An efficient CMAC neural network for stock index forecasting

Stock index forecasting is one of the major activities of financial firms and private investors in making investment decisions. Although many techniques have been developed for predicting stock index, building an efficient stock index forecasting model is still an attractive issue since even the smallest improvement in prediction accuracy can have a positive impact on investments. In this paper, an efficient cerebellar model articulation controller neural network (CAMC NN) is proposed for stock index forecasting. The traditional CAMC NN scheme has been successfully used in robot control due to its advantages of fast learning, reasonable generalization capability and robust noise resistance. But, few studies have been reported in using a CMAC NN scheme for forecasting problems. To improve the forecasting performance, this paper presents an efficient CMAC NN scheme. The proposed CMAC NN scheme employs a high quantization resolution and a large generalization size to reduce generalization error, and uses an efficient and fast hash coding to accelerate many-to-few mappings. The forecasting results and robustness evaluation of the proposed CMAC NN scheme were compared with those of a support vector regression (SVR) and a back-propagation neural network (BPNN). Experimental results from Nikkei 225 and Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX) closing indexes show that the performance of the proposed CMAC NN scheme was superior to the SVR and BPNN models.     

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。     

Quarterly Time-Series Forecasting With Neural Networks

Forecasting of time series that have seasonal and other variations remains an important problem for forecasters. This paper presents a neural network (NN) approach to forecasting quarterly time series. With a large data set of 756 quarterly time series from the M3 forecasting competition, we conduct a comprehensive investigation of the effectiveness of several data preprocessing and modeling approaches. We consider two data preprocessing methods and 48 NN models with different possible combinations of lagged observations, seasonal dummy variables, trigonometric variables, and time index as inputs to the NN. Both parametric and nonparametric statistical analyses are performed to identify the best models under different circumstances and categorize similar models. Results indicate that simpler models, in general, outperform more complex models. In addition, data preprocessing especially with deseasonalization and detrending is very helpful in improving NN performance. Practical guidelines are also provided.     

Comparing lazy and eager learning models for water level forecasting in river-reservoir basins of inundation regions

This study developed a methodology for formulating water level models to forecast river stages during typhoons, comparing various models by using lazy and eager learning approaches. Two lazy learning models were introduced: the locally weighted regression (LWR) and the k-nearest neighbor (kNN) models. Their efficacy was compared with that of three eager learning models, namely, the artificial neural network (ANN), support vector regression (SVR), and linear regression (REG). These models were employed to analyze the Tanshui River Basin in Taiwan. The data collected comprised 50 historical typhoon events and relevant hourly hydrological data from the river basin during 1996–2007. The forecasting horizon ranged from 1 h to 4 h. Various statistical measures were calculated, including the correlation coefficient, mean absolute error, and root mean square error. Moreover, significance, computation efficiency, and Akaike information criterion were evaluated. The results indicated that (a) among the eager learning models, ANN and SVR yielded more favorable results than REG (based on statistical analyses and significance tests). Although ANN, SVR, and REG were categorized as eager learning models, their predictive abilities varied according to various global learning optimizers. (b) Regarding the lazy learning models, LWR performed more favorably than kNN. Although LWR and kNN were categorized as lazy learning models, their predictive abilities were based on diverse local learning optimizers. (c) A comparison of eager and lazy learning models indicated that neither were effective or yielded favorable results, because the distinct approximators of models that can be categorized as either eager or lazy learning models caused the performance to be dependent on individual models.     

基于集成模型的焦炉火道温度软测量技术研究与应用

在分析焦炉火道温度特性的基础上，提出了一种基于线性回归和神经网络模型的火道温度软测量集成模型；分析生产工艺得到典型蓄热室的选取原则，从典型蓄热室获得蓄顶温度，建立一元和二元线性回归模型反映蓄顶温度和火道温度的线性关系；建立神经网络模型拟和蓄顶温度和火道温度的非线性关系；最后利用误差最小法将线性回归模型和神经网络模型集成，提高软测量精度；模型实际运行效果验证了所建模型的有效性。     

基于EEMD-LMD-LSTM-LEC深度学习模型的短时物流需求预测

短时物流需求预测是智慧物流系统的重要组成部分.由于短时物流需求数据具有非平稳性、强随机性、局部突变、非线性等特征,精确预测较为困难.对此,考虑集成经验模态分解(EEMD)、局部均值分解(LMD)、长短期记忆网络(LSTM)以及考虑局部误差校正(LEC),提出用于短时物流需求预测的EEMD-LMD-LSTM-LEC深度学习模型.该预测模型分为两个阶段:第1阶段基于特征分解和特征提取,构建EEMD-LMD-LSTM模型,以降低非线性的原始短时物流需求不平稳及随机变化导致的预测误差;第2阶段构建局部误差校正模型,用于校正第1阶段的预测结果,以减少短时物流需求的局部突变带来的预测误差.实验结果表明,EEMD-LMD-LSTM-LEC短时物流需求预测模型在均方根误差、绝对误差均值、绝对误差百分比和校正决定系数方面,均优于其他11种对比模型,其中包括:数理统计模型-----ARIMA;浅层机器学习模型-----支持向量回归和BP神经网络;深度学习模型-----LSTM和卷积神经网络;组合模型——深度置信网络-LSTM、经验模态分解(EMD)-LSTM、EEMD-LSTM、LMD-LSTM、EMD-LMD-LSTM和EEMD-LMD-LSTM.     

自适应差分进化算法优化BP神经网络的时间序列预测

针对BP神经网络学习算法随机初始化连接权值和阈值易使模型陷入局部极小点的缺点,设计了一种自适应差分进化算法优化BP神经网络的混合算法。该混合算法中,差分进化算法采用自适应变异和交叉因子优化BP神经网络的初始权值和阈值,再用预寻优得到的初始权值和阈值训练BP神经网络得到最优的权值和阈值。首先对改进的自适应差分进化算法运用测试函数进行性能测试,然后用一个经典时间序列问题对提出的混合算法进行了检验,并与一般的神经网络、ARIMA预测模型及其它混合预测模型进行了对比,实验结果表明,本文提出的混合算法有效并且明显提高了预测精度。     

HYBRID GREY RELATIONAL ARTIFICIAL NEURAL NETWORK AND AUTO REGRESSIVE INTEGRATED MOVING AVERAGE MODEL FOR FORECASTING TIME-SERIES DATA

The aim of this study is to develop a new hybrid model by combining a linear and nonlinear model for forecasting time-series data. The proposed model (GRANN_ARIMA) integrates nonlinear grey relational artificial neural network (GRANN) and a linear autoregressive integrated moving average (ARIMA) model by combining new features and grey relational analysis to select the appropriate inputs and hybridization succession. To validate the performance of the proposed model, small and large scale data sets are used. The forecasting performance is compared with several models, and these include: individual models (ARIMA, multiple regression, GRANN), several hybrid models (MARMA, MR_ANN, ARIMA_ANN), and an artificial neural network (ANN) trained using a Levenberg Marquardt algorithm. The experiments have shown that the proposed model has outperformed other models with 99.5% forecasting accuracy for small-scale data and 99.84% for large-scale data. The obtained empirical results have proven that the GRANN_ARIMA model can provide a better alternative for time-series forecasting due to its promising performance and capability in handling time-series data for both small- and large-scale data.     

An investigation of neural networks for linear time-series forecasting

This study examines the capability of neural networks for linear time-series forecasting. Using both simulated and real data, the effects of neural network factors such as the number of input nodes and the number of hidden nodes as well as the training sample size are investigated. Results show that neural networks are quite competent in modeling and forecasting linear time series in a variety of situations and simple neural network structures are often effective in modeling and forecasting linear time series.Scope and purposeNeural network capability for nonlinear modeling and forecasting has been established in the literature both theoretically and empirically. The purpose of this paper is to investigate the effectiveness of neural networks for linear time-series analysis and forecasting. Several research studies on neural network capability for linear problems in regression and classification have yielded mixed findings. This study aims to provide further evidence on the effectiveness of neural network with regard to linear time-series forecasting. The significance of the study is that it is often difficult in reality to determine whether the underlying data generating process is linear or nonlinear. If neural networks can compete with traditional forecasting models for linear data with noise, they can be used in even broader situations for forecasting researchers and practitioners.     

Differential Evolution and Levenberg Marquardt Trained Neural Network Scheme for Nonlinear System Identification

This paper proposes a new nonlinear system identification scheme using differential evolution (DE), neural network and Levenberg Marquardt algorithm (LM). Here, DE and LM in a combined framework are used to train a neural network for achieving better convergence of neural network weight optimization. A number of examples including a practical case-study have been considered for implementation of different system identification methods namely, only NN, DE+NN and DE+LM+NN. After, a series of simulation studies of these methods on the different nonlinear systems it has been confirmed that the proposed DE and LM trained NN approach to nonlinear system identification has yielded better identification results in terms of time of convergence and less identification error.