multi-output regression. Previous stock forecasting merely considers the stock price in homogeneous scenarios. However, the price distributions from different stocks may be heterogeneous. It is a challenging task to analyze the relationship between different stocks which follow heterogeneous distributions. In order to forecast stocks in heterogeneous scenarios, this paper introduces multi-output transfer learning into stock price forecasting. Compared with traditional regression or multi-output regression models, the multi-output transfer regression can predict opening price, closing price, highest price and lowest price of stocks and utilize source domain of a known stock to enhance the prediction of target stock price which may have limited known data in training set. The experimental results on four public market indices demonstrate the effectiveness of multi-output transfer regression for stock price forecasting. [ABSTRACT FROM AUTHOR]

Recently, a substantial body of literature in finance has implemented deep learning algorithms as predicting approaches. The principal merit of these methods is the ability to approximate any nonlinear and linear behaviors without understanding the data generation process, making them suitable for predicting stock market movement. This paper explores deep learning approaches to forecast stock price movement in the Hong Kong stock market. The forecasting performance of a temporal convolutional network (TCN) approach and several recurrent neural network (RNN) models is compared. The results show that the TCN can outperform all compared RNN models. Further parameter tuning results also show the superiority of the TCN approach. In addition, we demonstrate that a profitable strategy can be built based on the forecasting results of the proposed model. [ABSTRACT FROM AUTHOR]

Objectives: Certainty in investment decisions are the main tools for evaluation of stock markets. Every investor will have to identify the future stock prices before developing investment strategy so that their returns will be boosted. Due to the nonlinear, complicated, volatile, and dynamic character of stock data, forecasting stock prices is challenging. This study aims to address these challenges and improve prediction accuracy through advanced modelling techniques. Methodology: We proposed a hybrid neural network that combines Bidirectional Gated Recurrent Units (BiGRU) with one-dimensional Convolutional Neural Networks (CNNs). Experiments were conducted on five stock price datasets, including three individual stock items and two performance indices of stock markets. The evaluation metrics included Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). Findings: The proposed hybrid model achieved the lowest MAE for individual datasets, ranging from 1.747 to 0.357. Additionally, our experiments demonstrated a 42–91% reduction in RMSE compared to standard CNN and GRU-based approaches, reflecting significantly improved prediction precision. Implications: The results indicate that the hybrid Bidirectional GRU and CNN model is effective for precise stock price prediction, offering enhanced reliability for investment decision-making. This model can support investors and analysts in navigating the complexities of the stock market. Conclusions: The hybrid Bidirectional GRU and CNN model demonstrates superior performance in stock price prediction compared to traditional methods. It holds promise for advanc- ing predictive analytics in financial markets, contributing to better investment strategies and reduced market risks. [ABSTRACT FROM AUTHOR]

Predicting stock price movements remains a major challenge in time series analysis. Despite extensive research on various machine learning techniques, few models have consistently achieved success in automated stock trading. One of the main challenges in stock price forecasting is that the optimal model changes over time due to market dynamics. This paper aims to predict stock prices using automated reinforcement learning algorithms and to analyse their efficiency compared with conventional methods. We automate DQN models and their variants, known for their adaptability, by continuously retraining them using recent data to capture market dynamics. We demonstrate that our dynamic models improve the accuracy of predicting the directions of various DAX stocks from 50.00% to approximately 60.00%, compared with conventional methods. Additionally, we conclude that dynamic models should be updated in response to shifts rather than at fixed intervals. [ABSTRACT FROM AUTHOR]

In the field of stock price forecasting, we are actively seeking to integrate various information to more accurately grasp market dynamics. Although historical stock prices and financial news have been widely used in previous studies, it is relatively rare to find research considering news-based, technical, and chip factors simultaneously and evaluating their combined effect. In this study, we innovatively propose a multi-kernel model that not only combines news-based, technical, and chip factor analysis but also utilizes market data provided by the Taiwan Stock Exchange, including institutional trading situations and stock price technical indicators. The aim is to further enhance the prediction accuracy of stock price dynamics. Based on the frequency of word occurrences, we design a new discriminant index to extract features highly correlated with stock prices from financial news. The empirical results show that our multi-kernel model significantly surpasses the single-kernel model in prediction accuracy. However, we also find that although financial news is somewhat correlated with stock price dynamics, information such as chip factors and stock price technical indicators contribute more significantly in our model. This further validates that our multi-kernel learning algorithm can effectively handle multifaceted data sources and give appropriate weights according to the importance of each data point, thereby enhancing the comprehensiveness of prediction. Through this research, we hope to bring new perspectives and inspirations to the field of stock price forecasting. [ABSTRACT FROM AUTHOR]

Predicting the stock market remains a difficult field because of its inherent volatility. With the development of artificial intelligence, research using deep learning for stock price prediction is increasing, but the importance of applying a prediction system consisting of preparing verified data and selecting an optimal feature set is lacking. Accordingly, this study proposes a GA optimization-based deep learning technique (CNN-LSTM) that predicts the next day's closing price based on an artificial intelligence model to more accurately predict future stock values. In this study, CNN extracts features related to stock price prediction, and LSTM reflects the long-term history process of input time series data. Basic stock price data and technical indicator data for the last 20 days prepare a data set to predict the next day's closing price, and then a CNN-LSTM hybrid model is set. In order to apply the optimal parameters of this model, GA was used in combination. The Korea Stock Index (KOSPI) data was selected for model evaluation. Experimental results showed that GA-based CNN-LSTM has higher prediction accuracy than single CNN, LSTM models, and CNN-LSTM model. This study helps investors and policy makers who want to use stock price fluctuations as more accurate predictive data using deep learning models. [ABSTRACT FROM AUTHOR]

Owing to the dynamic nature of the financial industry, determining accurate stock market forecasts remains a significant challenge. Traditional forecasting methods often struggle to capture the intricate and volatile dynamics of stock price movements. Similarly numerous strategies for stock market prediction have been presented, precise prediction in this field still requires attention. Based on this insight, a novel sequential training model is proposed by adopting the optimal feature selection procedure. In order to determine stock price predictions, primarily financial Nifty data is obtained from the corresponding source. After acquiring financial data, the feature extraction phase is used to extract features from fundamental analysis, such as the Relative Strength Index, Rate of Change, Average True Range, and Exponential Moving Average. Additionally, statistical characteristics such as mean, standard deviation, variance, skewness, and kurtosis are derived from the stock market data. In order to select parameters, the fitness dependent randomised tunicate swarm optimization technique is utilized after the features have been retrieved. Feature selection improves the deep learning process and increases prediction capability by selecting the most important variables and eliminating irrelevant features. A novel sequential training technique is introduced aimed at forecasting stock market trends by leveraging the chosen features. The suggested approach undergoes comprehensive testing, evaluating its predictive capability using accuracy, precision, and recall metrics, implemented towards enhancing future stock price forecasts. [ABSTRACT FROM AUTHOR]

Our study aims to investigate the interdependence between international stock markets and sentiments from financial news in stock forecasting. We adopt the Temporal Fusion Transformers (TFT) to incorporate intra and inter-market correlations and the interaction between the information flow, i.e. causality, of financial news sentiment and the dynamics of the stock market. The current study distinguishes itself from existing research by adopting Dynamic Transfer Entropy (DTE) to establish an accurate information flow propagation between stock and sentiments. DTE has the advantage of providing time series that mine information flow propagation paths between certain parts of the time series, highlighting marginal events such as spikes or sudden jumps, which are crucial in financial time series. The proposed methodological approach involves the following elements: a FinBERT-based textual analysis of financial news articles to extract sentiment time series, the use of the Transfer Entropy and corresponding heat maps to analyze the net information flows, the calculation of the DTE time series, which are considered as co-occurring covariates of stock Price, and TFT-based stock forecasting. The Dow Jones Industrial Average index of 13 countries, along with daily financial news data obtained through the New York Times API, are used to demonstrate the validity and superiority of the proposed DTE-based causality method along with TFT for accurate stock Price and Return forecasting compared to state-of-the-art time series forecasting methods. [ABSTRACT FROM AUTHOR]

In recent years, uncertain fractional differential equations was proposed for the description of complex uncertain dynamic systems with historical characteristics. For wider applications of uncertain fractional differential equations, researches on parameter estimation for uncertain fractional differential equations are of great importance. In this paper, based on the thought of least squares estimation and uncertain hypothesis test, an algorithm of parameter estimation for uncertain fractional differential equations is discussed. Finally, we consider the application of uncertain fractional differential equations based model to predict the forecasting stock price of three major indexes of U.S. stocks and make a comparison between uncertain fractional differential equations, uncertain differential equations and stochastic differential equations. [ABSTRACT FROM AUTHOR]

The stock market serves as a macroeconomic indicator, and stock price forecasting aids investors in analysing market trends and industry dynamics. Several deep learning network models have been proposed and extensively applied for stock price prediction and trading scenarios in recent times. Although numerous studies have indicated a significant correlation between market sentiment and stock prices, the majority of stock price predictions rely solely on historical indicator data, with minimal effort to incorporate sentiment analysis into stock price forecasting. Additionally, many deep learning models struggle with handling the long-distance dependencies of large datasets. This can cause them to overlook unexpected stock price fluctuations that may arise from long-term market sentiment, making it challenging to effectively utilise long-term market sentiment information. To address the aforementioned issues, this investigation suggests implementing a new technique called Long-term Sentiment Change Enhanced Temporal Analysis (LEET) which effectively incorporates long-term market sentiment and enhances the precision of stock price forecasts. The LEET method proposes two market sentiment index estimation methods: Exponential Weighted Sentiment Analysis (EWSA) and Weighted Average Sentiment Analysis (WASA). These methods are utilized to extract the market sentiment index. Additionally, the study proposes a Transformer architecture based on ProbAttention with rotational position encoding for enhanced positional information capture of long-term emotions. The LEET methodology underwent validation using the Standard & Poor's 500 (SP500) and FTSE 100 indices. These indices accurately reflect the state of the US and UK equity markets, respectively. The experimental results obtained from a genuine dataset demonstrate that this method is superior to the majority of deep learning network architectures when it comes to predicting stock prices. [ABSTRACT FROM AUTHOR]

This paper explores into stock market analysis using computer models to predict stock price changes, particularly focusing on the AAPL dataset from Apple Inc. Accurate stock forecasts are vital for informed investment decisions. By comparing different models—Multilayer Perceptron (MLP), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU)—the study offers a comprehensive performance analysis of deep learning approaches. The use of different deep learning architectures allowed us to capture different aspects of the stock price data and assess their effectiveness in making predictions. The project's findings would enable us to make informed decisions about which model to choose for future stock price prediction tasks, benefiting traders, investors, and other stakeholders in the financial domain. LSTM exhibited the best predictive capability, capturing intricate patterns due to its ability to handle long-term dependencies GRU also performed well. However, the MLP model didn't do as well because it couldn't grasp the complex patterns in the data as effectively as the other two models. So, for forecasting stock prices, the LSTM model proved to be the most accurate and reliable choice. These findings offer valuable insights for financial practitioners aiming to enhance stock price prediction using deep learning techniques, aiding in smarter investment strategies. [ABSTRACT FROM AUTHOR]

Traders and investors find predicting stock market values an intriguing subject to study in stock exchange markets. Accurate projections lead to high financial revenues and protect investors from market risks. This research proposes a unique filtering-combination approach to increase forecast accuracy. The first step is to filter the original series of stock market prices into two new series, consisting of a nonlinear trend series in the long run and a stochastic component of a series, using the Hodrick-Prescott filter. Next, all possible filtered combination models are considered to get the forecasts of each filtered series with linear and nonlinear time series forecasting models. Then, the forecast results of each filtered series are combined to extract the final forecasts. The proposed filtering-combination technique is applied to Pakistan's daily stock market price index data from January 2, 2013 to February 17, 2023. To assess the proposed forecasting methodology's performance in terms of model consistency, efficiency and accuracy, we analyze models in different data set ratios and calculate four mean errors, correlation coefficients and directional mean accuracy. Last, the authors recommend testing the proposed filtering-combination approach for additional complicated financial time series data in the future to achieve highly accurate, efficient and consistent forecasts. [ABSTRACT FROM AUTHOR]

This paper aims to construct a trader model tailored to offer individualized investment strategies for users engaged in the US stock market. The approach taken involves two key aspects: forecasting stock prices and discerning users' personality traits to formulate optimal trading recommendations. The framework is realized through the integration of neural networks and the Moving Averages algorithm. This combined approach allows forecasting upcoming changes in stock prices and generating appropriate trading signals. Complementing this, a user risk assessment is administered, and its outcomes are leveraged to furnish personalized trading advice, offering invaluable support for informed decision-making amid intricate real-time scenarios. By synergizing predictive modeling and user-specific insights, this comprehensive system contributes to enhancing trading precision and user empowerment. This work can be useful in decision making for a wide range of stock market participants, as well as for institutions specialized for this area of operation. [ABSTRACT FROM AUTHOR]

This study investigates how the Global Financial Crisis has affected the weak-form Efficient Market Hypothesis (EMH) on the stock prices of sixteen nations throughout the globe based on a suite of Fourier unit root tests. Considering the smooth structural breaks, we employed the Fourier-based unit root tests to assess the weak-form efficient market hypothesis. We used multiple frequency datasets of global financial stock market indexes that span over 20 years to have comprehensive analysis and robustness in the results. The study is performed from distinct sub-sample periods of the global financial crisis, including the pre-crisis period (2000–2007), the crisis and post-crisis period (2008–2020), and the overall sample period (2000–2020). We observed seven stock markets in the total sample period and twelve in the pre-crisis period, which were weak-form efficient across different frequency data sets. During the crisis and post-crisis period, just four out of sixteen stock market indexes were found to be weak in efficiency based on Fourier unit root tests. Given the superior properties of the Fourier unit root tests, this study reiterates that investors may receive a stream of arbitrage benefits in all markets due to the inefficiency of these countries. We offer investment implications that enable forecasting future stock price changes based on past performance and creating trading methods that produce anomalous profits. [ABSTRACT FROM AUTHOR]

Stock market movements, stocks, and exchange rates are the primary subjects and active areas of research for analysts and researchers. The stock prices is being influenced by financial news, which has been demonstrated to be an important element in fluctuating stock prices. Furthermore, previous research mostly evaluated shallow characteristics and ignored functional relationships between words in a sentence. Many studies have attempted to analyse the sentiment of investors' reactions to corresponding news occurrences. In this paper, we proposed a unique methodology for predicting the stock prices trend by using both stock features and financial news. The proposed methodology is the hybrid Recurrent Neural-Network (HyRNN) architecture. This design includes Bidirectional Long Short-Term Memory (Bi-LSTM) on top of the Gated Recurrent Unit (GRU) and stacked Long Short-Term Memory (sLSTM). The performance of HyRNN for forecasting stock price can be considerably improved by mixing the sentiments of financial news with the features of stock as an input to the model. In comparison to earlier statistical models, the suggested model increases the analysing capability of GRU, LSTM, RNN, and proposed models independently. The findings of this study shows the deep learning (DL) approach has high potential for predicting stock price changes. [ABSTRACT FROM AUTHOR]

The prediction of stock prices has long been a captivating subject in academic research. This study aims to forecast the prices of prominent stocks in five key industries of the Chinese A-share market by leveraging the synergistic power of deep learning techniques and investor sentiment analysis. To achieve this, a sentiment multi-classification dataset is for the first time constructed for China's stock market, based on four types of sentiments in modern psychology. The significant heterogeneity of sentiment changes in the sectors' leading stock markets is trained and mined using the Bi-LSTM-ATT model. The impact of multi-classification investor sentiment on stock price prediction was analyzed using the CNN-Bi-LSTM-ATT model. It finds that integrating sentiment indicators into the prediction of industry leading stock prices can enhance the accuracy of the model. Drawing upon four fundamental sentiment types derived from modern psychology, our dataset provides a comprehensive framework for analyzing investor sentiment and its impact on forecasting the stock prices of China's A-share market. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to perform Shariah review of Brownian motion that is used for prediction of Islamic stock prices and their volatility. Design/methodology/approach: It uses the Shariah compliant development model guidelines to review the Brownian motion and its applications. Findings: The model of Brownian motion does not involve any variable that renders it non-Shariah compliant; neither all applications of Brownian motion are Shariah compliant. Because the model is based on stochastic properties that involve randomness, therefore the issue of gharar takes the utmost important to handle in the applications of the model. The results need to be analyzed strictly in accordance with the Shariah whether they create any element of gharar or uncertainty in case of expected price and volatility estimates. Research limitations/implications: The research suffers from the limitation that it analyses only one model of physics, i.e. Brownian motion model from Shariah perspective. Practical implications: The research opens an area for Shariah analysis of results generated from the application of advanced models of physics on matters related to Islamic financial markets. Originality/value: The originality of this study stems from the fact that to the best of the authors' knowledge, it is the first study that extends Shariah guidelines into Financial physics for making the foundations of Islamic econophysics. [ABSTRACT FROM AUTHOR]

This study introduces the Spacetimeformer model, a novel approach for predicting stock prices, leveraging the Transformer architecture with a time–space mechanism to capture both spatial and temporal interactions among stocks. Traditional Long–Short Term Memory (LSTM) and recent Transformer models lack the ability to directly incorporate spatial information, making the Spacetimeformer model a valuable addition to stock price prediction. This article uses the ten minute stock prices of the constituent stocks of the Taiwan 50 Index and the intraday data of individual stock on the Taiwan Stock Exchange. By training the Timespaceformer model with multi-time-step stock price data, we can predict the stock prices at every ten minute interval within the next hour. Finally, we also compare the prediction results with LSTM and Transformer models that only consider temporal relationships. The research demonstrates that the Spacetimeformer model consistently captures essential trend changes and provides stable predictions in stock price forecasting. This article proposes a Spacetimeformer model combined with daily moving windows. This method has superior performance in stock price prediction and also demonstrates the significance and value of the space–time mechanism for prediction. We recommend that people who want to predict stock prices or other financial instruments try our proposed method to obtain a better return on investment. [ABSTRACT FROM AUTHOR]

The achievement of profits when trading on the stock markets is conditioned by a quality analytical forecast of the development of stock prices in the coming period. This research attempts to compare the results of the ARIMA model and the ARIMA-GARCH model to forecast the development of stock prices on a sample of selected stocks from the Czech, German, Austrian, Polish and British markets. The 4 most liquid titles from each of the above-mentioned markets were selected for the sample of analyzed stocks. Available daily closing stock price data, mostly from the period 2000-2022, were used for the analysis. Research has shown that for most of the analyzed titles, it is more appropriate to use the ARIMA-GARCH model, which better captures variability for this data than just the ARIMA model. The quality of the selected model is evaluated by autocorrelation, heteroskedasticity tests, and Theil's inequality coefficient. [ABSTRACT FROM AUTHOR]

Forecasting the stock market has always been one of the challenges for stock market participants to make more profit. Among the problems of stock price forecasting, we can mention its dynamic nature, complexity and its dependence on factors such as the governing system of countries, emotions, economic conditions, inflation, and so on. In recent years, many studies have been conducted to predict the capital stock market using traditional techniques, machine learning algorithms and deep learning. The lower our forecast stock error, the More we can reduce investment risk and increase profitability. In this paper, we present a machine learning (ML) approach called support vector machine (SVM) that can be taught using existing data. SVM extracts knowledge between data and ultimately uses this knowledge to predict new stock data. We have also aimed to select the best SVM method parameters using the particle swarm optimization (PSO) algorithm to prevent over-fitting and improve forecast accuracy. Finally, we compare our proposed method (SVM-PSO) with several other methods, including support vector machine, artificial neural network (ANN) and LSTM. The results show that the proposed algorithm works better than other methods and in all cases, its forecast accuracy is above 90%. [ABSTRACT FROM AUTHOR]

In the past, the bottom-up study of financial stock markets relied on first-generation multi-agent systems (MAS) , which employed zero-intelligence agents and often required the additional implementation of so-called noise traders to emulate price formation processes. Nowadays, thanks to the tools developed in cognitive science and machine learning, MAS can quantitatively gauge agent learning, a pivotal element for information and stock price estimation in finance. In our previous work, we therefore devised a new generation MAS stock market simulator , which implements two key features: firstly, each agent autonomously learns to perform price forecasting and stock trading via model-free reinforcement learning ; secondly, all agents ' trading decisions feed a centralised double-auction limit order book, emulating price and volume microstructures. Here, we study which trading strategies (represented as reinforcement learning policies) the agents learn and the time-dependency of their heterogeneity. Our central result is that there are more ways to succeed in trading than to fail. More specifically, we find that : i- better-performing agents learn in time more diverse trading strategies than worse-performing ones, ii- they tend to employ a fundamentalist, rather than chartist, approach to asset price valuation, and iii- their transaction orders are less stringent (i.e. larger bids or lower asks). [ABSTRACT FROM AUTHOR]

Stock price trend forecasting is an important and challenging problem, and effective forecasting will help to improve investment returns and reduce investment risks. Previous studies are usually limited to modeling specific stocks, while the information contained in a single stock is limited and independent, so exploring the common patterns of stock price trend changes is a worthwhile direction of research. Based on this, this paper proposes the Stocks-BERT framework, which aims to investigate the semantic commonalities contained in the stock market. The framework is mainly divided into three modules: firstly, this paper proposes Ranking division and Base mapping to turn daily trading data into "words", so that continuous trading data forms "sentences", and constructs the "BERT training sentences" for training. Then, in the BERT pre-training stage, the Steps training method is used for the input data of 987 stocks (S&P 500 and CCTV Finance 500) to make the model converge faster and improve the effect. Finally, in the fine-tuning stage, it is proposed to use the word vectors extracted from the Embedding Layer to optimize the classifier in the output layer to adapt to individual stock characteristics. The results show that the Stocks-BERT framework model proposed in this paper is superior to the state-of-the-art models on two publicly available datasets (ACL18 and KDD17) and 14 stock market index datasets (INDEX14). The accuracy can reach more than 60% on individual stocks and stock market indexes, and it shows good generalization. In addition, it is found that even though the Chinese and American stock markets are in different economic environments, the models trained using Chinese stock market data and American stock market data show similar results in terms of outcome performance, indicating that the two markets have similar expressive power. • A new framework that shows the use of LLM models in the stock prediction. • Tokenization of stock data can filter the high-frequency noise of stock data. • BERT model can quickly converge by the Steps training method. • Using the modified BERT model to optimize the effect. [ABSTRACT FROM AUTHOR]

Stock price forecasting has been an important topic for investors, researchers, and analysts. In this paper, a prediction model of Dynamic Gaussian Deep Belief Network (DGDBN) is proposed. Generally, the network structure of traditional Deep Belief Network (DBN) determines the performance of its time series prediction. Most previous research uses artificial experience to adjust the network structure, it is difficult to ensure performance and time efficiency by constantly trying. In addition, the accuracy of the traditional DBN stacked by binary Restricted Boltzmann Machines(RBM) needs to be improved when solving the time series problem. The DGDBN designed in this paper contains two points: The first point is to add Gaussian noise to the RBM. The second point is to realize the increase or decrease branch algorithm of hidden layer structure according to the connection weights and average percentage error (MAPE). Finally, the forecast for the stocks of United Technologies Corporation and Unisys Corp, DGDBN is compared with DBN and LSTM. The root means square error (RMSE) increases by 15% and 65%. The interesting thing we found is that the number of neurons in the last layer of the DGDBN network has a greater effect than other layers. [ABSTRACT FROM AUTHOR]

The research objective of this article is to train a computer (agent) with market information data so it can learn trading strategies and beat the market index in stock trading without having to make any prediction on market moves. The approach assumes no trading knowledge, so the agent will only learn from conducting trading with historical data. In this work, we address this task by considering Reinforcement Learning (RL) algorithms for stock portfolio management. We first generate a three-dimension fuzzy vector to describe the current trend for each stock. Then the fuzzy terms, along with other stock market features, such as prices, volumes, and technical indicators, were used as the input for five algorithms, including Advantage Actor-Critic, Trust Region Policy Optimization, Proximal Policy Optimization, Actor-Critic Using Kronecker Factored Trust Region, and Deep Deterministic Policy Gradient. An average ensemble method was applied to obtain trading actions. We set SP100 component stocks as the portfolio pool and used 11 years of daily data to train the model and simulate the trading. Our method demonstrated better performance than the two benchmark methods and each individual algorithm without fuzzy extension. In practice, real market traders could use the trained model to make inferences and conduct trading, then retrain the model once in a while since training such models is time0consuming but making inferences is nearly simultaneous. [ABSTRACT FROM AUTHOR]

Machine learning for stock market prediction has recently been popular for identifying stock selection strategies and providing market insights. In this study, we adopted machine learning algorithms to analyze technical indicators, and Google Trends search terms based on the Thai stock market. This study uses three datasets, which are technical indicators, Google Trends search terms, and a combination of the two. The objectives were to study and identify the factors in stock selection, develop and evaluate portfolio selection models using keyword proxies from the three datasets mentioned, and compare the performance of the selected algorithms. In the prediction process, we discovered that the combination of technical indicators and Google Trends search terms while applying Logistic Regression, Random Forest, and Extreme Gradient Boosting (XGBoost) exhibited the highest ROC curves. For success prediction rate and annualized return, Random Forest and XGBoost were almost similar but still different. While XGBoost performs well during a period of market critical conditions (COVID-19), Random Forest performs marginally better than XGBoost during normal market conditions in terms of average success rate. [ABSTRACT FROM AUTHOR]

This paper predicts the two most common stock market exits — mergers and drops — using logit models based on firm-level variables and analyzes the returns of stocks that have high exit probabilities. Such analysis is important for investors given that frequent exits are partly responsible for the large US listing gap (Doidge et al., 2017). High merger probability stocks have positive 3-factor alphas and lower-than-average volatility. Firms with high drop probabilities have anomalously negative 3-, 4-, and 5-factor alphas between − 1. 8 % and − 4 % per month. Results are robust to controlling for the effects of skewness, volatility, and turnover on returns. [ABSTRACT FROM AUTHOR]

Financial data are a type of historical time series data that provide a large amount of information that is frequently employed in data analysis tasks. The question of how to forecast stock prices continues to be a topic of interest for both investors and financial professionals. Stock price forecasting is quite challenging because of the significant noise, non-linearity, and volatility of time series data on stock prices. The previous studies focus on a single stock parameter such as close price. A hybrid deep-learning, forecasting model is proposed. The model takes the input stock data and forecasts two stock parameters close price and high price for the next day. The experiments are conducted on the Shanghai Composite Index (000001), and the comparisons have been performed by existing methods. These existing methods are CNN, RNN, LSTM, CNN-RNN, and CNN-LSTM. The generated result shows that CNN performs worst, LSTM outperforms CNN-LSTM, CNN-RNN outperforms CNN-LSTM, CNN-RNN outperforms LSTM, and the suggested single Layer RNN model beats all other models. The proposed single Layer RNN model improves by 2.2%, 0.4%, 0.3%, 0.2%, and 0.1%. The experimental results validate the effectiveness of the proposed model, which will assist investors in increasing their profits by making good decisions. [ABSTRACT FROM AUTHOR]

A stock forecasting and trading system is a complex information system because a stock trading system needs to be analyzed and modeled using data science, machine learning, and artificial intelligence. Previous time series models have been widely used to forecast stock prices, but due to several shortcomings, these models cannot apply all available information to make a forecast. The relationship between stock prices and related factors is nonlinear and involves nonstationary fluctuations, and accurately forecasting stock prices is not an easy task. Therefore, this study used support vector machines (linear and radial basis functions), gene expression programming, multilayer perceptron regression, and generalized regression neural networks to calculate the importance of indicators. We then integrated the five indicator selection methods to find the key indicators. Next, we used long short-term memory (LSTM) and gated recurrent units (GRU) to build time series models for forecasting stock prices and compare them with the listing models. To evaluate the effectiveness of the proposed model, we collected six different stock market data from 2011 to 2019 to evaluate their forecast performance based on RMSE and MAPE metrics. It is worth mentioning that this study proposes two trading policies to evaluate trading profits and compare them with the listing methods, and their profits are pretty good to investors. After the experiments, the proposed time series model (GRU/LSTM combined with the selected key indicators) exhibits better forecast ability in fluctuating and non-fluctuating environments than the listing models, thus presenting an effective reference for stakeholders. [ABSTRACT FROM AUTHOR]

In this study, we apply a machine learning approach to try to anticipate supply costs. Expert systems are used efficiently to project supply rates. Projecting supply costs is meant to help financiers make better informed and focused financial decisions. We suggest a supply price forecast system that integrates mathematical characteristics, expert systems, and other external factors in order to increase supply projection accuracy and also provide satisfying careers. Stocks come in two different price ranges. The term "day trading," which refers to intraday trading, may be familiar to you. Most frequently, intraday traders keep their positions in safekeeping for a number of days, occasionally even for weeks or months. LSTMs are particularly adept at navigating challenges associated with series prediction because of their ability to retain historical information. This is pertinent to our situation since a supply's historical cost is a key factor in estimating its future rate. Even if it's just a test of our ability to anticipate a stock's true price, we can develop a model that will tell us whether a stock will surely increase in cost or decrease. [ABSTRACT FROM AUTHOR]

Stock prediction is a prominent and challenging topic of interest for both investors and researchers. With the introduction of Graph Convolutional Networks (GCNs) to financial data analysis, many researchers have attempted to use GCNs to exploit the interrelationships among stock data. However, a notable research gap remains in the application of GCNs to establish associations among transaction data, which inherently exhibit more stable and well-defined correlations. Hence, this study proposes a regularized ensemble framework with graph convolutional networks for stock price prediction. The framework employs multiple multi-graph convolutional networks to construct an ensemble graph convolutional network, elucidating spatiotemporal relationships within transaction data across various time scales. Additionally, the Variational Modal Decomposition (VMD) method is utilized to extract features from each dimensional sequence of the transaction data, enabling the capture of features across different time scales and mitigating non-stationarity and noise in the data. Furthermore, a regularization term incorporating trend accuracy is introduced to strike a balance between numerical precision and trend accuracy, thereby enhancing the overall model performance. Finally, this study presents a specialized investment strategy designed for stock price prediction. Our approach yields substantial improvements on SSE and DJIA datasets, with ACC and R 2 improving by over 15% and 10%, respectively, accompanied by reductions of more than 40% in RMSE, MAE, and MAPE compared to the baseline. These results underscore the effectiveness, robustness, and adaptability of our proposed methodology. Our codes and data can be accessed at https://github.com/WonderNothing/REGCN/. [Display omitted] • Predicting stock price using a regularized ensemble framework. • The ensemble framework can capture data relationships across different time scales. • Utilizing spatiotemporal correlations in trading data for stock price prediction. • Introducing a regularization term to balance numerical precision and trend accuracy. • Proposing a trading strategy to assess stock price prediction model performance. [ABSTRACT FROM AUTHOR]

In the realm of quantitative investing, predicting stock prices and developing effective trading strategies are paramount. The inherent randomness of the stock market, however, limits the precision of stock price predictions, thus undermining investment performance when these predictions are the sole basis for strategy. Nonetheless, forecasting future prices can offer invaluable insights for strategic models. When predictions are paired with well-designed strategies, they can augment investment returns. This paper proposes a novel approach to enhance investment returns by integrating Long Short Term Memory (LSTM) predictions with the Evolutionary Operating-weights (EOW) algorithmic strategy. The proposed method employs a multi-layer LSTM to forecast future stock prices, incorporating the predictions with real market data, subsequently deriving an operational strategy using the EOW algorithm. The results of this research indicate that this proposed methodology outperforms existing approaches. • Using stock feature factors containing price-related information for the LSTM model. • Proposing the evolutionary operating-weights algorithmic strategy. • Proposing a method to boost profit by integrating LSTM prediction with EOW strategy. [ABSTRACT FROM AUTHOR]

Post-1970, share issuance exhibits a strong cross-sectional ability to predict stock returns. This predictive ability is more statistically significant than the individual predictive ability of size, book-to-market, or momentum. Our finding is related to research that finds that long-run returns are associated with share repurchase announcements, seasoned equity offerings, and stock mergers, although our results remain strong even after exclusion of the data used in these studies. We estimate the issuance relation pre-1970 and find no statistically significant predictive ability for most holding periods. [ABSTRACT FROM AUTHOR]

Applying machine learning methods to forecast stock prices has been a topic of interest in recent years. However, a few studies have been reported based on generative adversarial networks (GANs) in this area, but their results are promising. While GANs are powerful generative models successfully applied in different areas, they suffer from inherent challenges such as training instability and mode collapse. Another primary concern is capturing correlations in stock prices. Therefore, the main challenges fall into two categories: capturing correlations and addressing the inherent problems of GANs. In this paper, we introduce a novel framework based on DRAGAN 1 1 Deep Regret Analytic Generative Adversarial Network. and feature matching for stock price forecasting, which improves training stability and alleviates mode collapse. We employ windowing to acquire temporal correlations by the generator and exploit conditioning on discriminator inputs to capture temporal correlations and correlations between prices and features. Experimental results on data from several stocks indicate that proposed method outperforms long short-term memory (LSTM) as a baseline method, as well as basic GANs and WGAN-GP 2 2 Wasserstein GAN – Gradient Penalty. as two different variants of GANs. [ABSTRACT FROM AUTHOR]

This study shows that past trading volume provides an important link between "momentum" and "value" strategies. Specifically, we find that firms with high (low) past turnover ratios exhibit many glamour (value) characteristics, earn lower (higher) future returns, and have consistently more negative (positive) earnings surprises over the next eight quarters. Past trading volume also predicts both the magnitude and persistence of price momentum. Specifically, price momentum effects reverse over the next five years, and high (low) volume winners (losers) experience faster reversals. Collectively, our findings show that past volume helps to reconcile intermediate-horizon "underreaction" and long-horizon "overreaction" effects. [ABSTRACT FROM AUTHOR]

The author comments on a paper by Lo, Mamaysky, and Wang (LWM) that evaluates several trading strategies employed by those who practice technical analysis (TA). LMW attempt to remove the subjective element involved in TA by employing objective standards, but even then they cannot avoid subjectivity on several levels. Although LWM suggest certain strategies may be profitable, the magnitude of this advantage is not markedly different from zero. Still, the pattern-recognition algorithms put forth by LWM help illuminate the topic of technical analysis and provide a basis for further inquiry.

Technical analysis, also known as "charting," has been a part of financial practice for many decades, but this discipline has not received the same level of academic scrutiny and acceptance as more traditional approaches such as fundamental analysis. One of the main obstacles is the highly subjective nature of technical analysis--the presence of geometric shapes in historical price charts is often in the eyes of the beholder. In this paper, we propose a systematic and automatic approach to technical pattern recognition using nonparametric kernel regression, and we apply this method to a large number of U.S. stocks from 1962 to 1996 to evaluate the effectiveness of technical analysis. By comparing the unconditional empirical distribution of daily stock returns to the conditional distribution-conditioned on specific technical indicators such as head-and-shoulders or double-bottoms--we find that over the 31-year sample period, several technical indicators do provide incremental information and may have some practical value. [ABSTRACT FROM AUTHOR]

The article presents information on stock price and annual earnings reports by 51 industrial corporations traded on the New York Stock Exchange during 1905-10. At the time, there were very little disclosure requirements or any other government regulation. The authors investigate how a change in dividends related to the stock price, while earnings statements showed a different relationship. Earnings decreases were associated with significant negative returns whereas significant positive contemporaneous returns accompanied earnings increases only for dividend-paying firms.

We analyze tests for long-run abnormal returns and document that two approaches yield well-specified test statistics in random samples. The first uses a traditional event study framework and buy-and-hold abnormal returns calculated using carefully constructed reference portfolios. Inference is based on either a skewness-adjusted t-statistic or the empirically generated distribution of long-run abnormal returns. The second approach is based on calculation of mean monthly abnormal returns using calendar-time portfolios and a time-series t-statistic. Though both approaches perform well in random samples, misspecification in nonrandom samples is pervasive. Thus, analysis of long-run abnormal returns is treacherous. [ABSTRACT FROM AUTHOR]

Investigates whether the stock market overreacts to extreme earnings by examining firms' stock returns over the 36 months subsequent to extreme earnings years. Minimal evidence of differential performance between poor earners and good earners of equal size; Evidence that support the claim that firm size is responsible for the overreaction phenomenon. This paper tests whether the stock market overreacts to extreme earnings, by examining firms' stock returns over the 36 months subsequent to extreme earnings years. While the poorest earners do outperform the best earners, the poorest earners are also significantly smaller than the best earners. When poor earners are matched with good earners of equal size, there is little evidence of differential performance. This suggests that size, and not investor overreaction to earnings, is responsible for the "overreaction" phenomenon, the tendency for prior period losers to outperform prior period winners in the subsequent period. [ABSTRACT FROM AUTHOR]