股票市场的波动会影响人们生活的各个方面,因此准确预测股票价格具有重要意义。然而,传统的时间序列预测模型(如ARIMA)在处理股票价格中的非线性特征时表现不佳,难以获得令人满意的预测效果。鉴于深度学习在处理非线性问题上的优越能力...股票市场的波动会影响人们生活的各个方面,因此准确预测股票价格具有重要意义。然而,传统的时间序列预测模型(如ARIMA)在处理股票价格中的非线性特征时表现不佳,难以获得令人满意的预测效果。鉴于深度学习在处理非线性问题上的优越能力,它在股票价格预测中展现出巨大的潜力。本文提出了一种ARIMA-CNN-LSTM混合模型来预测股票价格,该模型充分挖掘了股票市场的历史信息,从而实现更高精度的预测。首先,使用ARIMA对股票数据进行预处理,将处理得到的残差序列输入CNN,通过卷积提取股票数据的深层特征;随后,通过LSTM挖掘股票数据的长期时间序列特征。本文以中国银行2009年1月1日至2023年12月31日的股票数据为研究对象,构建混合模型,并与ARIMA-LSTM模型、CNN-LSTM模型的预测结果进行对比。实验结果表明,本文提出的混合模型预测精度更高,相较于ARIMA-LSTM与CNN-LSTM模型,本模型在均方误差(MSE)指标上分别降低了25%与16.7%,在平均绝对误差(MAE)指标上分别降低了14.1%与9.4%,展示了更好的预测效果。The volatility of the stock market affects various aspects of people’s lives, making accurate stock price predictions highly significant. However, traditional time series forecasting models, such as ARIMA, perform poorly when dealing with the nonlinear characteristics of stock prices, leading to unsatisfactory prediction outcomes. Given the superior capability of deep learning in handling nonlinear problems, it shows great potential in stock price prediction. This paper proposes a hybrid ARIMA-CNN-LSTM model for stock price prediction, which fully exploits historical market information to achieve higher prediction accuracy. First, ARIMA is used to preprocess the stock data, with the resulting residual series fed into a CNN, which extracts deep features of the stock data through convolution. Subsequently, LSTM is employed to capture the long-term temporal characteristics of the stock data. Using the stock data of the Bank of China from January 1, 2009, to December 31, 2023, as the research object, the hybrid model is constructed and compared with the prediction results of the ARIMA-LSTM model and CNN-LSTM model. The experimental results show that the proposed hybrid model achieves higher prediction accuracy. Compared to the ARIMA-LSTM and CNN-LSTM models, this model reduces the mean squared error (MSE) by 25% and 16.7%, respectively, and decreases the mean absolute error (MAE) by 14.1% and 9.4%, respectively, demonstrating better forecasting performance.展开更多
本文基于弹性网络回归模型对股票价格进行了预测分析。通过收集国内某酒厂738个交易日的数据,选取开盘价、最高价、最低价、交易量、涨跌幅等作为自变量,以收盘价为因变量,分别应用线性回归、岭回归、Lasso回归及弹性网络回归四种模型...本文基于弹性网络回归模型对股票价格进行了预测分析。通过收集国内某酒厂738个交易日的数据,选取开盘价、最高价、最低价、交易量、涨跌幅等作为自变量,以收盘价为因变量,分别应用线性回归、岭回归、Lasso回归及弹性网络回归四种模型进行预测分析。研究结果表明,弹性网络回归模型在处理多重共线性问题和变量筛选方面具有显著优势。通过交叉验证确定了最优的惩罚参数,使得模型的预测误差最小。最终,最高价、最低价、交易量和涨跌幅被筛选为影响股票收盘价的主要因素。本文的研究为股票价格预测提供了有效的方法和工具,并为金融市场的投资决策提供了重要参考。This study conducts a stock price prediction analysis based on the Elastic Net regression model. Using data from 738 trading days of a domestic brewery, the study selects opening price, highest price, lowest price, trading volume, and price change percentage as independent variables, with the closing price as the dependent variable. Four models are applied for prediction analysis: linear regression, ridge regression, Lasso regression, and Elastic Net regression. The results show that the Elastic Net regression model has significant advantages in handling multicollinearity issues and variable selection. The optimal penalty parameters are determined through cross-validation, minimizing the prediction error. Ultimately, the highest price, lowest price, trading volume, and price change percentage are identified as the key factors influencing stock closing prices. This research provides an effective method and tool for stock price prediction and offers important insights for financial market investment decisions.展开更多
在全球化日益深入的今天,国际间的贸易越来越多,汇率对一国经济的影响也越来越重。而股票市场作为宏观经济的晴雨表,是资产市场的重要组成部分,其受宏观经济的影响是非常剧烈而且直接的。本文选取2009~2023年人民币兑美元汇率中间价、...在全球化日益深入的今天,国际间的贸易越来越多,汇率对一国经济的影响也越来越重。而股票市场作为宏观经济的晴雨表,是资产市场的重要组成部分,其受宏观经济的影响是非常剧烈而且直接的。本文选取2009~2023年人民币兑美元汇率中间价、上证综合指数和进出口贸易差额,建立向量自回归模型进行分析,通过Johansen协整检验和格兰杰因果检验等,得出结论:1) Johansen协整检验结果说明人民币兑美元汇率中间价和上证综合指数之间存在从汇率到股票价格的长期协整关系;2) 人民币兑美元汇率中间价对上证综合指数有着一个正向的影响。也就是汇率上升,股票价格上升,汇率下降,股票价格下降,但是股价的变动对汇率的影响不显著。最后根据实证分析的结论,提出了有针对性的政策与建议。In today’s increasingly globalized world, international trade is increasing, and the impact of exchange rates on a country’s economy is also becoming increasingly significant. As a barometer of macroeconomics, the stock market is an important component of the asset market, and its impact from macroeconomics is very severe and direct. This article selects the middle price of the RMB to USD exchange rate, the Shanghai Composite Index, and the import and export trade balance from 2009 to 2023, and establishes a vector autoregressive model for analysis. Through Johansen cointegration test and Granger causality test, the following conclusions are drawn: 1) The Johansen cointegration test results indicate that there is a long-term cointegration relationship between the middle price of the RMB to USD exchange rate and the Shanghai Composite Index from exchange rate to stock price;2) The central parity rate between the Chinese yuan and the US dollar has a positive impact on the Shanghai Composite Index. That is, when the exchange rate rises, stock prices rise, exchange rates fall, and stock prices fall, but the impact of stock price fluctuations on the exchange rate is not significant. Finally, based on the conclusions of empirical analysis, targeted policies and recommendations were proposed.展开更多
文摘股票市场的波动会影响人们生活的各个方面,因此准确预测股票价格具有重要意义。然而,传统的时间序列预测模型(如ARIMA)在处理股票价格中的非线性特征时表现不佳,难以获得令人满意的预测效果。鉴于深度学习在处理非线性问题上的优越能力,它在股票价格预测中展现出巨大的潜力。本文提出了一种ARIMA-CNN-LSTM混合模型来预测股票价格,该模型充分挖掘了股票市场的历史信息,从而实现更高精度的预测。首先,使用ARIMA对股票数据进行预处理,将处理得到的残差序列输入CNN,通过卷积提取股票数据的深层特征;随后,通过LSTM挖掘股票数据的长期时间序列特征。本文以中国银行2009年1月1日至2023年12月31日的股票数据为研究对象,构建混合模型,并与ARIMA-LSTM模型、CNN-LSTM模型的预测结果进行对比。实验结果表明,本文提出的混合模型预测精度更高,相较于ARIMA-LSTM与CNN-LSTM模型,本模型在均方误差(MSE)指标上分别降低了25%与16.7%,在平均绝对误差(MAE)指标上分别降低了14.1%与9.4%,展示了更好的预测效果。The volatility of the stock market affects various aspects of people’s lives, making accurate stock price predictions highly significant. However, traditional time series forecasting models, such as ARIMA, perform poorly when dealing with the nonlinear characteristics of stock prices, leading to unsatisfactory prediction outcomes. Given the superior capability of deep learning in handling nonlinear problems, it shows great potential in stock price prediction. This paper proposes a hybrid ARIMA-CNN-LSTM model for stock price prediction, which fully exploits historical market information to achieve higher prediction accuracy. First, ARIMA is used to preprocess the stock data, with the resulting residual series fed into a CNN, which extracts deep features of the stock data through convolution. Subsequently, LSTM is employed to capture the long-term temporal characteristics of the stock data. Using the stock data of the Bank of China from January 1, 2009, to December 31, 2023, as the research object, the hybrid model is constructed and compared with the prediction results of the ARIMA-LSTM model and CNN-LSTM model. The experimental results show that the proposed hybrid model achieves higher prediction accuracy. Compared to the ARIMA-LSTM and CNN-LSTM models, this model reduces the mean squared error (MSE) by 25% and 16.7%, respectively, and decreases the mean absolute error (MAE) by 14.1% and 9.4%, respectively, demonstrating better forecasting performance.
文摘本文基于弹性网络回归模型对股票价格进行了预测分析。通过收集国内某酒厂738个交易日的数据,选取开盘价、最高价、最低价、交易量、涨跌幅等作为自变量,以收盘价为因变量,分别应用线性回归、岭回归、Lasso回归及弹性网络回归四种模型进行预测分析。研究结果表明,弹性网络回归模型在处理多重共线性问题和变量筛选方面具有显著优势。通过交叉验证确定了最优的惩罚参数,使得模型的预测误差最小。最终,最高价、最低价、交易量和涨跌幅被筛选为影响股票收盘价的主要因素。本文的研究为股票价格预测提供了有效的方法和工具,并为金融市场的投资决策提供了重要参考。This study conducts a stock price prediction analysis based on the Elastic Net regression model. Using data from 738 trading days of a domestic brewery, the study selects opening price, highest price, lowest price, trading volume, and price change percentage as independent variables, with the closing price as the dependent variable. Four models are applied for prediction analysis: linear regression, ridge regression, Lasso regression, and Elastic Net regression. The results show that the Elastic Net regression model has significant advantages in handling multicollinearity issues and variable selection. The optimal penalty parameters are determined through cross-validation, minimizing the prediction error. Ultimately, the highest price, lowest price, trading volume, and price change percentage are identified as the key factors influencing stock closing prices. This research provides an effective method and tool for stock price prediction and offers important insights for financial market investment decisions.
文摘在全球化日益深入的今天,国际间的贸易越来越多,汇率对一国经济的影响也越来越重。而股票市场作为宏观经济的晴雨表,是资产市场的重要组成部分,其受宏观经济的影响是非常剧烈而且直接的。本文选取2009~2023年人民币兑美元汇率中间价、上证综合指数和进出口贸易差额,建立向量自回归模型进行分析,通过Johansen协整检验和格兰杰因果检验等,得出结论:1) Johansen协整检验结果说明人民币兑美元汇率中间价和上证综合指数之间存在从汇率到股票价格的长期协整关系;2) 人民币兑美元汇率中间价对上证综合指数有着一个正向的影响。也就是汇率上升,股票价格上升,汇率下降,股票价格下降,但是股价的变动对汇率的影响不显著。最后根据实证分析的结论,提出了有针对性的政策与建议。In today’s increasingly globalized world, international trade is increasing, and the impact of exchange rates on a country’s economy is also becoming increasingly significant. As a barometer of macroeconomics, the stock market is an important component of the asset market, and its impact from macroeconomics is very severe and direct. This article selects the middle price of the RMB to USD exchange rate, the Shanghai Composite Index, and the import and export trade balance from 2009 to 2023, and establishes a vector autoregressive model for analysis. Through Johansen cointegration test and Granger causality test, the following conclusions are drawn: 1) The Johansen cointegration test results indicate that there is a long-term cointegration relationship between the middle price of the RMB to USD exchange rate and the Shanghai Composite Index from exchange rate to stock price;2) The central parity rate between the Chinese yuan and the US dollar has a positive impact on the Shanghai Composite Index. That is, when the exchange rate rises, stock prices rise, exchange rates fall, and stock prices fall, but the impact of stock price fluctuations on the exchange rate is not significant. Finally, based on the conclusions of empirical analysis, targeted policies and recommendations were proposed.
