SVM与神经网络模型在股票预测中的应用研究

介绍了SVM、BP神经网络和小波神经网络模型在股票预测中的应用研究。通过输入历史股票价格走势数据进行模型训练,并分别进行三个模型预测输出,最后通过均方误差、走势方向准确率和总盈利率三个指标分析比较三个模型,从而了解模型在股票预测领域的应用效果,为后续研究做参考。     

一种基于遗传BP神经网络的预测模型

目前神经网络常用于数据挖掘及金融预测中,提出了一个改进的稳定且高效的遗传BP神经网络预测模型.在该模型中提出了一种能够真实反映BP网络结构的编码,并对二进制编码与实数进行映射而不改变染色体的表达方式,以便更好地进行杂交变异.同时还提出了一种更能准确地反映网络误差的误差函数,它是利用相对误差并综合其他相关因素来定义的,通过实验对比分析,该误差函数使预测更加准确.最后,从编码方式以及网络误差出发提出了相应的遗传算法的适应度函数.实验中对股票及其他数据进行了测试,并与其他的预测模型进行了对比分析.通过实验表明,提出的遗传BP神经网络模型适用于长趋式预测,同时预测结果准确率高.     

时态神经网络模型及其在股票分类预测上应用

对具有时间属性的数据进行数据挖掘称为时态数据挖掘，用以发现数据在时间上的知识，当数据变化不规律时，如股票交易数据,就很难发现有价值的规律与规则。而神经网络具有并行、容错、可以硬件实现以及自我学习的优点,可作为股票分类预测应用的一种方法。通过将股票数据与时态型相结合，将股票数据转换成时态型股票数据，提出时态神经网络模型的分类方法，对收集的若干上市公司十年内的股票数据进行分析，构建了时态股票数据神经网络分类器对股票进行分类预测。经过实验验证，相比改进前的神经网络和支持向量机方法，该分类器具有更高的分类准确率。结果证明，这种时态数据神经网络模型对于多只股票的分类预测是非常有效的，可以很好地运用到股票市场的分类预测中。     

基于LSTM神经网络的短期价格趋势预测

本文主要对LSTM模型结构改进及优化其参数,使其预测股票涨跌走势准确率明显提高,同时对美股周数据及日数据在LSTM神经网络预测效果展开研究.一方面通过分析对比两者预测效果差别,验证不同数据集对预测效果的影响;另一方面为LSTM股票预测研究提供数据集的选择建议,以提高股票预测准确率.本研究通过改进后的LSTM神经网络模型使用多序列股票预测方法来进行股票价格的涨跌趋势预测.实验结果证实,与日数据相比,周数据的预测效果表现更优,其中日数据的平均准确率为52.8%,而周数据的平均准确率为58%,使用周数据训练LSTM模型,股票预测准确率更高.     

改进的XGBoost模型在股票预测中的应用

随着时代的不断进步，人民生活水平日益提高。在解决温饱问题之余，有了可供投资的余财。越来越多的人将目光转向股市投资，为股市发展提供了资金条件。然而在纷繁复杂的股票市场，如何寻找最优股成为亟待解决的问题。这不仅是投资者单方面的困惑，也是股票预测领域中学者们所关心的重点。通过网格搜索算法对XGBoost模型进行参数优化构建GS-XGBoost的金融预测模型，并将该模型运用于股票短期预测中。分别以中国平安、中国建筑、中国中车、科大讯飞和三一重工2005年4月至2018年12月28日的每日收盘价作为实验数据。通过实验对比，相较于XGBoost原模型、GBDT模型以及SVM模型，GS-XGBoost模型在MSE、RMSE与MAE三个评价指标上都表现出较好的预测结果。从而验证，GS-XGBoost金融预测模型在股票短期预测中具有更好的拟合性能。     

基于NLP的股票选择策略的优化研究

由于股评、新闻对股票价格变化有巨大影响,为选出优质股票以提高投资的收益率,采用了自然语言处理NLP技术对股评数据和新闻数据进行分析,基于朴素贝叶斯模型建立了文本情感倾向分类模型,模型预测准确率达到84%,生成了股评因子。基于LDA主题模型对新闻文本进行话题建模,快速获取新闻文本主题,并引入困惑度寻找文档最优主题数,生成了新闻因子,将股评因子和新闻因子作为筛选股票的依据,从股评和新闻信息中获取对股市带来的影响因素,从而优化选股策略。对于股票基本面数据,采用决策树模型进行因子的重要性分析,选出重要性最高的前5个因子,模型预测准确率达到88%。通过决策树模型,可以更准确地确定哪些因子在影响股价变化方面发挥着关键作用,这种改进的方法能够提高选股策略的有效性和准确性。最终使用主成分分析（PCA）对数据进行降维处理,依据主成分数值的高低来进行股票选择。     

基于深度学习的股票趋势预测算法

针对股票趋势预测难的问题,提出一种利用CNN和LSTM进行特征提取,并结合注意力机制和对抗训练的股票趋势预测算法——AACL（Adversarial Attentive CNN-LSTM）算法。该算法利用CNN提取股票的整体趋势信息,LSTM提取股票的短期波动信息,并通过注意力机制将多个股票联系起来,捕捉股票之间的涨跌关系。算法还引入了对抗训练,通过对数据进行干扰,提高算法的鲁棒性。为了验证算法的有效性,在KDD17、ACL18和China50这3个数据集上进行实验,并与现有的算法进行比较,实验结果表明本文提出的算法可以获得最优的预测效果。     

文化算法在股票数据建模中的应用

数据预测在金融投资领域占有重要地位,而股票价格是金融数据中最复杂的数据类型之一。本文将文化算法应用于股票指数建立时间序列模型,并且针对股票数据的特点,选择适应股票规律的文化算法模型,并与线性回归算法得到的数据结果进行了对比分析,以此来分析文化算法在该问题应用上的优劣。实验结果表明,利用文化算法模型进行预测取得了较好的结果,其预测精度较高,预测的相对误差在3%以内,涨跌分析正确率在70%以上。     

基于组合模型的股票停牌预测研究

针对股票的无规律性停牌和长时间停牌的问题,采用机器学习相关技术,提出了股票停牌预测的组合模型,选取财务和股票两方面的指标作为数据,通过计算各个指标的重要性进行筛选,并划分出多个特征数据集,进而完成多个分类子模型的学习,形成子模型池,系统随机抽取多个子模型进行分类,并通过投票法得到最终的预测结果。实证分析以中国上市公司为研究对象,结果表明组合模型预测取得了较高的准确率,与单一模型相比在误报率和漏报率上有较大的改进。     

基于隐马尔可夫模型的股票价格预测组合模型

提出了一种用于股票价格预测的人工神经网络(ANN),隐马尔可夫模型(HMM)和粒子群优化算法(PSO)的组合模型-APHMM模型.在APHMM模型中,ANN算法将股票的每日开盘价、最高价、最低价与收盘价转换为相互独立的量并作为HMM的输入.然后,利用PSO算法对HMM的参数初始值进行优化,并用Baum-Welch算法进行参数训练.经过训练后的HMM在历史数据中找出一组与今天股票的上述4个指标模式最相似数据,加权平均计算每个数据与它后一天的收盘价格差,则今天的股票收盘价加上这个加权平均价格差便为预测的股票收盘价.实验结果表明,APHMM模型具有良好的预测性能.     

一种多源数据驱动的自动交易系统决策模型

股票自动交易系统属于典型的复杂系统,其成功的关键是如何对股价进行有效的预测与决策.股价受多种信息的影响,但传统的自动交易模型多建立在历史交易数据的基础上.针对上述问题,本文综合利用新闻文本数据与股价技术指标数据,基于人工神经网络（Artificial neural netuorks,ANN）方法设计了一种多源数据驱动的股票自动交易决策模型.本文首先分析了各类财经新闻的特点及其对股价的影响,然后设计了相应模板抽取了中文文本中的财经新闻事件;在此基础上,设计了历史股价和新闻事件数据共同驱动的ANN-News模型,并利用实际数据验证了模型的有效性.实验发现,ANN-News模型比传统的机器学习类模型股价预测准确率提升约4%,收益率提升约7%.     

Forecasting the volatility of a combined multi‐country stock index using GWMA algorithms

Globalization has increased the volatility of international financial transactions, particularly those related to international stock markets. An increase in the volatility of one country's stock market spreads throughout the globe, affecting other countries' stock markets. In particular, the Dow Jones Industrial Average plays an extremely important role in the international stock market. This paper uses the generally weighted moving average method and data from the Dow Jones Industrial Average, the National Association of Securities Dealers Automated Quotations, Japan's Nikkei 225, the Korea Composite Stock Price Index, and the Hong Kong Hang Seng Index to predict the performance of the Taiwan Capitalization Weighted Stock Index. This paper attempts to find the smallest prediction error using the optimal combination of generally weighted moving average model parameters and combinations of various international stock market data and compares the results to that found using the exponentially weighted moving average model to explore differences between the two types of forecasting models.     

基于深度迁移学习的多尺度股票预测

股票市场不仅是上市公司的重要融资渠道,也是重要的投资市场,股票预测一直受到人们的关注。为了充分利用来自不同股票价格的信息,提高股票的预测效果,提出一种多尺度股票价格预测模型TL-EMD-LSTM-MA（TELM）。TELM模型通过经验模态分解将收盘价分解为多个时间尺度分量,不同时间尺度分量震荡频率不同,反映了不同的周期性信息;根据分量的震荡频率选择不同方法进行预测,高频分量利用深度迁移学习的方法训练堆叠LSTM,低频分量利用移动平均法进行预测;将所有分量的预测值相加作为收盘价的最终预测输出。通过深度迁移学习训练的堆叠LSTM,包含来自不同股票的信息,具备更多行业或市场的知识,能有效降低预测误差。利用移动平均法预测低频分量,更有效捕获股票的总体趋势。对中国A股市场内500支股票以及上证指数、深证成指等指数进行预测,结果表明,与其他模型相比,TELM预测误差最低,拟合优度最高。根据TELM预测的股票收盘价模拟股票交易过程,结果表明TELM投资风险低、收益高。     

基于遗传神经网络的股票价格短期预测

该文在总结非线性时间序列预测模型的基础上,将遗传算法和人工神经网络相结合,提出了遗传神经网络模型。并将其应用到股票价格的短期预测。最后,针对仿真结果进行分析,该文得到的结果为平均相对误差小于0.086,实际值与预测值之间的相关系数大于0.91。结果表明该模型有较好的预测能力。     

基于多视图注意力机制的多维度价格预测模型研究

传统的股票价格预测模型只针对单一维度价格进行预测,忽略了多维度价格之间的复杂关系。因此,为了更好地对股票价格进行准确预测和为决策者提供前瞻性信息,提出了一种新的基于多视图注意力机制的多维度价格预测模型。通过多视图的深度可分离卷积网络学习多维度股票价格潜在的复杂的输入—输出关系,更好地提取股票价格的时空特征,实现时空数据的智能关联,并使用注意力机制进一步提升模型的预测性能,进而通过时空多维度的股价历史数据来预测单和多时间步长股票价格。该模型与其他四种模型在中国银行股价数据集上进行实验和比较,发现所提模型在不同预测时长下相比于表现最好的模型,平均绝对误差分别降低了0.4%、0.5%、4.2%、3.9%,均方误差分别降低了0.8%、2%、1.9%、1.9%,平均百分比误差分别降低了0.15%、0.21%、1.24%和1.34%。因此所提模型预测精度最高,预测性能最好,并且在对其他维度的股票价格预测上具有普适性。     

A Naïve SVM-KNN based stock market trend reversal analysis for Indian benchmark indices

This paper proposes a hybridized framework of Support Vector Machine (SVM) with K-Nearest Neighbor approach for Indian stock market indices prediction. The objective of this paper is to get in-depth knowledge in the stock market in Indian Scenario with the two indices such as, Bombay Stock Exchange (BSE Sensex) and CNX Nifty using technical analysis methods and tools such as predicting closing price, volatility and momentum of the stock market for the available data. This hybrid model uses SVM with different kernel functions to predict profit or loss, and the output of SVM helps to compute best nearest neighbor from the training set to predict future of stock value in the horizon of 1 day, 1 week and 1 month. The proposed SVM and KNN based prediction model is experienced with the above mentioned distinguished stock market indices and the performance of proposed model has been computed using Mean Squared Error and also been compared with recent developed models such as FLIT2NS and CEFLANN respectively. The limitation of both of those existing models undergoes complex weight updating procedures, whereas, proposed SVM-KNN hybridized model scales relatively well to high dimensional data and the trade-off between classifier complexity and error can be controlled explicitly and have better prediction capability.     

An integrated framework of genetic network programming and multi-layer perceptron neural network for prediction of daily stock return: An application in Tehran stock exchange market

Evolutionary algorithms are generally used to find or generate the best individuals in a population. Whenever these algorithms are applied to agent systems, they will lead to optimal solutions. Genetic Network Programming (GNP), which contains graph networks, is one of the developed evolutionary algorithms. When the aim is to forecast the share price or return, ascending and descending trends, volatilities, recent returns, fundamental and technical factors have remarkable impacts on the prediction. This is why technical indicators are used to constitute a set of trading rules. In this paper, we apply an integrated framework consisting of GNP model along with a reinforcement learning and Multi-Layer Perceptron (MLP) neural network to classify data and also time series models to forecast the stock return. Moreover, we utilize rules of accumulation based on the GNP model’s results to forecast the return. The aim of using these models alongside one another is to estimate one-day return. The results derived from 9 stocks with regard to the Tehran Stock Exchange Market. GNP extracts a prodigious number of rules on the basis of 5 technical indicators with 3 times period. Next, MLP network classifies data and finds the similarity between future data and past data concerning a stock (5 sub-period) through classification. Subsequently, a number of conditions are established, in order to choose the best estimation between GNP-RL and ARMA. Distinct comparison with the ARMA–GARCH model, which is operated for return estimation and risk measurement in many researches, demonstrates an extended forecasting power of the proposed model, by the name of GNP–ARMA, reducing error by a mean of 16%.     

Stock Trading Using RSPOP: A Novel Rough Set-Based Neuro-Fuzzy Approach

This paper investigates the method of forecasting stock price difference on artificially generated price series data using neuro-fuzzy systems and neural networks. As trading profits is more important to an investor than statistical performance, this paper proposes a novel rough set-based neuro-fuzzy stock trading decision model called stock trading using rough set-based pseudo outer-product (RSPOP) which synergizes the price difference forecast method with a forecast bottleneck free trading decision model. The proposed stock trading with forecast model uses the pseudo outer-product based fuzzy neural network using the compositional rule of inference [POPFNN-CRI(S)] with fuzzy rules identified using the RSPOP algorithm as the underlying predictor model and simple moving average trading rules in the stock trading decision model. Experimental results using the proposed stock trading with RSPOP forecast model on real world stock market data are presented. Trading profits in terms of portfolio end values obtained are benchmarked against stock trading with dynamic evolving neural-fuzzy inference system (DENFIS) forecast model, the stock trading without forecast model and the stock trading with ideal forecast model. Experimental results showed that the proposed model identified rules with greater interpretability and yielded significantly higher profits than the stock trading with DENFIS forecast model and the stock trading without forecast model.     

Application of wrapper approach and composite classifier to the stock trend prediction

The research on the stock market prediction has been more popular in recent years. Numerous researchers tried to predict the immediate future stock prices or indices based on technical indices with various mathematical models and machine learning techniques such as artificial neural networks (ANN), support vector machines (SVM) and ARIMA models. Although some researches in the literature exhibit satisfactory prediction achievement when the average percentage error and root mean square error are used as the performance metrics, the prediction accuracy of whether stock market goes or down is seldom analyzed. This paper employs wrapper approach to select the optimal feature subset from original feature set composed of 23 technical indices and then uses voting scheme that combines different classification algorithms to predict the trend in Korea and Taiwan stock markets. Experimental result shows that wrapper approach can achieve better performance than the commonly used feature filters, such as χ²-Statistic, Information gain, ReliefF, Symmetrical uncertainty and CFS. Moreover, the proposed voting scheme outperforms single classifier such as SVM, kth nearest neighbor, back-propagation neural network, decision tree, and logistic regression.     

Predicting stock index increments by neural networks: The role of trading volume under different horizons

Recent studies show that there is a significant bidirectional nonlinear causality between stock return and trading volume. In this research, we reinforce this statement and the results presented in some earlier literatures and further investigate whether trading volume can significantly improve the prediction performance of neural networks under short-, medium-and long-term forecasting horizons. An application of component-based neural networks is used in forecasting one-step ahead stock index increments. The models are also augmented by the addition of different combinations of indices’ and component stocks’ trading volumes as inputs to form more general ex-ante forecasting models. Neural networks are trained with the data of stock returns and volumes from NASDAQ, DJIA and STI indices. Results indicate that augmented neural network models with trading volumes lead to improvements, at different extents, in forecasting performance under different terms of forecasting horizon. Empirical results indicate that trading volumes lead to modest improvements on the performance of stock index increments prediction under medium-and long-term horizons.