基于分解集成的LSTM神经网络模型的油价预测

为了提高油价的预测效果,提出一种基于EEMD分解、小波阈值去噪、fine-to-coarse法重构和LSTM神经网络的组合预测方法.EEMD对油价原始时间序列分解,利用小波阈值去噪法获取第一高频模态分量的有效信息;分解出的模态分量运用fine-to-coarse法重构,得到从高到低的重构分量;使用LSTM神经网络预测重构分量;对重构序列简单加和得到最终结果.实证结果表明,与其他基准模型比较,在水平预测和趋势预测上该方法能有效地预测原油价格.     

基于分布式神经网络的苹果价格预测方法

针对传统农产品价格预测模型在大数据场景下无法快速准确对苹果市场价格进行预测的问题,提出一种基于分布式神经网络的苹果价格预测方法。首先,研究影响苹果市场价格的相关因素,选取苹果历史价格、替代品历史价格、居民消费水平和原油价格四个特征作为神经网络模型的输入;然后,构建蕴含价格波动规律的分布式神经网络模型,实现对苹果市场价格的短期预测。实验结果显示,基于分布式神经网络的苹果市场价格短期预测模型具有较高的预测精度,平均相对误差仅为0.50%,满足苹果市场价格预测的要求。实验结果表明,分布式神经网络模型能够通过自学习特性揭示出苹果市场价格的波动规律和发展趋势,所提方法能为稳定苹果市场秩序和市场价格宏观调控提供科学依据,有助于降低价格波动带来的危害,帮助果农规避市场风险。     

基于LSTM-BP组合模型的短时交通流预测

为减轻日益严重的交通拥堵问题,实现智能交通管控,给交通流诱导和交通出行提供准确实时的交通流预测数据,设计了基于长短时记忆神经网络（LSTM）和BP神经网络结合的LSTM-BP组合模型算法.挖掘已知交通流数据的特征因子,建立时间序列预测模型框架,借助Matlab完成从数据的处理到模型的仿真,实现基于LSTM-BP的短时交通流精确预测.通过与LSTM\BP\WNN三种预测网络模型的对比,结果表明LSTM-BP预测的时间序列具有较高的精度和稳定性.该模型的搭建,可对交通分布的预测、交通方式的划分、实时交通流的分配提供依据和参考.     

一种应用Radon变换的H.264/AVC帧内预测算法

在H.264/AVC视频编码过程中,编码时间受诸多因素影响,如帧间/帧内模式选择、率失真优化(RDO)等.JVT(Joint Video Team)提供的参考软件采用全搜索算法进行帧内预测,其算法复杂度很高.为此,提出一种基于Radon变换的快速预测算法,通过对4 ×4块进行Radon变换求取其纹理方向,根据求取的纹理方向减少4×4块的预测模式,有效的降低了预测时间.实验结果表明本算法在信噪比和码率变化极小的情况下,编码速度有显著提高.     

基于GARCH-V模型的处置效应研究

为了考察作为投资者决策非理性因素的处置效应与股价波动之间的关系,引入用来检验处置效应是否存在的资本盈利突出量(Capital gains overhang).首先,在GARCH-V模型的基础上,引入用来检验处置效应是否存在的资本盈利突出量,并构建GARCH-V-G模型;然后,对成熟市场与新兴市场这两个不同类型市场上投资者在投资决策过程中存在的处置效应与股票价格波动之间的关系进行实证研究和比较,发现资本盈利突出量与股票市场的波动负相关,对股市波动的持续性具有一定的解释能力,并且新兴市场上投资者表现出的处置效应无论是对波动持续性的解释能力还是对波动的影响程度都比成熟市场要强;最后,根据赤池信息准则(AIC)发现,所构建的基于处置效应的GARCH-V-G模型比GARCH-V模型的拟合效果更好.     

基于偏态深度分类的高炉硅含量及波动预测

高炉冶炼是个具有高度复杂性、混沌性、时滞性的动态过程,工业上常常用铁水硅含量反馈高炉炉温热状态波动变化,而偏态投影深度在数据有偏时可以较好地反映出数据的离群情况,在高维数据分类计算中十分稳健.首先,通过差分处理及相关性分析确定11个影响因素作为输入变量,用于研究各变量变化对硅含量变化的关系;然后,将偏态投影深度值在90%的置信区间外的数据视作离群值,分为稳定类和离群类;最后,对稳定数据利用Elman神经网络预测模型进行预测,对于离群类利用Logistic模型在炉温不同波动方向下的规律进行归类预测.实例仿真研究表明,稳定类157炉的预测精度高达85.3%,离群类的预测精度达到82.6%.     

基于近端强化学习的股价预测方法

股价预测一直是金融时间序列研究的热点和难点,采用一种合理有效的股价预测方法对于投资者获取高额收益回报及规避交易风险具有重要的指导意义.通过结合近端策略优化(proximal policy optimization, PPO)和强化学习(reinforcement learning, RL),将股价预测视为一个时间序列预测问题,提出一种近端强化学习的股价预测方法 (PPORL).此外,在预测方法的基础上引入股票的相对强弱性能和股票均线指标,提出一种能够自动捕捉潜在交易点的量化交易策略,期望在获取高额收益的同时降低交易过程中存在的风险.通过实验对比了长短期记忆网络(long short-term memory, LSTM)和循环神经网络(recurrent neural network, RNN)模型在上证指数(SZZS)、深证成指(SZCZ)和沪深300指数(HS300)上的预测性能和交易决策表现,并利用多种误差评估方法对预测结果进行定量分析,从而验证了PPORL在预测性能和交易决策等方面的有效性和鲁棒性.     

基于优化LSTM模型的股票预测

股票预测研究一直是困扰投资者的难题.以往,投资者采用传统分析方法如K线图、十字线等方法来预测股票走势,但随着科技的进步和经济市场的发展,以及经济政策的变动,股票的价格走势受到越来越多方面因素的干扰,仅靠传统的分析方法远远不能解析出股票价格波动中隐藏着的重要信息,因此预测精度大打折扣.为了提高股票价格的预测精度,提出一种基于PCA和LASSO的LSTM神经网络股票价格预测模型.采用2015-2019年平安银行(000001)五大类技术指标数据,通过PCA和LASSO方法对五大类技术分析指标进行降维筛选,再使用LSTM模型进行平安银行股票收盘价预测,对比前两种模型和单纯使用LSTM模型的预测效果稳定性及准确性.结果表明,相比于LASSO-LSTM模型和LSTM模型,PCA-LSTM模型能够大幅削减数据冗余,并且获得了更优异的预测精度.     

基于优化LSTM模型的股票预测

股票预测研究一直是困扰投资者的难题.以往,投资者采用传统分析方法如K线图、十字线等方法来预测股票走势,但随着科技的进步和经济市场的发展,以及经济政策的变动,股票的价格走势受到越来越多方面因素的干扰,仅靠传统的分析方法远远不能解析出股票价格波动中隐藏着的重要信息,因此预测精度大打折扣.为了提高股票价格的预测精度,提出一种基于PCA和LASSO的LSTM神经网络股票价格预测模型.采用2015-2019年平安银行(000001)五大类技术指标数据,通过PCA和LASSO方法对五大类技术分析指标进行降维筛选,再使用LSTM模型进行平安银行股票收盘价预测,对比前两种模型和单纯使用LSTM模型的预测效果稳定性及准确性.结果表明,相比于LASSO-LSTM模型和LSTM模型,PCA-LSTM模型能够大幅削减数据冗余,并且获得了更优异的预测精度.     

基于灰色加权马尔可夫SCGM(1,1)c的交通事故预测

交通事故预测是交通安全评价、规划和决策的基础。基于灰色系统理论和马尔可夫链理论,应用系统云灰色模型SCGM(1,1)c拟合道路交通时序数据的总体趋势,所得拟合指标是随机波动的。马尔可夫链原理适合处理波动性大的系统过程,因此选用能更好解决随机波动性的加权马尔可夫链预测方法,提出一种用于道路交通事故次数预测的灰色加权马尔可夫SCGM(1,1)c模型,它适用于时间序列短,数据量少且随机波动不太大的动态过程预测。以某市1975—2010年道路交通事故次数为例进行了预测分析,结果表明该模型既能揭示交通事故次数变化的总体趋势,又能克服随机波动性数据对预测精度的影响,具有较强的工程实用性。     

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。     

Predicting the direction,maximum, minimum and closing prices of daily Bitcoin exchange rate using machine learning techniques

Bitcoin is the most accepted cryptocurrency in the world, which makes it attractive for investors and traders. However, the challenge in predicting the Bitcoin exchange rate is its high volatility. Therefore, the prediction of its behavior is of great importance for financial markets. In this way, recent studies have been carried out on what internal and/or external Bitcoin information is relevant to its prediction. The increased use of machine learning techniques to predict time series and the acceptance of cryptocurrencies as financial instruments motivated the present study to seek more accurate predictions for the Bitcoin exchange rate. In this way, in a first stage of the proposed methodology, different feature selection techniques were evaluated in order to obtain the most relevant attributes for the predictions. In the sequence, it was analyzed the behavior of Artificial Neural Networks (ANN), Support Vector Machines (SVM) and Ensemble algorithms (based on Recurrent Neural Networks and the k-Means clustering method) for price direction predictions. Likewise, the ANN and SVM were employed for regression of the maximum, minimum and closing prices of the Bitcoin. Moreover, the regression results were also used as inputs to try to improve the price direction predictions. The results showed that the selected attributes and the best machine learning model achieved an improvement of more than 10%, in accuracy, for the price direction predictions, with respect to the state-of-the-art papers, using the same period of information. In relation to the maximum, minimum and closing Bitcoin prices regressions, it was possible to obtain Mean Absolute Percentage Errors between 1% and 2%. Based on these results, it was possible to demonstrate the efficacy of the proposed methodology when compared to other studies.     

基于金融文本情感的股票波动预测

股票市场的情绪可以在一定程度上反映投资者的行为并影响其投资决策。市场新闻作为一种非结构性数据,能够体现并引导市场的大环境情绪,与股票价格一同成为至关重要的市场参考数据,能够为投资者的投资决策提供有效帮助。文中提出了一种可以准确、快速地建立针对海量新闻数据的多维情绪特征向量化方法,利用支持向量机(Support Victor Machine,SVM)模型来预测金融新闻对股票市场的影响,并通过bootstrap来减轻过拟合问题。在沪深股指上进行实验的结果表明,相比于传统模型,所提方法能够将预测准确度提高约8%,并在3个月的回测实验中获得了6.52%的超额收益,证明了其有效性。     

A hybrid grid-GA-based LSSVR learning paradigm for crude oil price forecasting

In order to effectively model crude oil spot price with inherently high complexity, a hybrid learning paradigm integrating least squares support vector regression (LSSVR) with a hybrid optimization searching approach for the parameters selection in the LSSVR [consisting of grid method and genetic algorithm (GA)], i.e., a hybrid grid-GA-based LSSVR model, is proposed in this study. In the proposed hybrid learning paradigm, the grid method, a simple but efficient searching method, is first applied to roughly but rapidly determine the proper boundaries of the parameters in the LSSVR; then, the GA, an effective and powerful intelligent searching algorithm, is further implemented to select the most suitable parameters. For illustration and verification, the proposed learning paradigm is used to predict the crude oil spot prices of the West Texas Intermediate and the Brent markets. The empirical results demonstrate that the proposed hybrid grid-GA-based LSSVR learning paradigm can outperform its benchmarking models (including some popular forecasting techniques and similar LSSVRs with other parameter searching algorithms) in terms of both prediction accuracy and time-savings, indicating that it can be utilized as one effective forecasting tool for crude oil price with high volatility and irregularity.     

Implied volatility in oil markets

Modelling the implied volatility surface as a function of an option’s strike price and maturity is a subject of extensive research in financial markets. The implied volatility in commodity markets is much less studied, due to a limited liquidity and the complicated structure of commodity options. A new semi-parametric method is introduced for modelling the implied volatility surface and is applied to the option price data from oil markets. This approach combines the simplicity of a parametric method with the flexibility of a non-parametric approach. The method can successfully deal with a limited amount of option price data. Performance of the method is investigated by applying it to prices of exchange-traded crude oil and gasoline options, and the results are compared with those obtained by a purely parametric approach. Furthermore, the investigation of the relationship between volatilities implied from European and Asian options shows that Asian options in oil markets are significantly more expensive than theoretical arguments imply.     

改进的支持向量机石油期货价格预测模型研究

研究石油期货价格预测精确度问题。石油价格预测随机性很强且受到市场复杂变化条件影响,是曲型非线性问题。针对传统线性关系的价格预测模型对石油的价格预测准确度较低,提出了一种改进的支持向量机石油期货价格预测模型方法,采用石油期货价格序列的一阶差分作为SVM的输出,一阶差分的若干滞后值作为SVM的输入。同时采用一种新的滞后阶数寻优方法,将滞后阶数与其它模型参数一样看待,使用验证集中技术获得所有参数的最佳值。最后实验采集了纽约商品交易市场石油期货价格数据作为实验数据,仿真结果表明,改进的价格预测模型提高了石油价格预测的准确度,是一种有效使用的石油价格预测模型。     

Daily prediction of short-term trends or crude oil prices using neural networks exploiting multimarket dynamics

This paper documents a systematic investigation on the predictability of short-term trends of crude oil prices on a daily basis. In stark contrast with longer-term predictions of crude oil prices, short-term prediction with time horizons of 1-3 days posits an important problem that is quite different from what has been studied in the literature. The problem of such short-term predicability is tackled through two aspects. The first is to examine the existence of linear or nonlinear dynamic processes in crude oil prices. This sub-problem is addressed with statistical analysis involving the Brock-Dechert-Scheinkman test for nonlinearity. The second aspect is to test the capability of artificial neural networks (ANN) for modeling the implicit nonlinearity for prediction. Four experimental models are designed and tested with historical data: (1) using only the lagged returns of filtered crude oil prices as input to predict the returns of the next days; this is used as the benchmark, (2) using only the information set of filtered crude oil futures price as input, (3) combining the inputs from the benchmark and second models, and (4) combing the inputs from the benchmark model and the intermarket information. In order to filter out the noise in the original price data, the moving averages of prices are used for all the experiments. The results provided sufficient evidence to the predictability of crude oil prices using ANN with an out-of-sample hit rate of 80%, 70%, and 61% for each of the next three days’ trends.     

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。     

Efficiency of Crude Oil Futures Markets: New Evidence from Multifractal Detrending Moving Average Analysis

In this paper, we examine the weak-form efficient market hypothesis of crude oil futures markets by testing for the random walk behavior of prices. Using a method borrowed from statistical physics, we find that crude oil price display weak persistent behavior for time scales smaller than a year. For time scales larger than a year, strong mean-reversion behaviors can be found. That is, crude oil futures markets are not efficient in the short-term or in the long-term. By quantifying the market inefficiency using a “multifractality degree”, we find that the futures markets are more inefficient in the long-term than in the short-term. Furthermore, we investigate the “stylized fact” of volatility dynamics on market efficiency. The simulating and empirical results indicate that volatility clustering, volatility memory and extreme volatility have adverse effects on market efficiency, especially in the long-term.     

A hybrid ANFIS based on n-period moving average model to forecast TAIEX stock

Linear model is a general forecasting model and moving average technical index (MATI) is one of useful forecasting methods to predict the future stock prices in stock markets. Therefore, individual investors, stock fund managers, and financial analysts attempt to predict price fluctuation in stock markets by either linear model or MATI. From literatures, three major drawbacks are found in many existing forecasting models. First, forecasting rules mined from some AI algorithms, such as neural networks, could be very difficult to understand. Second, statistic assumptions about variables are required for time series to generate forecasting models, which are not easily understandable by stock investors. Third, stock market investors usually make short-term decisions based on recent price fluctuations, i.e., the last one or two periods, but most time series models use only the last period of stock price. In order to overcome these drawbacks, this study proposes a hybrid forecasting model using linear model and MATI to predict stock price trends with the following four steps: (1) test the lag period of Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) and calculate the last n-period moving average; (2) use subtractive clustering to partition technical indicator values into linguistic values based on data discretization method objectively; (3) employ fuzzy inference system (FIS) to build linguistic rules from the linguistic technical indicator dataset, and optimize the FIS parameters by adaptive network; and (4) refine the proposed model by adaptive expectation models. The proposed model is then verified by root mean squared error (RMSE), and a ten-year period of TAIEX is selected as experiment datasets. The results show that the proposed model is superior to the other forecasting models, namely Chen's model and Yu's model in terms of RMSE.