基于遗传算法和半参数回归的神经网络集成股市预测研究

股票时间序列预测在经济和管理领域具有重要的应用前景,也是很多商业和金融机构成功的基础.首先利用奇异谱分析对股市时间序列重构,降低噪声并提取趋势序列.再利用C-C算法确定股市时间序列的嵌入维数和延迟阶数,对股市时间序列进行相空间重构,生成神经网络的学习矩阵.进一步利用Boosting技术和不同的神经网络模型,生成神经网络集成个体.最后采用带有惩罚项的半参数回归模型进行集成,并利用遗传算法选择最优的光滑参数,以此建立遗传算法和半参数回归的神经网络集成股市预测模型.通过上证指数开盘价进行实例分析,与传统的时间序列分析和其他集成方法对比,发现该方法能获得更准确的预测结果.计算结果表明该方法能充分反映股票价格时间序列趋势,为金融时间序列预测提供一个有效方法.     

混合区间多尺度分解的区间时间序列组合预测

鉴于传统预测方法一直基于“点”来衡量时间序列数据,然而现实生活中在给定的时间段内许多变量是有区间限制的,点值预测会损失波动性信息。因此,本文提出了一种基于混合区间多尺度分解的组合预测方法。首先,建立区间离散小波分解方法(IDWT)、区间经验模态分解方法(IEMD)和区间奇异普分析方法(ISSA)。其次,用本文构建的IDWT、IEMD和ISSA对区间时间序列进行多尺度分解,从而得到区间趋势序列和残差序列。然后,用霍尔特指数平滑方法(Holt's)、支持向量回归(SVR)和BP神经网络对区间趋势序列和残差序列进行组合预测得到三种分解方法下的区间时间序列预测值。最后,用BP神经网络对各预测结果进行集成得到区间时间序列最终预测值。同时,为证明模型的有效性进行了AQI空气质量的实证预测分析,结果表明,本文所提出基于混合区间多尺度分解的组合预测方法具有较高的预测精度和良好的适用性。     

Improved pollution forecasting hybrid algorithms based on the ensemble method

In a new fine particle concentrations forecasting model, the Hampel identifier outlier correction preprocessing detects and corrects the outliers in the original series. Empirical wavelet transform method decomposes the corrected series into a set of subseries adaptively, and each subseries are used to train the Stacking ensemble method. In the Stacking ensemble forecasting method, the outlier robust extreme learning machine meta-learner combines different Elman neural network base learners and outputs the forecasting results of different subseries. Different forecasting subseries are combined and then reconstructed by inverse empirical wavelet transform reconstruction method to get the final forecasting fine particle concentrations results. It has been proved in the study that the model proposed in the study has better accuracy and wide applicability comparing to the existing models.     

Non-traditional methods of forecasting

The traditional, statistical approach to forecasting has been based upon the identification, specification and estimation of a single model. Recently, we have seen the rise of computationally-intensive methods which depart from this protocol, such as multiple model switching, combinations and neural network methods. At the same time, we are also seeing an increased awareness of the judgemental role in forecasting, also to deal with the inadequacies of model specification. This paper seeks to address the issue of achieving a balance between data and judgement and the need to develop formal methods for it to be effective.     

Neural network approach to forecasting of quasiperiodic financial time series

A novel neural network approach to forecasting of financial time series based on the presentation of the series as a combination of quasiperiodic components is presented. Separate components may have aliquant, and possibly non-stationary frequencies. All their parameters are estimated in real time in an ensemble of predictors, whose outputs are then optimally combined to obtain the final forecast. Special architecture of artificial neural network and learning algorithms implementing this approach are developed.     

Neural network forecasting for seasonal and trend time series

Neural networks have been widely used as a promising method for time series forecasting. However, limited empirical studies on seasonal time series forecasting with neural networks yield mixed results. While some find that neural networks are able to model seasonality directly and prior deseasonalization is not necessary, others conclude just the opposite. In this paper, we investigate the issue of how to effectively model time series with both seasonal and trend patterns. In particular, we study the effectiveness of data preprocessing, including deseasonalization and detrending, on neural network modeling and forecasting performance. Both simulation and real data are examined and results are compared to those obtained from the Box–Jenkins seasonal autoregressive integrated moving average models. We find that neural networks are not able to capture seasonal or trend variations effectively with the unpreprocessed raw data and either detrending or deseasonalization can dramatically reduce forecasting errors. Moreover, a combined detrending and deseasonalization is found to be the most effective data preprocessing approach.     

基于组合预测模型的广东省第三产业产值预测

首先分析了影响广东省第三产业发展的主要因素,指出由于上述因素相互制约、相互影响,导致第三产业的发展呈现出高度的非线性特征,并使得单一的预测模型在预测效果和泛化能力方面难以胜任.在此基础上,提出了基于神经网络集成的组合预测模型,对广东省第三产业的发展进行预测,阐述了算法的基本原理和数据处理流程,实证分析表明:基于神经网络集成的组合预测模型要比单一预测模型的预测精度高.     

Forecasting nonlinear time series with a hybrid methodology

In recent years, artificial neural networks (ANNs) have been used for forecasting in time series in the literature. Although it is possible to model both linear and nonlinear structures in time series by using ANNs, they are not able to handle both structures equally well. Therefore, the hybrid methodology combining ARIMA and ANN models have been used in the literature. In this study, a new hybrid approach combining Elman’s Recurrent Neural Networks (ERNN) and ARIMA models is proposed. The proposed hybrid approach is applied to Canadian Lynx data and it is found that the proposed approach has the best forecasting accuracy.     

基于改进BP神经网络的组合预测模型设计

为提高预测精度,解决非线性组合预测中的困难,利用改进BP神经网络对非线性组合预测模型进行了设计.讨论了模型设立的原则和一般程序,比较其与传统的组合预测方法之间的优劣,并给出实例加以验证.结果显示,基于改进BP神经网络的非线性组合预测模型能够准确描述系统中的非线性,提高预测精度.     

基于神经网络的股票预测模型

针对股票市场的特征提取困难、预测精度较低等问题,本文基于深度学习算法,构建了一系列用于股票市场预测的神经网络模型,包括基于多层感知机(MLP)、卷积神经网络(CNN)、递归神经网络(RNN)、长短期记忆网络(LSTM)和门控神经单元(GRU)的模型。 针对RNN、LSTM和GRU无法充分利用所参考的时间维度的信息,引入注意力机制(Attention Mechanism) 给各时间维度的信息赋予不同权重,区分不同信息对预测的重要程度,从而提升递归网络模型的性能。上述模型均基于股票数据进行了优化,基于上证指数对各类模型进行了充分的对比实验,探索了模型中重要变量对性能的影响,旨在为基于神经网络的股票预测模型给出具体的优化方向。     

基于ARIMA与神经网络集成的GDP时间序列预测研究

本文深入分析了单整自回归移动平均(ARIMA)模型与神经网络(NN)模型的预测特性和优劣,并在此基础上建立了由ARIMA模型和NN模型集成的GDP时间序列预测模型与算法。其基本思想是充分发挥两种模型在线性空间和非线性空间的预测优势,据此将GDP时间序列的数据结构分解为线性自相关主体和非线性残差两部分,首先用ARIMA模型预测序列的线性主体,然后用NN模型对其非线性残差进行估计,最终集成为整个序列的预测结果。仿真实验表明:集成模型的预测准确率显著高于单一模型的预测准确率,从而证实了集成模型用于GDP预测的有效性。     

基于二阶段异质随机森林的汽油辛烷值预测

构建了基于二阶段异质随机森林的汽油辛烷值预测模型.首先利用样本-位点信息表知识约简模型,筛选出对汽油辛烷值影响大的位点数据作为第一阶段;然后,利用集成学习思想集成支持向量回归和动态时间序列神经网络,构建异质随机森林预测模型作为第二阶段.利用十折交叉法验证模型精度,结果表明该集成学习算法具有有效性和高精度.     

Forecasting and recombining time-series components by using neural networks

Operations and other business decisions often depend on accurate time-series forecasts. These time series usually consist of trend-cycle, seasonal, and irregular components. Existing methodologies attempt to first identify and then extrapolate these components to produce forecasts. The proposed process partners this decomposition procedure with neural network methodologies to combine the strengths of economics, statistics, and machine learning research. Stacked generalization first uses transformations and decomposition to pre-process a time series. Then a time-delay neural network receives the resulting components as inputs. The outputs of this neural network are then input to a backpropagation algorithm that synthesizes the processed components into a single forecast. Genetic algorithms guide the architecture selection for both the time-delay and backpropagation neural networks. The empirical examples used in this study reveal that the combination of transformation, feature extraction, and neural networks through stacked generalization gives more accurate forecasts than classical decomposition or ARIMA models.?Scope and Purpose.?The research reported in this paper examines two concurrent issues. The first evaluates the performance of neural networks in forecasting time series. The second assesses the use of stacked generalization as a way of refining this process. The methodology is applied to four economic and business time series. Those studying time series and neural networks, particularly in terms of combining tools from the statistical community with neural network technology, will find this paper relevant.     

Integrating spectral clustering with wavelet based kernel partial least square regressions for financial modeling and forecasting

Traditional forecasting models are not very effective in most financial time series. To address the problem, this study proposes a novel system for financial modeling and forecasting. In the first stage, wavelet analysis transforms the input space of raw data to a time-scale feature space suitable for financial modeling and forecasting. A spectral clustering algorithm is then used to partition the feature space into several disjointed regions according to their time series dynamics. In the second stage, multiple kernel partial least square regressors ideally suited to each partitioned region are constructed for final forecasting. The proposed model outperforms neural networks, SVMs, and traditional GARCH models, significantly reducing root-mean-squared forecasting errors.     

Representing and Learning Distributions with the Aid of a Neural Network

This paper describes a method by which a neural network learns to fit a distribution to sample data. The neural network may be used to replace the input distributions required in a simulation or mathematical model and it allows random variates to be generated for subsequent use in the model. Results are given for several data sets which indicate the method is robust and can represent different families of continuous distributions. The neural network is a three-layer feed-forward network of size (1-3-3-1). This paper suggests that the method is an alternative approach to the problem of selection of suitable continuous distributions and random variate generation techniques for use in simulation and mathematical models.     

交通流灰色RBF网络非线性组合预测方法

针对智能交通系统的开发,提出一种基于灰色GM(1,1)模型和RBF网络非线性组合的短时交通流预测方法.该方法采用三层结构的RBF网络将两种单一预测方法(灰色GM(1,1)模型和RBF网络)进行了非线性组合.利用实测数据对组合方法进行了仿真实验,结果表明:非线性组合模型的预测准确性高于单独的RBF网络预测的准确性;组合模型发挥了两种单一方法各自的优势,是短时交通流预测的有效方法.     

Fuzzy adaptive network in presidential elections

Several scientific forecasting models for presidential elections have been suggested. However, most of these models are based on traditional statistics approaches. Since the system is linguistic, vague, and dynamic in nature, the traditional rigorous mathematical approaches are inappropriate for the modeling of this kind of humanistic system. This paper presents a combined neural fuzzy approach, namely a fuzzy adaptive network, to model and forecast the problem of a presidential election. The fuzzy adaptive network, which is ideally suited for the modeling of vaguely defined humanistic systems, combines the advantages of the representation ability of fuzzy sets and the learning ability of a neural network. To illustrate the approach, experiments were carried out by first formulating the problem, then training the network, and, finally, predicting the election results based on the trained network. The experimental results show that a fuzzy adaptive network is an ideal approach for the modeling and forecasting of national presidential elections.     

基于ARIMA和LSSVM的非线性集成预测模型

针对复杂时间序列预测困难的问题,在综合考虑线性与非线性复合特征的基础上,提出一种基于ARIMA和最小二乘支持向量机(LSSVM)的非线性集成预测方法.首先采用ARIMA模型进行时间序列线性趋势建模,并为LSSVM建模确定输入阶数;接着根据确定的输入阶数进行时间序列样本重构,采用LSSVM模型进行时间序列非线性特征建模;最后采用基于LSSVM的非线性集成技术形成一个综合的预测结果.将该方法用于中国GDP预测取得的结果,与单独预测方法及流行的其他集成预测方法相比,预测精度有了较大的提高,从而验证了方法的有效性和可行性.     

偏最小二乘回归的贝叶斯正则化神经网络集成模型在证券分析预测中的应用

神经网络集成技术能有效地提高神经网络的预测精度和泛化能力,已经成为机器学习和神经计算领域的一个研究热点.利用Bagging技术和不同的神经网络算法生成集成个体,并用偏最小二乘回归方法从中提取集成因子,再利用贝叶斯正则化神经网络对其集成,以此建立上证指数预测模型.通过上证指数开、收盘价进行实例分析,计算结果表明该方法预测精度高、稳定性好.     

Forecasting corporate failure using ensemble of self-organizing neural networks

For more than a decade, the number of research works that deal with ensemble methods applied to bankruptcy prediction has been increasing. Ensemble techniques present some characteristics that, in most situations, allow them to achieve better forecasts than those estimated with single models. However, the difference between the performance of an ensemble and that of its base classifier but also between that of ensembles themselves, is often low. This is the reason why we studied a way to design an ensemble method that might achieve better forecasts than those calculated with traditional ensembles. It relies on a quantification process of data that characterize the financial situation of a sample of companies using a set of self-organizing neural networks, where each network has two main characteristics: its size is randomly chosen and the variables used to estimate its weights are selected based on a criterion that ensures the fit between the structure of the network and the data used over the learning process. The results of our study show that this technique makes it possible to significantly reduce both the type I and type II errors that can be obtained with conventional methods.