A Novel Data Mining Algorithm based on BP Neural Network and Its Applications on Stock Price Prediction

Forecasting stock indices with back propagation neural network

Prediction of stock prices has been the primary objective of an investor. Any future decision taken by the investor directly depends on the stock prices associated with a company. This work presents a hybrid approach for the prediction of intra-day stock prices by considering both time-series and sentiment analysis. Furthermore, it focuses on long short-term memory (LSTM) architecture for the time-series analysis of stock prices and Valence Aware Dictionary and sEntiment Reasoner (VADER) for sentiment analysis. LSTM is a modified recurrent neural network (RNN) architecture. It is efficient at extracting patterns over sequential time-series data, where the data spans over long sequences and also overcomes the gradient vanishing problem of RNN. VADER is a lexicon and rule-based sentiment analysis tool attuned to sentiments expressed in social media and news articles. The results of both techniques are combined to forecast the intra-day stock movement and hence the model named as LSTM-VDR. The model is first of its kind, a combination of LSTM and VADER to predict stock prices. The dataset contains closing prices of the stock and recent news articles combined from various online sources. This approach, when applied on the stock prices of Bombay Stock Exchange (BSE) listed companies, has shown improvements in comparison to prior studies.

As global financial markets become increasingly interconnected, relying solely on historical data from a single market is insufficient for achieving high prediction accuracy in stock price forecasting. It is essential to consider the impact of cross-market transactions on China’s stock market fluctuations. This study investigates this impact by constructing a comprehensive dataset that includes stock market, bond market, and foreign exchange market data from multiple countries. A deep learning algorithm, combined with the grid search method, was employed to compare different structural hyperparameters of four models: LSTM, GRU, MLP, and Transformer. The results indicate that the GRU model outperformed the others in terms of prediction accuracy. Consequently, a GRU-Arbitrage trading system based on optimal structural hyperparameters was developed. This system effectively integrates international and domestic information for stock price prediction, providing investors with a practical and accurate tool. The research findings show that the mean squared error (MSE) of stock prices predicted using international market transaction information for the Chinese stock market is 0.0069, followed by 0.0035 for the bond market and 0.0102 for the foreign exchange market. These results verify the significant impact of cross-market data on predicting China’s stock market fluctuations.

From past to present, the prediction of stock price in stock market has been a knotty problem. Many researchers have made various attempts and studies to predict stock prices. The prediction of stock price in stock market has been of concern to researchers in many disciplines, including economics, mathematics, physics, and computer science. This study intends to learn fluctuation of stock prices in stock market by using recently spotlighted techniques of deep learning to predict future stock price. In previous studies, we have used price-based input-features to measure performance changes in deep learning models. Results of this studies have revealed that the performance of stock price models would change according to varied input-features configured based on stock price. Therefore, we have concluded that more novel input-feature in deep learning model is needed to predict patterns of stock price fluctuation more precisely. In this paper, for predicting stock price fluctuation, we design deep learning model using 715 novel input-features configured on the basis of technical analyses. The performance of the prediction model was then compared to another model that employed simple price-based input-features. Also, rather than taking randomly collected set of stocks, stocks of a similar pattern of price fluctuation were filtered to identify the influence of filtering technique on the deep learning model. Finally, we compared and analyzed the performances of several models using different configuration of input-features and target-vectors.

Stock price exhibits distinct features during different time scales due to the effects of complex factors. Analyzing these features can help delineate the mechanisms that determine the stock price and enhance the prediction accuracy of the stock price. By using singular spectrum analysis (SSA), this paper first decomposes the original price series into a trend component, a market fluctuation component and a noise component to analyze the stock price. The economic meanings of the three components are identified as a long-term trend, effects of significant events and short-term fluctuations caused by noise in the market. Then, to take into account the features of the above three components to the stock price prediction, a novel combined model that integrates SSA and support vector machine (SVM) (e.g., SSA–SVM) is proposed. Compared with SVM, adaptive network-based fuzzy inference system (ANFIS), ensemble empirical mode decomposition-ANFIS (EEMD–ANFIS), EEMD–SVM and SSA–ANFIS, SSA–SVM demonstrates the best prediction performance based on four criteria, indicating that the proposed model is a promising approach for stock price prediction.

As the stock price decoupling between domestic and foreign stock markets is prolonged, the so-called ‘Seohak ants’ are emerging to expand investing targets to the global stock market. This study is to predict the stock prices and volatility of global automotive companies and analyze whether economic value appears through performance analysis of investment strategy. The investment target was selected as automakers in Germany, the U.S., Japan, and Korea, which are advanced countries in the global automotive industry and fiercely competing as the paradigm of electric and self-driving cars emerged. Machine learning models were used to predict the stock prices, which show good results in predictive studies of time series data such as irregular and nonlinear moving stock prices. The empirical results from January 2011 to September 2022 data are as follows. First, daily low prices showed the highest importance score in feature variables for stock price prediction. Second, the random forest model in stock price prediction and the support vector regression model in volatility prediction showed excellent predictive power. Third, the investment strategy using the predicted stock price showed higher profitability than the benchmark, finding the economic value of the predicted stock price. This study is of academic and practical significance in that it predicted the stock prices volatility of the global automotive industry by using the machine learning models in the face of expanding global stock investment. In future studies, it is necessary to diversify the investment target and add sophisticated prediction techniques to study to improve the predictive performance.

In the era of artificial intelligence, machine learning methods are successfully used in various fields. Machine learning has attracted extensive attention from investors in the financial market, especially in stock price prediction. However, one argument for the machine learning methods used in stock price prediction is that they are black-box models which are difficult to interpret. In this paper, we focus on the future stock price prediction with the historical stock price by machine learning and deep learning methods, such as support vector machine (SVM), random forest (RF), Bayesian classifier (BC), decision tree (DT), multilayer perceptron (MLP), convolutional neural network (CNN), bi-directional long-short term memory (BiLSTM), the embedded CNN, and the embedded BiLSTM. Firstly, we manually design several financial time series where the future price correlates with the historical stock prices in pre-designed modes, namely the curve-shape-feature (CSF) and the non-curve-shape-feature (NCSF) modes. In the CSF mode, the future prices can be extracted from the curve shapes of the historical stock prices. Conversely, in the NCSF mode, they can’t. Secondly, we apply various algorithms to those pre-designed and real financial time series. We find that the existing machine learning and deep learning algorithms fail in stock price prediction because in the real financial time series, less information of future prices is contained in the CSF mode, and perhaps more information is contained in the NCSF. Various machine learning and deep learning algorithms are good at handling the CSF in historical data, which are successfully applied in image recognition and natural language processing. However, they are inappropriate for stock price prediction on account of the NCSF. Therefore, accurate stock price prediction is the key to successful investment, and new machine learning algorithms handling the NCSF series are needed.

Stock price prediction is useful for investors to see how the prospects of a company's stock investment in the future. Stock price prediction can be used to anticipate the deviation of stock prices. It can also helps investors in decision making. Artificial Neural Networks do not require mathematical models but data from problems to be solved. Information is conveyed through the data, and the Artificial Neural Network filters the information through training. Therefore, Artificial Neural Network is appropriate to solve the problem of stock price prediction. Learning method that will be used to predict stock price is Supervised Learning with Backpropagation algorithm. With this algorithm, networks can be trained using stock price data from the previous time, classify it and adjust network link weight as new input and forecast future stock prices. By using ANN, time series prediction is more accurate. After analyzing the problem of stock price movement system, the writer can know the pattern of what variables will be taken for further insert into the stock price forecasting system. This application can be used for stock price forecasting technique, so it will be useful for beginner investor as well as advanced investor as reference to invest in capital market. Implementing supervised learning backpropagation method will get accurate forecasting results more than 98%.Keyword - artificial neural network, stock, backpropagation.

Against the backdrop of an increasingly large stock market and a growing number of investors, many individuals have faced bankruptcy due to blindly following trends in stock investment. This situation has created a demand for methods to predict stock prices in advance. To address this issue, researchers have previously proposed various approaches, including traditional analytical methods based on historical data, statistical analysis methods, machine learning and deep learning methods, etc. The research focus of this paper is to investigate the specific conditions under which the Backpropagation Neural Network model delivers superior performance in stock price prediction. This study utilizes 44 years of historical stock price data from Apple Inc. (AAPL), encompassing key features such as Date, Opening Price, Highest Price of the Day, Lowest Price of the Day, Closing Price, Adjusted Closing Price, and Trading Volume. Specifically, the study focuses on selecting the Opening Price, Highest Price of the Day, Lowest Price of the Day, Closing Price, and Trading Volume as input features. The research ultimately achieved relatively accurate results. These findings are then leveraged to extend insights into effective configuration strategies for a wider range of other prediction methods.

A stock price principal component neural network prediction model was established by combining principal component analysis and BP neural network to address the non-linear characteristics of stock opening prices. Using Python to crawl historical market data of Shanghai and Shenzhen 300 from the BaoStock system, and conducting empirical analysis based on the crawled data. The results show that the relative error of the training is controlled within 4%, and the prediction accuracy is higher than that of the prediction model constructed solely using BP neural network. Finally, through misalignment training, the stock price for the next 5 days was predicted with a prediction error controlled within 4%. The prediction effect was good, and the research results can provide valuable reference for decision-making by relevant departments and investors.

In recent years, the development of technology and artificial intelligence has brought forth new opportunities in analyzing and predicting stock prices. One of the approaches used is the Neural Network algorithm, which is a part of the branch of artificial intelligence known as Deep Learning. This algorithm can learn complex patterns and relationships among data by modeling inspired by the human neural network. This research utilizes the Neural Network for stock price prediction and aims to understand the application of Neural Network in predicting stock prices, which can benefit investors and market participants. Additionally, historical stock price data can be used as input for the Neural Network algorithm. The Neural Network is a frequently used algorithm for accurate predictions and is widely employed in prediction-based or forecasting research. The result of this research is the Root Mean Squared Error (RMSE) value of 19.734 +/- 0.000. The use of the Neural Network as an algorithm for stock price prediction provides investors with valuable information for making investment decisions for companies..

Stock price prediction targets to predict the future development direction of the stock market and the degree of rise and fall of the stock price according to stock market quotations. However, since the stock price has high nonlinear, high noisy, and dynamic characteristics, it is challenging to predict stock prices. This paper predicts stock price prediction with a long-short term memory (LSTM) model according to the above data characteristics. First, because the stock price is distributed in different price ranges, we pre-process the data by normalizing all the data to the range of 0 to 1. Then, we improve the model performance by adjusting the three main parameters, hidden layers, learning rate, and time window. LSTM adds a control part into LSTM to further catch these data to make the best of historical data. We compare the proposed method with Recurrent Neural Network (RNN) on a related dataset with relative root mean square error (RRMSE), mean absolute error (MAE) and mean absolute error percentage (MAPE). The lower the score on all three indicators, the more accurate the prediction. The experimental results show that the scores of LSTM are lower than RNN in three indicators, so its prediction is more accurate than RNN with appropriate parameters. Our analyses illustrate that LSTM can better predict the dynamic non-linear data like a stock price by considering the historical data.

To aid in the prediction of stock prices, forecasting algorithms can be beneficial. Black box modelling techniques can be, and have been, applied to the prediction of stock prices, but do not offer any clarity on the parameters that have impact on the model predictions. Hence, the focus of this work is to utilise a transparent model to enable the understanding and interpretation of the model output. Stock market data between 2009 and 2019 (a 10-year period) were analysed to determine if a Nonlinear AutoRegressive Moving Average model with eXogenous input (NARMAX) model could accurately predict day ahead stock prices. A NARMAX model was initially developed using a single input variable (Open) and then extended using multiple input variables which included Open, High and Low stock prices. Obtained results revealed that the NARMAX model has strong potential for day ahead price prediction and can be compared against existing techniques for stock market price prediction. Performance evaluation, demonstrated across multiple stock market datasets, demonstrate that NARMAX is efficient in predicting stock market closing price.

Abstract— Stocks are investments that have dynamic movements. Stock price changes move every day even hourly. With very fast changes, stock prices require predictions to be able to determine stock market projections. Predictions are used to reduce risk when making transactions. In this study, predictions of stock price trends were made using the Recurrent Neural Network (RNN). The approach taken is to perform a time series analysis using the RNN variance, namely Long Short Term Memory (LSTM). Hyperparameter construction in the LSTM model testing simulation can estimate stock prices with maximum percentage accuracy. The results showed that the prediction model produced a loss function of 0.0012 and a training time of 73 m/step. The evaluation was carried out with the RMSE which resulted in a score of 17.13325. Predictions are obtained after doing machine learning using 1239 data. The RMSE and LSTM models are calculated by changing the number of epochs, the variation between the predicted stock price and the current stock price. Computations are carried out using a stock market dataset that includes open, high, low, close, adj prices, closes, and volumes. The main objective of this study is to determine the extent to which the LSTM algorithm anticipates stock market prices with better accuracy. Code can be seen at iranihoeronis/RNN-LSTM (github.com) Keywords— Stock Prediction, Time Series, Recurrent Neural Network (RNN), Long Short Term Memory (LSTM).

Over the past two years, global stock markets have gradually recovered and new investors have entered the market. While there are many factors affecting stock prices and the stock market is changing rapidly, the way to accurately predict stock prices has become the focus of investors. This paper will use the concept of machine learning to predict the stock prices of three listed companies based on three different regression models (i.e., OLS, Ridge and XGBoost). According to the analysis, the OLS model and the Ridge model are very accurate in predicting stock prices, especially in the low and middle price ranges. In contrast to these typical linear regression models, the XGBoost model is not as accurate in predicting stock prices and even has a significant prediction bias in the high price range. These results will enable subsequent research to make better choices when selecting models for forecasting, especially for data sets with different characteristics.