ARIMA和RBF神经网络相融合的股票价格预测研究

针对股票价格的突变性、非线性和随机性,单一预测方法仅能描述股票价格片断信息等缺陷,提出一种股票价格组合预测模型。采用自回归移动平均模型（ARIMA）对股票价格进行预测,捕捉股票价格线性变化趋势。采用RBF神经网络对非线性、随机变化规律进行预测。将两者结果组合得到股票价格预测结果。采用组合模型对包钢股份（600010）股票收盘价进行仿真实验,结果表明,相对于单一预测模型,组合预测模型更加全面、准确刻画了股票价格的变化规律,提高了股票价格预测精度。     

基于组合预测模型的股票价格趋势预测

针对股票市场高度非线性的特点,单一预测模型很难描述出股票价格趋势的整体特征,提出了一种金融时序预测的组合预测模型。首先,利用自回归移动模型(ARIMA)对股票价格线性趋势进行预测。然后,利用回归支持向量机(SVR)模型对非线性随机变化规律进行预测。最后,采用模糊时变权重方式对两种模型进行结合,得到一种综合考虑股票价格线性和非线性的预测模型。仿真结果显示,组合预测模型取得了令人满意的效果。     

时变β系数的卡尔曼滤波的仿真与估计

旨在预测风险系数,我们对沪市10个行业的β系数的时变行为采用随机游走（RW）模型,在随机游走模型的回归变量前引进了未知参数,仿真预测的结果表明,引进未知系数后的模型,其绝对预测误差MAE和均方预测误差MSE都比引进未知系数前的模型更精确,改后的模型更适合描述沪市行业风险系数的时变行为。仿真过程是通过卡尔曼滤波的递推过程获取新息及其协方差阵,得到似然函数,从而推进参数估计。将估计的结果返回卡尔曼滤波更新过程,易得观测变量的预测值。     

基于经验模态分解与投资者情绪的长短期记忆网络股票价格涨跌预测模型

针对传统的基于统计学的回归股票预测模型难以表征多个变量之间的关系,预测出的股票价格趋势误差较大,提出一种基于经验模态分解（EMD）与投资者情绪的长短期记忆（LSTM）神经网络股票价格涨跌预测模型。首先,将股票收盘价通过EMD分解得到若干个具有不同时间尺度的局部特征信号的本征模函数（IMF）;其次,通过引入改进的股票领域情感词典,对东方财富网股吧的帖子,进行上一个股票交易日收盘后和下一个股票交易日开盘前的投资者情感分析,得到下一个股票交易日的投资者情绪指标;最后,将基础的股票基本行情数据、经过EMD得到的IMF以及投资者情绪指标加入LSTM神经网络预测下一个交易日的股票涨跌。仿真实验结果表明,在2019年1月至2021年9月的牧原股份（002714）股票数据上,与单独使用LSTM模型相比,改进后的LSTM模型的预测准确率提高了12.25个百分点,在预测为涨的F1值和预测为跌的F1值上分别提高了1.2个百分点和25.21个百分点。由此可见,基于EMD与投资者情绪的LSTM股票价格涨跌预测模型有效提高了预测精度,为股票市场的涨跌预测提供了一种有效的实验方法。     

组合模型在股票价格预测中应用研究

研究股票价格预测问题,针对股票价格的影响因子之间存在高度冗余、非线性特点,从而导致传统方法预测准确率低的难题,为提高预测精度,提出一种支持向量机(SVM)和自回归(CAR)组合的股票价格预测方法(CAR-SVM).CAR-SVM首先利用SVM对股票价格数据时滞阶数进行确定,然后用SVM对股票价格变化影响因素进行筛选,建立通过交叉验证得到股票价格的CAR-SVM预测模型,并以中兴通讯股票历史数据对CAR-SVM模型进行了验证性实验.实验结果表明,相对于传统的股票预测方法,CAR-SVM模型的预测精度更高,并更能反映股票价格变化的非线性动态规律,在股票价格预测中有着广泛的应用前景.     

静态图像中采用混合卷积结构进行人群密度估计

提出了一种混合卷积神经网络用于人群数量的感知计算,在高度密集的场景中可以准确地预测人群密度图。模型仅由两个部分组成：前端为扩张卷积神经网络提取二维特征;后端采用分数步长卷积神经网络降低下采样中的信息损失。为了验证和分析算法性能,模型设计基于当前较为流行的Shanghai Tech数据集,使用回归问题的评价指标,即平均绝对误差（MAE）和均方误差（MSE）作为评估算法性能的标准。在Shanghai Tech（MAE=100.8）、UCF_CC_50（MAE=305.3）与WorldExpo’10数据集上进行测试,实验表明模型在密集场景下较以往的方法有效降低了MAE和MSE,提高了密集人群计数的准确率。     

基于梯度提升回归模型的生猪价格预测

研究生猪价格的准确预测问题,传统预测模型存在速度慢、陷入局部极小值、核函数的选择等问题,预测效果不佳。为此,首先筛选出生猪价格的显著因素,接着利用Python数据分析分别建立贝叶斯岭回归、普通线性回归、弹性网络和支持向量机模型,将这4个回归模型作为梯度提升回归模型的训练集,对生猪价格进行预测。结果表明,综合集成的梯度提升回归模型的均方差(MSE)为0.056,平均绝对误差(MAE)为0.18,判定系数为0.994,比前面单一模型预测效果好。最后,利用梯度提升回归模型对2017年2月至2017年11月的生猪价格预测,发现输出的预测值与真实值比较接近,最大相对误差为3.495%,梯度提升回归模型具有较高的预测精度。     

一种基于ARIMA和LSTM的民航旅客订座组合预测模型

针对民航旅客订座预测问题,提出一种组合预测模型。首先,根据订座特性,设计缺失值、噪声数据预处理方法,使得历史订座数据得到有效校正。然后,为了提高预测准确性,建立自回归求积移动平均模型（ARIMA）以及基于特征选取长短时记忆网络（LSTM）的组合预测模型,并利用某航空公司实际订座数据,将该组合模型应用于旅客订座预测场景中,实验结果表明,本文提出的组合模型的MAE值、RMSE值均小于2个单项模型,预测结果更准确。     

基于机器学习的肿瘤免疫治疗应答预测研究

肿瘤免疫治疗应答的预测对肿瘤治疗方案设计及治疗有着重要的意义。本文引入基于随机森林的机器学习方法,将病人黑色素瘤组织转录组RNA-seq的基因表达谱作为特征,对免疫检查点阻断治疗的结果进行预测研究。对病人的基因表达谱使用随机森林算法来构建预测模型,并与Logistic回归模型和XGBoost模型进行比较。实验结果表明,随机森林模型对免疫检查点阻断治疗的应答能够进行较准确的预测,并且较Logistic回归模型和XGBoost模型预测效果更好。     

二次指数平滑多目标组合模型电力负荷预测

为提高短期电力负荷预测精度,提出一种二次指数平滑多目标组合模型ES-BiLSTM-LSTM预测方法。通过获取负荷目标预测值和残差目标预测值,实现多目标负荷预测;利用Pearson相关系数,选取与电力负荷相关性较高的影响因素;采用双向长短期记忆神经网络(BiLSTM)和长短期记忆神经网络(LSTM)串行学习负荷数据的时序性特征和周期性特征;利用二次指数平滑法平滑处理负荷数据,获得残差项,通过LSTM模型训练和迭代,提取残差数据的波动性特征;将负荷预测值与残差预测值融合得到修正预测值。实验结果表明,该方法在MAE、MSE和RMSE上,对比3种负荷预测模型均有提升。     

基于EMD改进的Elman神经网络对股票的短期预测模型

Elman神经网络在短期预测股市收盘价时存在预测趋势良好但准确度较低的问题。在Elman神经网络的思想上提出以经验模态分解EMD为基础的Elman新组合模型。应用EMD将各交易日的收盘价序列分解成不同时间尺度上的本征模函数IMF分量和剩余分量,进而利用偏自相关函数PACF计算每一个分量的滞后期,以确定各分量在Elman神经网络中的输入和输出变量,从而得到各分量的预测值,相加得到最终的预测结果。与EMD单一网络、EMD-Elman模型、BP网络及EMD-BP模型进行实验对比,结果表明:该短期预测模型的预测值均方误差、平均绝对误差和平均绝对百分比误差都得到较大的改善;新组合模型可有效实现对股票收盘价的短期预测,且能降低非平稳性对预测结果的影响。该研究为进一步预测股市的走向提供了有效依据,也为投资者提供了更充分的决策参考。     

Stock price prediction based on LSTM and LightGBM hybrid model

Finding an accurate, stable and effective model to predict the rise and fall of stocks has become a task increasingly favored by scholars. This paper proposes a long short-term memory (LSTM) network based on Pearson's correlation coefficient and a Bayesian-optimized LightGBM hybrid model, named as LSTM-BO-LightGBM, to solve the problem of stock price fluctuation prediction. The multilayer bidirectional LSTM-BO-LightGBM prediction model is compared with the LSTM-BO-XGBoost hybrid model, the LSTM-LightGBM hybrid model, the LSTM-XGBoost hybrid model, the single LSTM network model and the RNN network model. The prediction result of the LSTM-BO-LightGBM model for the "ES?=?F" stock is an RMSE value of 596.04, MAE value of 15.24, accuracy value of 0.639 and f1_score value of 0.799, which are improved compared with the prediction results of the other five models. At the same time, when applying the model to "YM?=?F", "CL?=?F", "^TNX", "^N225", "NQ?=?F", "AAPL", "GC?=?F", "JPY?=?X" and "SI?=?F", all of the nine stocks showed good forecasting performance. The results demonstrate that the multilayer bidirectional LSTM-BO-LightGBM model proposed in this paper has better approximation ability and generalization ability in the stock fluctuation forecast than previous models and can well fit the stock fluctuation.

     

基于Pytorch的LSTM模型对股价的分析与预测

股价预测一直都是股票投资者重点关注和重点研究的方向,针对股价具有高度非线性、高噪声、动态性等问题,提出一种基于自组织特征映射(SOM)神经网络和长短期记忆网络(LSTM)共同应用的股价预测方法。第一步聚类,使用python语言实现改进的自组织特征映射神经网络算法,将187支股票分成三类,三类股票以盈利能力大小进行聚类,并且求出每一类所包含的股票代码;第二步预测,基于Pytorch深度学习框架构造长短期记忆网络模型,分别对每一类中随机的3支股票进行股价预测,再通过均方误差和决定系数对预测结果进行评价。结果表明,在使用相同的预测模型对不同盈利能力的股票做股价预测时,盈利能力越大的股票,预测精度越高。此研究可以为投资者筛选出盈利能力更大的股票,并且在提高股价预测精度上也具有一定的贡献。     

最优组合模型在证券市场预测中的应用研究

研究证券市场预测中的股票价格预测精度问题,股票价格受到政治、经济、投资者心理等多种因素影响,股票价格波动较大,系统具有非线性复杂变化规律,单一预测模型只能反映股票价格变化时段信息,预测精度比较低。为了提高股票价格预测精度,提出一种组合模型的股票价格预测方法。首先分别采用ARIMA、GM、RBF神经网络对股票价格进行预测,然后通过权重值获得最优组合预测模型进行股票价格预测。结果表明,组合预测模型提高了股票价格预测精度,降低了预测误差,克服了单一预测模型在股票价格预测中的缺陷,为股票价格等非线性系统准确性预测提供了参考依据。     

基于改进回声状态神经网络的个股股价预测

当今社会股价预测是研究的热门问题,人们越来越关注对股价预测模型的建立,提高股价预测的精度对股票投资者有实际的应用价值.目前股价的预测方法层出不穷,其中较为典型的有传统的技术分析和ARMA模型等.为了提升预测的精度,同时考虑到股市的非线性,本文提出一种改进的回声状态神经网络的个股股价预测模型,针对回声状态神经网络(ESN)泛化能力不强的特点,应用改进的粒子群算法(GTPSO)对回声状态神经网络(ESN)的输出连接权进行搜索,最终得到最优解,即ESN的最优输出连接权,GTPSO算法概括来说就是在传统粒子群算法(PSO)的基础上引入禁忌搜索算法(TS)中禁忌的思想和遗传算法(GA)中变异的思想,从而降低PSO在学习过程中陷入局部最小值的状况,同时提高PSO搜寻全局的能力.将预测模型用于个股每日收盘价预测中,使用每10天的收盘价预测第11天的收盘价.通过实验验证了模型的正确性,实验证实,该模型拥有较好的预测效果.     

纠正学习策略下LightGBM-GRU模型的股票波动率预测

为提高传统智能算法进行时间序列预测时的精度和解决工程数据问题时的适应性,提出一种纠正学习策略。波动性广泛应用于金融领域,对股票的波动性进行预测具有重要的价值。由于股票价格的时间序列是非线性和非平稳的,预测股票市场波动成为时间序列预测中的难点。本文通过纠正学习策略进行仿真实验,设计出LightGBM-GRU模型,以LightGBM和GRU作为基模型和纠正器,预测3年内126只来自不同行业的股票在未来10 min的波动率,根据RMSPE、MAE、MSE、RMSE等指标表明：即使经典的效果比较好的集成学习模型,也能通过纠正学习策略同时提高精度和泛化能力。本文指出在算法富集和大数据的时代,智能算法的矛盾转变为智能算法通用性有限与工程问题多样性之间的矛盾,纠正学习策略可以为数据仿真提供新思路。     

Stock trend prediction based on a new status box method and AdaBoost probabilistic support vector machine

Stock trend prediction is regarded as one of the most challenging tasks of financial time series prediction. Conventional statistical modeling techniques are not adequate for stock trend forecasting because of the non-stationarity and non-linearity of the stock market. With this regard, many machine learning approaches are used to improve the prediction results. These approaches mainly focus on two aspects: regression problem of the stock price and prediction problem of the turning points of stock price. In this paper, we concentrate on the evaluation of the current trend of stock price and the prediction of the change orientation of the stock price in future. Then, a new approach named status box method is proposed. Different from the prediction issue of the turning points, the status box method packages some stock points into three categories of boxes which indicate different stock status. And then, some machine learning techniques are used to classify these boxes so as to measure whether the states of each box coincides with the stock price trend and forecast the stock price trend based on the states of the box. These results would support us to make buying or selling strategies. Comparing with the turning points prediction that only considered the features of one day, each status box contains a certain amount of points which represent the stock price trend in a certain period of time. So, the status box reflects more information of stock market. To solve the classification problem of the status box, a special features construction approach is presented. Moreover, a new ensemble method integrated with the AdaBoost algorithm, probabilistic support vector machine (PSVM), and genetic algorithm (GA) is constructed to perform the status boxes classification. To verify the applicability and superiority of the proposed methods, 20 shares chosen from Shenzhen Stock Exchange (SZSE) and 16 shares from National Association of Securities Dealers Automated Quotations (NASDAQ) are applied to perform stock trend prediction. The results show that the status box method not only have the better classification accuracy but also effectively solve the unbalance problem of the stock turning points classification. In addition, the new ensemble classifier achieves preferable profitability in simulation of stock investment and remarkably improves the classification performance compared with the approach that only uses the PSVM or back-propagation artificial neural network (BPN).     

Maximum and minimum stock price forecasting of Brazilian power distribution companies based on artificial neural networks

Time series forecasting has been widely used to determine future prices of stocks, and the analysis and modeling of finance time series is an important task for guiding investors’ decisions and trades. Nonetheless, the prediction of prices by means of a time series is not trivial and it requires a thorough analysis of indexes, variables and other data. In addition, in a dynamic environment such as the stock market, the non-linearity of the time series is a pronounced characteristic, and this immediately affects the efficacy of stock price forecasts. Thus, this paper aims at proposing a methodology that forecasts the maximum and minimum day stock prices of three Brazilian power distribution companies, which are traded in the São Paulo Stock Exchange BM&FBovespa. When compared to the other papers already published in the literature, one of the main contributions and novelty of this paper is the forecast of the range of closing prices of Brazilian power distribution companies’ stocks. As a result of its application, investors may be able to define threshold values for their stock trades. Moreover, such a methodology may be of great interest to home brokers who do not possess ample knowledge to invest in such companies. The proposed methodology is based on the calculation of distinct features to be analysed by means of attribute selection, defining the most relevant attributes to predict the maximum and minimum day stock prices of each company. Then, the actual prediction was carried out by Artificial Neural Networks (ANNs), which had their performances evaluated by means of Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) calculations. The proposed methodology for addressing the problem of prediction of maximum and minimum day stock prices for Brazilian distribution companies is effective. In addition, these results were only possible to be achieved due to the combined use of attribute selection by correlation analysis and ANNs.     

基于模糊近似支持向量回归的股价预测研究

股价预测是投资策略形成和风险管理模型发展的基础。为了降低股价变化趋势中的噪声信息和投资者关于两种股价预测误差的不同偏好对股价预测的影响,提出了基于信噪比的模糊近似支持向量回归(FPSVR)的股价预测模型。首先构建信噪比输入变量,然后引入模糊隶属度和双边权重测量方法对支持向量回归(SVR)模型进行改进,最后借助沪深300成份股2008至2019年的股票时间序列日数据,按照股市的波动情况将其分为三个阶段(牛市、熊市、震荡市),并建立三个基准模型进行对比分析。研究结果表明:与三个基准模型相比,所提出的股价预测模型的预测误差最低;与原有的SVR模型相比,FPSVR模型可以更好地对处于牛市和震荡市阶段的股票时间序列进行股价预测。