In recent years, with the rapid development of the economy, more and more people begin to invest into the stock market. Accurately predicting the change of stock price can reduce the investment risk ...of stock investors and effectively improve the investment return. Due to the volatility characteristics of the stock market, stock price prediction is often a nonlinear time series prediction. Stock price is affected by many factors. It is difficult to predict through a simple model. Therefore, this paper proposes a CNN-BiLSTM-AM method to predict the stock closing price of the next day. This method is composed of convolutional neural networks (CNN), bi-directional long short-term Memory (BiLSTM), and attention mechanism (AM). CNN is used to extract the features of the input data. BiLSTM uses the extracted feature data to predict stock closing price of the next day. AM is used to capture the influence of feature states on the stock closing price at different times in the past to improve the prediction accuracy. In order to prove the effectiveness of this method, this method and other seven methods are used to predict the stock closing price of the next day for 1000 trading days of the Shanghai Composite Index. The results show that the performance of this method is the best, MAE and RMSE are the smallest (which are 21.952 and 31.694). R
2
is the largest (its value is 0.9804). Compared with other methods, the CNN-BiLSTM-AM method is more suitable for the prediction of stock price and for providing a reliable way for investors’ to make stock investment decisions.
Stock price prediction is an important topic for investors and companies. The increasing effect of machine learning methods in every field also applies to stock forecasting. In this study, it is ...aimed to predict the future prices of the stocks of companies in different sectors traded on the Borsa Istanbul (BIST) 30 Index. For the study, the data of two companies selected as examples from each of the holding, white goods, petrochemical, iron and steel, transportation and communication sectors were analyzed. In the study, in addition to the share analysis of the sectors, the price prediction performances of the machine learning algorithm on a sectoral basis were examined. For these tests, XGBoost, Support Vector Machines (SVM), K-nearest neighbors (KNN) and Random Forest (RF) algorithms were used. The obtained results were analyzed with mean absolute error (MAE), mean absolute percent error (MAPE), mean squared error (MSE), and R2 correlation metrics. The best estimations on a sectoral basis were made for companies in the Iron and Steel and Petroleum field. One of the most important innovations in the study is the examination of the effect of current macro changes on the forecasting model. As an example, the effect of the changes in the Central Bank Governors, which took place three times in the 5-year period, on the forecast was investigated. The results showed that the unpredictable effects on the policies after the change of Governors also negatively affected the forecast performance
In today’s society, investment wealth management has become a mainstream of the contemporary era. Investment wealth management refers to the use of funds by investors to arrange funds reasonably, for ...example, savings, bank financial products, bonds, stocks, commodity spots, real estate, gold, art, and many others. Wealth management tools manage and assign families, individuals, enterprises, and institutions to achieve the purpose of increasing and maintaining value to accelerate asset growth. Among them, in investment and financial management, people’s favorite product of investment often stocks, because the stock market has great advantages and charm, especially compared with other investment methods. More and more scholars have developed methods of prediction from multiple angles for the stock market. According to the feature of financial time series and the task of price prediction, this article proposes a new framework structure to achieve a more accurate prediction of the stock price, which combines Convolution Neural Network (CNN) and Long–Short-Term Memory Neural Network (LSTM). This new method is aptly named stock sequence array convolutional LSTM (SACLSTM). It constructs a sequence array of historical data and its leading indicators (options and futures), and uses the array as the input image of the CNN framework, and extracts certain feature vectors through the convolutional layer and the layer of pooling, and as the input vector of LSTM, and takes ten stocks in U.S.A and Taiwan as the experimental data. Compared with previous methods, the prediction performance of the proposed algorithm in this article leads to better results when compared directly.
The sporadic large fluctuations seen in the stock market are due to different factors. These large fluctuations are termed extreme events (EE). We have identified fundamental, technical, and external ...factors and categorized positive or negative EE depending on the impact of these factors. During such events, the stock price time series is found to be nonstationary. Hence, the Hilbert–Huang transformation is used to identify EEs based on high instantaneous energy (IE) concentration. The analysis shows that IE concentration in the stock price is very high during both positive and negative EE, surpassing a threshold of Eμ+4σ, where Eμ and σ are the mean energy and standard deviation of energy, respectively. Further, support vector regression is used to predict the stock price during an EE, with the close price being found to be the most useful input than the open-high-low-close (OHLC) inputs. The maximum prediction accuracy for one step using close price and OHLC prices are 95.98% and 95.64%, respectively. Whereas, for the two step prediction, the accuracies are 94.09% and 93.58%, respectively. These results highlight that the accuracy of one-step predictions surpasses that of two-step predictions. Also, accuracy decreases when predicting stock prices closer to an EE. The EEs identified from predicted time series exhibit statistical characteristics similar to those obtained from the original data. The analysis emphasizes the importance of monitoring factors that lead to EEs for an effective entry or exit strategy as investors can gain or lose significant amounts of capital due to these events.
•Fundamental, technical, external factors have a significant impact on stock prices.•The stock market experiences extreme events (EE) as a result of these factors.•Positive and negative EEs are identified using Hilbert–Huang Transformation.•Support vector regression is used to predict stock prices during EEs.•The previous close price is a better input to forecast stock price the next day.
Predicting stock price is a trend yet very challenging task. It is because the stock prices depend upon several internal and external factors. Stock price prediction can be very useful for financial ...sectors and the government and help in informed decision-making. This paper analyzes the stock market prices of K-Electric Karachi. It is found that the stock prices of K-electric depend on the stock prices of the refinery sector. The paper analyzes the stock price data of the two sectors. Also, the paper compares the stock price prediction based on moving average, auto-regressive integrated moving average (ARIMA), convolutional neural network and long short-term memory (LSTM) model. It is found that ARIMA outperforms the other algorithms. A set of experiments were conducted to test the performance of algorithms. The algorithms were analyzed based on different metrics such as root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE).
•A data-driven stock price trend prediction system is designed and implemented.•Models are trained from historical data using random forest with feature selection.•Training data are created by ...unsupervised morphological pattern recognition.
This paper proposes a novel stock price trend prediction system that can predict both stock price movement and its interval of growth (or decline) rate within the predefined prediction durations. It utilizes an unsupervised heuristic algorithm to cut raw transaction data of each stock into multiple clips with the predefined fixed length and classifies them into four main classes (Up, Down, Flat, and Unknown) according to the shapes of their close prices. The clips in Up and Down can be further classified into different levels reflecting the extents of their growth (or decline) rates with respect to both close price and relative return rate. The features of clips include their prices and technical indices. The prediction models are trained from these clips by a combination of random forests, imbalance learning and feature selection. Evaluations on the seven-year Shenzhen Growth Enterprise Market (China) transaction data show that the proposed system can make effective predictions, is robust to the market volatility, and outperforms some existing methods in terms of accuracy and return per trade.
Stocks price prediction is a current hot spot with great promise and challenges. Recently, there have been many stock price prediction methods. However, the prediction accuracy of these methods is ...still far from satisfactory. In this paper, we propose a stock price prediction method that incorporates multiple data sources and the investor sentiment, which can be called S_I_LSTM. Firstly, we crawl multiple data sources on the Internet and preprocess them respectively. These data involve stock historical data, technical indicators, and non-traditional data sources, such as stock posts and financial news. Then, we use the sentiment analysis method based on convolutional neural network for the non-traditional data, which can calculate the investors' sentiment index. Finally, we combine sentiment index, technical indicators and stock historical transaction data as the feature set of stock price prediction and adopt the long short-term memory network for predicting the China Shanghai A-share market. The experiments show that the predicted stock closing price is closer to the true closing price than the single data source, and the mean absolute error can achieve 2.386835, which is better than traditional methods. We verified the effectiveness on the real data sets of five listed companies.
•A framework integrating various data preprocessing techniques is proposed.•A set of features from multiple data sources is compiled for information fusion.•Non-stationary signals in raw price series ...are decomposed in time-frequency domain.•The framework is exemplified and validated through analyses on BGI Genomics.•Online news and time-frequency features improve the prediction performance.
The recent availability of enormous amounts of both data and computing power has created new opportunities for predictive modeling. This paper compiles an analytical framework based on multiple sources of data including daily trading data, online news, derivative technical indicators, and time–frequency features decomposed from closing prices. We also provide a real-life demonstration of how to combine and capitalize on all available information to predict the stock price of BGI Genomics. Moreover, we apply a long short-term memory (LSTM) network equipped with an attention mechanism to identify long-term temporal dependencies and adaptively highlight key features. We further examine the learning capabilities of the network for specific tasks, including forecasting the next day’s price direction and closing price and developing trading strategies, comparing its statistical accuracy and trading performance with those of methods based on logistic regression, support vector machine, gradient boosting decision trees, and the original LSTM model. The experimental results for BGI Genomics demonstrate that the attention enhanced LSTM model remarkably improves prediction performance through multi-source heterogeneous information fusion, highlighting the significance of online news and time–frequency features, as well as exemplifying and validating our proposed framework.
Within last decade, the investing habits of people is rapidly increasing towards stock market. The nonlinearity and high volatility of stock prices have made it challenging to predict stock prices. ...Since stock price data contains incomplete, complex and fuzzy information, it is very difficult to capture any nonlinear characteristics of stock price data, which usually may be unknown to the investors. There is a dire need of an accurate stock price prediction model that could offer insights to the investors on stock prices, which ultimately could deliver positive investment returns. This research is focused on proposing a hybrid deep learning (DL) based predictive model, that combines a Bidirectional Cuda Deep Neural Network Long Short-Term Memory (BiCuDNNLSTM) and a one-dimensional Convolutional Neural Network (CNN), for timely and efficient prediction of stock prices. Our proposed model (BiCuDNNLSTM-1dCNN) is compared with other hybrid DL-based models and state of the art models for verification using five stock price datasets. The predicted results show that the proposed hybrid model is efficient for accurate prediction of stock price and reliable for supporting investors to make their informed investment decisions.
•BiCuDNNLSTM-1dCNN is a hybrid DL model based on Bidirectional CuDNNLSTM and CNN.•BiCuDNNLSTM-1dCNN is efficient and scalable in developed and emerging stock market.•BiCuDNNLSTM-1dCNN uses univariate time series data to predict stock price.•Results confirm BiCuDNNLSTM-1dCNN is effective for volatility of stock price data.•BiCuDNNLSTM-1dCNN predicts better than LSTM, LSTM-CNN, CuDNNLSTM and LSTM-DNN.