Stock Trend Prediction Research Articles

Improving stock trend prediction with pretrain multi-granularity denoising contrastive learning

Improving stock trend prediction with pretrain multi-granularity denoising contrastive learning

Stock trend prediction based on industry relationships driven hypergraph attention networks

Stock trend prediction based on industry relationships driven hypergraph attention networks

Using transformer in stock trend prediction

Large transformer model had achieved good results in many tasks, such as computer vision (CV) and natural language processing (NLP). However, in financial domains, the application of large deep learning models is rarely observed. Stock Trend Prediction (STP) is a task that using Limit Order Books (LOBs) to predict the future stock price trend by the sequence of historical limit order information, the trend can be Current works are mostly based on the structure of Convolutional Neural Network (CNN) + Recurrent Neural Networks (RNN). This structure is hard to parallel and cannot make full use of GPU resources. It is also difficult to increase the dimension to fit more complex data and performs poor when time sequence is long. Recently, some works proposed that CNN + Transformer model can also work is solving this task. This paper verifies that Transformer can be directly used into STP task and gain a good result, and proposes a novel Transformer-based model, Transformer-LOB, to enhance the basic transformer model performance. This model uses attention mechanisms to extract temporal information rather than using RNN, which utilizes the GPU effectively. Since all the feature extractions are based on transformer modules, the model is scalable and easy to parallel. Transformer-LOB is tested on FI-2010 LOB dataset and SZ-2015 LOB dataset, and outputs ideal results on both datasets.

Towards interpretable stock trend prediction through causal inference

With the emergence of artificial intelligence, deep learning techniques have been widely deployed in forecasting stock markets. However, existing deep-learning-based models for news-based forecasts of stock trends are mostly black-box and difficult to explain. The procedure by which how final predictions are made within models keeps unknown, making it hard to interpret why one prediction should be better than the other. To provide explanations on predictions, this paper proposes to inject causal inference into model procedures and causally interpret predictions. We first generate a causal graph from financial news, and then integrate the information in the causal graph into a neural network model for stock trend prediction. Moreover, in order to better extract keywords from financial news we introduce a novel keyword extraction method named Distinguishable Word Filtering by Kolmogorov–Smirnov Test (DWF-KST). The experiment results on five financial datasets demonstrate that not only our proposed model explicitly provides an interpretation of prediction results, but also outperforms the state-of-art methods. the achieved results boost predictions of S&P 500 2-category from 89.7% to 97.4%, 3-category from 77.4% to 82.5%, and 5-category from 61.5% to 71.6%. For the other two indexes, the performances of Dow index improve from 86.2% to 90.2% and Nasdaq index improve from 76.4% to 78.9%.

Dynamic graph construction via motif detection for stock prediction

Stock trend prediction is crucial for recommending high-investment value stocks and can strongly assist investors in making decisions. In recent years, the significance of stock relationships has been gradually recognized for trend prediction, and graph neural networks (GNNs) have been introduced to capture useful features from relationships. However, applying GNNs to stock relationship analysis still faces numerous challenges, including inappropriate distance algorithms, non-dynamic stock graphs, and over-fitting. To address these challenges, we propose a dynamic graph construction module. The module offers the following advantages: (1) A dynamic graph construction module is introduced. (2) A novel stock distance algorithm based on motif detection is proposed to reduce the distance between stocks with similar trends. (3) A dynamic graph-based LSTM is proposed to aggregate the changes in historical graphs. We have conduct numerous experiments on 4503 Chinese A-share stocks, spanning 1218 trading days. Our model demonstrates 8.65% and 1.02% relative improvements in accumulated return and accuracy, respectively. In addition, the trading simulation validates that our algorithm outperforms the state-of-the-art (SOTA) algorithms in terms of profitability.

Temporal-Relational hypergraph tri-Attention networks for stock trend prediction

Predicting the future price trends of stocks is a challenging yet intriguing problem given its critical role to help investors make profitable decisions. In this paper, we present a collaborative temporal-relational modeling framework for end-to-end stock trend prediction. Different from existing studies relying on the pairwise correlations between stocks, we argue that stocks are naturally connected as a collective group, and introduce two heterogeneous hypergraphs to separately characterize the stock group-wise relationships of industry-belonging and fund-holding. A novel hypergraph tri-attention network (HGTAN) is proposed to augment the hypergraph convolutional networks with a hierarchical organization of intra-hyperedge, inter-hyperedge, and inter-hypergraph attention modules. In this manner, HGTAN adaptively determines the importance of nodes, hyperedges, and hypergraphs during the information propagation among stocks, so that the potential synergies between stock movements can be fully exploited. Experimental evaluation and investment simulation on real-world stock data demonstrate the effectiveness of our approach.

Stock Return Prediction Based on CNN Model and Genetic Evolutionary Algorithm For A-share Medical Sector

Since the outbreak of the epidemic in December 2019, the real economy has been seriously affected, where the stock market has experienced a short-term crash. In this context, the financial market has become more turbulent and unpredictable. Previously, the traditional prediction method only captures the linear relationship between both the dependent and the independent variable. With the growing advancement of technology and science, the application of deep learning models to learn the nonlinear relationship between high latitude indicators and predictors has become the mainstream trend of stock prediction. Therefore, a convolutional neural network (CNN) model with fusion genetic algorithm is proposed in this paper to predict and analyze the stock return rate of China’s A-share medical sector from January 1,2020 to February 2020. In order to facilitate the operation, this paper chooses the GPU with better performance to process the large-scale calculation in the neural network and builds the experimental environment under the Huawei cloud model arts notebook system. This paper selects the Sequential model belonging to the tensor flow library Keras package. Subsequently, this paper optimizes the parameters in the model by using genetic algorithm. According to the analysis, the mean square error of the optimal model is 0.0017, and the prediction results of the model in the test set are validated with well performances, which is of great significance to investors' decision-making. These results shed light on guiding further exploration of stock trend prediction.

Evolutionary Trading Signal Prediction Model Optimization Based on Chinese News and Technical Indicators in the Internet of Things

The Internet-of-Things (IoT) technologies are essential in deploying successful IoT-based services, especially in the financial services sector in recent years. Stock market prediction, which could also be an IoT-based service, is a very attractive topic that has inspired countless studies. Using financial news articles to forecast the effect of certain events, understand investors’ emotions, and react accordingly has been proved viable in the existing pieces of the literature. In this study, we utilized Chinese financial news in an attempt to predict the stock price movement and to derive a trading strategy based on news factors and technical indicators. First, the stock trend prediction (STP) approach is proposed. It first extracts keywords from the given articles. Then, the 2-word combination is employed to generate more meaningful keywords. The feature extraction and selection are followed to obtain important attributes for building a trading signal prediction model. Also, to make the trading signal more reliable, the technical indicators are considered to confirm the trading signal. Because the hyperparameters for the STP and technical indicators will have influenced the final results, an enhanced approach, namely, the genetic algorithm (GA)-based STP (GASTP) approach, is then proposed to find hyperparameters automatically for constructing a better prediction model. Experiments on real data sets were also made to show the effectiveness of the proposed algorithms. The results show that the GASTP performs better than the buy-and-hold strategy as well as the STP.

Data fusion with factored quantization for stock trend prediction using neural networks

As compared to the continuous temporal distributions, discrete data representations may be desired for simplified and faster data analysis and forecasting. Data compression can introduce one of the efficient ways to reduce continuous historical stock market data and present them in discrete forms; while predicting stock trend, a primary concern is towards up and down directions of the price movement and thus, data discretization for a focused approach can be beneficial. In this article, we propose a quantization-based data fusion approach with a primary motivation to reduce data complexity and hence, enhance the prediction ability of a model. Here, the continuous time-series values are transformed into discrete quantum values prior to applying them to a prediction model. We extend the proposed approach and factorize quantization by integrating different quantization step sizes. Such fused data can reduce the data to mainly concentrate on the stock price movement direction. To empirically evaluate the proposed approach for stock trend prediction, we adopt long short-term memory, deep neural network, and backpropagation neural network models and compare our prediction results with five existing approaches on several datasets using ten performance metrics. We analyze the impact of specific quantization factors and determine the individual best as well as overall best factor sizes; the results indicate a consistent performance enhancement in stock trend prediction accuracy as compared to the considered baseline methods with an improvement up to 7%. To evaluate the impact of quantization-based data fusion, we analyze time required to execute the experiments along with percentage reduction in the number of unique numeric terms. Further, these results are statistically evaluated using Wilcoxon signed-rank test. We discuss the superiority and applicability of factored quantization-based data fusion approach and conclude our work with potential future research directions.

Forecasting Daily Stock Movement Using a Hybrid Normalization Based Intersection Feature Selection and ANN

The potential financial benefits of stock market forecasting have drawn a lot of interest. Due to the various interconnected aspects, predicting these markets is a difficult endeavour that necessitates a thorough as well as efficient feature selection procedure to discover the highest useful aspects. Stock price changes are also influenced by previous trading days' movements, which is a time series problem. In stock forecasting, feature selection techniques are commonly used, although most known systems use a single feature selection methodology that probably can neglect some key notions about the regression function that is at the root of the problem relating the variables for input and output. This study employs an artificial neural network (ANN) based generative model to forecast pricing changes in the future by combining features preferred by different feature picking strategies to build an ideal optimal feature group. We begin by calculating an expanded set of 83 technical indicators using day-to-day stock data of six stock indices, and then we normalize them using the Hybrid-Normalization (HN) technique. The important features are selected using various types of feature selection techniques and then considering the common features for the stock movement prediction. For stock trend predictions, we used a variety of classifiers such as Support Vector Machine, K Nearest Neighbour and Artificial Neural Network and. The system was given a performance review after simulations were done on 6 stock indices from various portions of the international market. The outcomes show that joining highlighted features got by various feature choice calculations and taking care of them into a profound generative model beats best in class techniques.

Research on stock trend prediction methods - Taking CSI 300 and CSI 500 as examples

As an important part of the capital market, the stock market can not only reflect the quality of the macro economy in time, but also reflect the policy changes in the change of the stock price.In addition, the stock market not only provides a public financing platform with strong liquidity for enterprises, but also plays a crucial role in the redistribution of social resources.This paper takes China's CSI 300 index CSI 500 index from 2007 to 2022 as the research object, and uses ARIMA, ARCH family and other models to implement it, which provides a better solution for the prediction of stock trends.

An efficient hybrid stock trend prediction system during COVID-19 pandemic based on stacked-LSTM and news sentiment analysis

The coronavirus is an irresistible virus that generally influences the respiratory framework. It has an effective impact on the global economy specifically, on the financial movement of stock markets. Recently, an accurate stock market prediction has been of great interest to investors. A sudden change in the stock movement due to COVID -19 appearance causes some problems for investors. From this point, we propose an efficient system that applies sentiment analysis of COVID-19 news and articles to extract the final impact of COVID-19 on the financial stock market. In this paper, we propose a stock market prediction system that extracts the stock movement with the COVID spread. It is important to predict the effect of these diseases on the economy to be ready for any disease change and protect our economy. In this paper, we apply sentimental analysis to stock news headlines to predict the daily future trend of stock in the COVID-19 period. Also, we use machine learning classifiers to predict the final impact of COVID-19 on some stocks such as TSLA, AMZ, and GOOG stock. For improving the performance and quality of future trend predictions, feature selection and spam tweet reduction are performed on the data sets. Finally, our proposed system is a hybrid system that applies text mining on social media data mining on the historical stock dataset to improve the whole prediction performance. The proposed system predicts stock movement for TSLA, AMZ, and GOOG with average prediction accuracy of 90%, 91.6%, and 92.3% respectively.

Improving stock trend prediction through financial time series classification and temporal correlation analysis based on aligning change point

Improving stock trend prediction through financial time series classification and temporal correlation analysis based on aligning change point

STGV-Similarity between trend generating vectors: A new sample weighting scheme for stock trend prediction using financial features of companies

The problem of effective stock trend prediction has aroused much attention these years for its profitability. The development of algorithmic trading drives explosive growth in fast and effective techniques for trend predictions. However, little attention has been paid to sample weighting schemes in this field. In this article, we propose a new sample weighting scheme for stock trend predictions based on financial features of companies. Specifically, stock trends are supposed to be determined by hidden market states represented by trend generating vectors. These vectors can be generated from financial features of companies. The scheme considers similarities between trend generating vectors (STGVs) when assigning weights to samples from different periods to differentiate their prediction capabilities. Similarity scores calculated with a proper metric are adopted to measure similarity. We train models with STGV to predict stock trends. Extensive experiments are conducted to figure out the most suitable similarity metric used in STGV and demonstrate its superiority over other sample weighting schemes together with its generalizability.

Research on trend prediction of component stock in fuzzy time series based on deep forest

With the continuous development of machine learning and the increasing complexity of financial data analysis, it is more popular to use models in the field of machine learning to solve the hot and difficult problems in the financial industry. To improve the effectiveness of stock trend prediction and solve the problems in time series data processing, this paper combines the fuzzy affiliation function with stock-related technical indicators to obtain nominal data that can widely reflect the constituent stocks in the case of time series changes by analysing the S&P 500 index. Meanwhile, in order to optimise the current machine learning algorithm in which the setting and adjustment of hyperparameters rely too much on empirical knowledge, this paper combines the deep forest model to train the stock data separately. The experimental results show that (1) the accuracy of the extreme random forest and the accuracy of the multi-grain cascade forest are both higher than that of the gated recurrent unit (GRU) model when the un-fuzzy index-adjusted dataset is used as features for input, (2) the accuracy of the extreme random forest and the accuracy of the multigranular cascade forest are improved by using the fuzzy index-adjusted dataset as features for input, (3) the accuracy of the fuzzy index-adjusted dataset as features for inputting the extreme random forest is improved by 18.89% compared to that of the un-fuzzy index-adjusted dataset as features for inputting the extreme random forest and (4) the average accuracy of the fuzzy index-adjusted dataset as features for inputting multi-grain cascade forest increased by 5.67%.

Case-Based Teaching for Stock Prediction System Based on Deep Learning

In recent years, securities investors hope to obtain certain income from securities investment by buying stocks. By referring to the historical trading data of the stock market, investors take into account various technical indicators and related financial data of listed companies to analyze and determine the investment plan, and select the appropriate stock for investment, which is relatively time-consuming and energy consuming. In this paper, LSTM short and long-term memory neural network is used for data modeling analysis, in-depth analysis of the inherent characteristics of the data, research on stock trend prediction, stock price prediction model is constructed, and the prediction effect of the stock market is explored. To examine different model structures to forecast the effect of future stock prices, and optimize the stock prediction model, by controlling the stock prediction model of variable of the factors affecting the prediction effect of contrast experiment results were analyzed, and the evaluation model prediction accuracy, to build and train a good stock prediction model. Finally, combined with the optimized stock price prediction model, it can help investors make better investment decisions and bring relatively stable income for investors.

Sparrow Search Algorithm-Optimized Long Short-Term Memory Model for Stock Trend Prediction.

The long short-term memory (LSTM) network is especially suitable for dealing with time series-related problems, which has led to a wide range of applications in analyzing stock market quotations and predicting future price trends. However, the selection of hyperparameters in LSTM networks was often based on subjective experience and existing research. The inability to determine the optimal values of the parameters results in a reduced generalization capability of the model. Therefore, we proposed a sparrow search algorithm-optimized LSTM (SSA-LSTM) model for stock trend prediction. The SSA was used to find the optimal hyperparameters of the LSTM model to adapt the features of the data to the structure of the model, so as to construct a highly accurate stock trend prediction model. With the Shanghai Composite Index stock data in the last decade, the mean absolute percentage error, root mean square error, mean absolute error, and coefficient of determination between stock prices predicted by the SSA-LSTM method and actual prices are 0.0093, 41.9505, 30.5300, and 0.9754. The result indicates that the proposed model possesses higher forecasting precision than other traditional stock forecasting methods and enhances the interpretability of the network model structure and parameters.

Assets Trading Strategy Based on ALG Evaluation and Prediction Integrated Model

With the rapid development of economy and the maturity of financial markets, more and more people choose to invest in stocks to achieve property appreciation, so the study of stock investment decision-making is increasingly important. In this topic, in order to maximize the interests of investors, our team not only needs to accurately predict the future trend of gold and bitcoin, but also needs to make the most reasonable strategy according to the future trend of gold and bitcoin. Therefore, our team reads a large number of papers, refer to the current model of stock trend prediction and decision-making and combine with the data given by the topic to establish our model. According to the stock trend, this paper designs an ALG (Apriori algorithm - Attentional BiLSTM neural network - GARCH model) evaluation and prediction integrated model, and makes a time series chart of daily return rate related to gold and bitcoin, finally predicts the daily return rate. This paper compares the daily yield predicted by ALG model with that predicted by grey model, which shows that the yield predicted by ALG model is much higher than that predicted by grey prediction model.

Improving Stock Trend Prediction using LSTM Neural Network Trained on a Complex Trading Strategy

Abstract: Technical analysis in stock trading addresses the crucial matter of making optimal trading decisions promptly. Predicting directional movement in the target market using technical indicators is quite common. Besides its many other applications, machine learning helps to solve the algorithmic trading problem of determining optimal trading positions, and some types of deep neural networks have been proven as up-and-coming methods for forecasting the returns of the stock market. The current work presents the idea of training a neural network on a new trading strategy, named, Unified Trading Strategy (UTS) that integrates technical indicators from three well-known categories referred to as leading, lagging, and volatility. The trained network serves as an excellent alternative to the classical technical analysis model by simplifying the process of finding potential events of effective trade with better performance and reusability.

Multi-layer features ablation of BERT model and its application in stock trend prediction

Stock comments published by experts are important references for accurate stock trends prediction. How to comprehensively and accurately capture the topic of expert stock comments is an important issue which belongs to text classification. The Bidirectional Encoder Representations from Transformers (BERT) pretrained language model is widely used for text classification, due to its high identification accuracy. However, BERT has some limitations. First, it only utilizes fixed length text, leading to suboptimal performance in long text information exploration. Second, it only relies on the features extracted from the last layer, resulting in incomprehensive classification features. To tackle these issues, we propose a multi-layer features ablation study of BERT model for accurate identification of stock comments’ themes. Specifically, we firstly divide the original text to meet the length requirement of the BERT model based on sliding window technology. In this way, we can enlarge the sample size which is beneficial for reducing the over-fitting problem. At the same time, by dividing the long text into multiple short texts, all the information of the long text can be comprehensively captured through the synthesis of the subject information of multiple short texts. In addition, we extract the output features of each layer in the BERT model and apply the ablation strategy to extract more effective information in these features. Experimental results demonstrate that compared with non-intercepted comments, the topic recognition accuracy is improved by intercepting stock comments based on sliding window technology. It proves that intercepting text can improve the performance of text classification. Compared with the BERT, the multi-layer features ablation study we present in the paper further improves the performance in the topic recognition of stock comments, and can provide reference for the majority of investors. Our study has better performance and practicability on stock trend prediction by stock comments topic recognition.