A simulation study of artificial neural networks for nonlinear time-series forecasting

This study presents an experimental evaluation of neural networks for nonlinear time-series forecasting. The effects of three main factors — input nodes, hidden nodes and sample size, are examined through a simulated computer experiment. Results show that neural networks are valuable tools for modeling and forecasting nonlinear time series while traditional linear methods are not as competent for this task. The number of input nodes is much more important than the number of hidden nodes in neural network model building for forecasting. Moreover, large sample is helpful to ease the overfitting problem.Scope and purposeInterest in using artificial neural networks for forecasting has led to a tremendous surge in research activities in the past decade. Yet, mixed results are often reported in the literature and the effect of key modeling factors on performance has not been thoroughly examined. The lack of systematic approaches to neural network model building is probably the primary cause of inconsistencies in reported findings. In this paper, we present a systematic investigation of the application of neural networks for nonlinear time-series analysis and forecasting. The purpose is to have a detailed examination of the effects of certain important neural network modeling factors on nonlinear time-series modeling and forecasting.     

基于模糊逻辑和神经网络的电力负荷预测

设计并实现了神经网络和模糊逻辑相结合的综合预测模型进行短期电力负荷预测。由神经网络和模糊逻辑分别对基本负荷和受天气、节假日影响的负荷进行预测,使其在天气突变等情况下也能达到较高的预测精度。采用此模型对石家庄电力系统负荷进行预测分析,取得了令人满意的结果。     

水文时间序列趋势预测挖掘系统研究

讨论了时间序列趋势预测研究的现状和典型方法，并在时间序列预测中引入神经网络方法。介绍了水文时间序列趋势预测挖掘系统的设计与实现，详细分析了系统采用的时间序列预测的神经网络方法。     

Fusion ANFIS models based on multi-stock volatility causality for TAIEX forecasting

Stock market investors value accurate forecasting of future stock price from trading systems because of the potential for large profits. Thus, investors use different forecasting models, such as the time-series model, to assemble a superior investment portfolio. Unfortunately, there are three major drawbacks to the time-series model: (1) most statistical methods rely on some assumptions about the variables; (2) most conventional time-series models use only one variable in forecasting; and (3) the rules mined from artificial neural networks are not easily understandable. To address these shortcomings, this study proposes a new model based on multi-stock volatility causality, a fusion adaptive-network-based fuzzy inference system (ANFIS) procedure, for forecasting stock price problems in Taiwan. Furthermore, to illustrate the proposed model, three practical, collected stock index datasets from the USA and Taiwan stock markets are used in the empirical experiment. The experimental results indicate that the proposed model is superior to the listing methods in terms of root mean squared error, and further evaluation reveals that the profits comparison results for the proposed model produce higher profits than the listing models.     

Connectionist approach to time series prediction: an empirical test

Among the various potential applications of neural networks, forecasting is considered to be a major application. Several researchers have reported their experiences with the use of neural networks in forecasting, and the evidence is inconclusive. This paper presents the results of a forecasting competition between a neural network model and a Box-Jenkins automatic forecasting expert system. Seventy-five series, a subset of data series which have been used for comparison of various forecasting techniques, were analysed using the Box-Jenkins approach and a neural network implementation. The results show that the simple neural net model tested on this set of time series could forecast about as well as the Box-Jenkins forecasting system.     

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.     

Database Integration Using Neural Networks: Implementation and Experiences

Applications in a wide variety of industries require access to multiple heterogeneous distributed databases. One step in heterogeneous database integration is semantic integration: identifying corresponding attributes in different databases that represent the same real world concept. The rules of semantic integration can not be ‘pre-programmed’ since the information to be accessed is heterogeneous and attribute correspondences could be fuzzy. Manually comparing all possible pairs of attributes is an unreasonably large task. We have applied artificial neural networks (ANNs) to this problem. Metadata describing attributes is automatically extracted from a database to represent their ‘signatures’. The metadata is used to train neural networks to find similar patterns of metadata describing corresponding attributes from other databases. In our system, the rules to determine corresponding attributes are discovered through machine learning. This paper describes how we applied neural network techniques in a database integration problem and how we represent an attribute with its metadata as discriminators. This paper focuses on our experiments on effectiveness of neural networks and each discriminator. We also discuss difficulties of using neural networks for this problem and our wish list for the Machine Learning community. Received 18 February 1999 / Revised 22 April 1999 / Accepted in revised form 20 November 1999     

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.     

Forecast Combination by Using Artificial Neural Networks

One of the efficient ways for obtaining accurate forecasts is usage of forecast combination method. This approach consists of combining different forecast values obtained from different forecasting models. Also artificial neural networks and fuzzy time series approaches have proved their success in the field of forecasting. In this study, a new forecast combination approach based on artificial neural networks is proposed. The forecasts obtain from different fuzzy time series models are combined by utilizing artificial neural networks. The proposed method is applied to index of Istanbul stock exchange (IMKB) time series and the results are compared to other forecast combination methods available in the literature. As a result of the implementation, it is seen that the proposed forecast combination approach produces better forecasts than those produced by other methods.     

Exchange rate forecasting: comparison of various architectures of neural networks

This paper evaluates the predictive accuracy of neural networks in forecasting exchange rate. The multi-layer perceptron (MLP) and radial basis function (RBF) networks with different architectures are used to forecast five exchange rate time series. The results of each prediction are evaluated and compared according to the networks and architectures used. It is found that neural networks can be effectively used in forecasting exchange rate and hence in designing trading strategies. RBF networks performed better than MLP networks in our simulation experiment. This experiment suggests that it is possible to extract information hidden in the exchange rate and predict it into future.     

基于预报-校正法的汇率预测模型

神经网络已成为金融时间序列预测的一个有力工具，但有些设计因素对神经网络的预测效果有很大的影响，这些因素包括输入变量选择、网络的结构和训练数据量。提出了基于预报一校正方法的神经网络预测模型，并对不同大小的训练集的影响进行了实验研究。结果发现大的训练集有更好的预测效果，且该方法的预测精度要普遍高于单一神经网络所能达到的效果。     

An empirical investigation of bias and variance in time series forecasting: modeling considerations and error evaluation

Bias and variance play an important role in understanding the fundamental issue of learning and generalization in neural network modeling. Several studies on bias and variance effects have been published in classification and regression related research of neural networks. However, little research has been done in this area for time-series modeling and forecasting. We consider modeling issues related to understanding error components given the common practices associated with neural-network time-series forecasting. We point out the key difference between classification and time-series problems in consideration of the bias-plus-variance decomposition. A Monte Carlo study on the role of bias and variance in neural networks time-series forecasting is conducted. We find that both input lag structure and hidden nodes are important in contributing to the overall forecasting performance. The results also suggest that overspecification of input nodes in neural network modeling does not impact the model bias, but has significant effect on the model variance. Methods such as neural ensembles that focus on reducing the model variance, therefore, can be valuable and effective in time-series forecasting modeling.     

Short-term traffic flow forecasting: parametric and nonparametric approaches via emotional temporal difference learning

Information signal from real case and natural complex dynamical systems such as traffic flow are usually specified by irregular motions. Chaotic nonlinear dynamics approach is now the most powerful tool for scientists to deal with complexities in real cases, and neural networks and neuro-fuzzy models are widely used for their capabilities in nonlinear modeling of chaotic systems more than the traditional methods. As mentioned, the traffic flow conditions caused the forecasting values of traffic flow to lack robustness and accuracy. In this paper, the traffic flow forecasting is analyzed with emotional concepts and multi-agent systems (MASs) points of view as a new method in this field. The findings enabled the researchers to develop a newly object-oriented method of forecasting traffic flow. Its architecture is based on a temporal difference (TD) Q-learning with a neuro-fuzzy structure, which is the nonparametric approach. The performance of TD Q-learning is improved by emotional learning. The proposed method on the present conditions and the action of the system according to the criteria could forecast traffic signals so that the objectives are reached in minimum time. The ability of presented learning algorithm to prospect gains from future actions and obtain rewards from its past experiences allows emotional TD Q-learning algorithm to improve its decisions for the best possible actions. In addition, to study in a more practical situation, the neuro-fuzzy behaviors could be modeled by MAS. The proposed method (intelligent/nonparametric approach) is compared by parametric approach, autoregressive integrated moving average (ARIMA) method, which is implemented by multi-layer perceptron neural networks and called ARIMANN. Here, the ARIMANN is updated by backpropagation and temporal difference backpropagation for the first time. The simulation results revealed that the studied forecaster could discover the optimal forecasting by means of the Q-learning algorithm. Difficult to handle through parametric and classic methods, the real traffic flow signals used for fitting the algorithms is obtained from a two-lane street I-494 in Minnesota City.     

Development of a recurrent Sigma-Pi neural network rainfall forecasting system in Hong Kong

At the moment, weather forecasting is still an art — the experience and intuition of forecasters play a significant role in determining the quality of forecasting. This paper describes the development of a new approach to rainfall forecasting using neural networks. It deals with the extraction of information from radar images and an evaluation of past rain gauge records to provide shortterm rainfall forecasting. All of the meteorological data were provided by the Royal Observatory of Hong Kong (ROHK). Preprocessing procedures were essential for this neural network rainfall forecasting. The forecast of the rainfall was performed every half an hour so that a storm warning signal can be delivered to the public in advance. The network architecture is based on a recurrent Sigma-Pi network. The results are very promising, and this neural-based rainfall forecasting system is capable of providing a rain storm warning signal to the Hong Kong public one hour ahead.     

Computational intelligence approaches and linear models in case studies of forecasting exchange rates

Artificial neural networks and fuzzy systems, have gradually established themselves as a popular tool in approximating complicated nonlinear systems and time series forecasting. This paper investigates the hypothesis that the nonlinear mathematical models of multilayer perceptron and radial basis function neural networks and the Takagi–Sugeno (TS) fuzzy system are able to provide a more accurate out-of-sample forecast than the traditional auto regressive moving average (ARMA) and ARMA generalized auto regressive conditional heteroskedasticity (ARMA-GARCH) linear models. Using series of Brazilian exchange rate (R$/US$) returns with 15 min, 60 min and 120 min, daily and weekly basis, the one-step-ahead forecast performance is compared. Results indicate that forecast performance is strongly related to the series’ frequency and the forecasting evaluation shows that nonlinear models perform better than their linear counterparts. In the trade strategy based on forecasts, nonlinear models achieve higher returns when compared to a buy-and-hold strategy and to the linear models.     

基于构造性神经网络的时间序列混合预测模型 *

针对传统时间序列预测模型不适应非线性预测而适应非线性预测的BP算法存在收敛速度慢,且容易陷入局部极小等问题,提出一种基于构造性神经网络的时间序列混合预测模型。采用构造性神经网络模型（覆盖算法）得出的类别值对统计时间序列模型的预测值进行修正,建立一种同时考虑时间序列自身周期变化和外生变量因子对时间序列未来变化趋势影响的混合预测模型,涵盖了实际问题的线性和非线性两方面,提高了预测精度。将该模型应用到粮食产量的预测中,取得了较好的预测效果。     

基于构造性神经网络的时间序列混合预测模型 *

针对传统时间序列预测模型不适应非线性预测而适应非线性预测的 BP算法存在收敛速度慢 ,且容易陷入局部极小等问题 ,提出一种基于构造性神经网络的时间序列混合预测模型。采用构造性神经网络模型 (覆盖算法 )得出的类别值对统计时间序列模型的预测值进行修正 ,建立一种同时考虑时间序列自身周期变化和外生变量因子对时间序列未来变化趋势影响的混合预测模型 ,涵盖了实际问题的线性和非线性两方面 ,提高了预测精度。将该模型应用到粮食产量的预测中 ,取得了较好的预测效果。     

Wavelet-based multi-resolution analysis and artificial neural networks for forecasting temperature and thermal power consumption

As part of the OptiEnR research project, the present paper deals with outdoor temperature and thermal power consumption forecasting. This project focuses on optimizing the functioning of a multi-energy district boiler (La Rochelle, west coast of France), adding to the plant a thermal storage unit and implementing a model-based predictive controller. The proposed short-term forecast method is based on the concept of time series and uses both a wavelet-based multi-resolution analysis and multi-layer artificial neural networks. One could speak of “MRA-ANN” methodology. The discrete wavelet transform allows decomposing sequences of past data in subsequences (named coefficients) according to different frequency domains, while preserving their temporal characteristics. From these coefficients, multi-layer Perceptrons are used to estimate future subsequences of 4 h and 30 min. Future values of outdoor temperature and thermal power consumption are then obtained by simply summing up the estimated coefficients. Substituting the prediction task of an original time series of high variability with the estimation of its wavelet coefficients on different levels of lower variability is the main idea of the present work. In addition, the sequences of past data are completed, for each of their components, by both the minute of the day and the day of the year to place the developed model in time. The present paper mainly focuses on the impact on forecast accuracy of various parameters, related with the discrete wavelet transform, such as both the wavelet order and the decomposition level, and the topology of the neural networks used. The number of past sequences to take into account and the chosen time step were also major concerns. The optimal configuration for the tools used leads to very good forecasting results and validates the proposed MRA-ANN methodology.     

Prediction of Road Traffic using a Neural Network Approach

A key component of the daily operation and planning activities of a traffic control centre is short-term forecasting, i.e. the prediction of daily to the next few days of traffic flow. Such forecasts have a significant impact on the optimal regulation of the road traffic on all kinds of freeways. They are increasingly important in an environment with increasing road traffic problems. The present paper aims at presenting the effectiveness of a neural network system for prediction based on time-series data. We only use one parameter, namely traffic volume for the forecasting. We employ artificial neural networks for traffic forecasting applied on a road section. Recurrent Jordan networks, popular in the modelling of time series, is examined in this study. Simulation results demonstrate that learning with this type of architecture has a good generalisation ability.     

Combining wavelet-based feature extractions with relevance vector machines for stock index forecasting

Abstract: The relevance vector machine (RVM) is a Bayesian version of the support vector machine, which with a sparse model representation has appeared to be a powerful tool for time-series forecasting. The RVM has demonstrated better performance over other methods such as neural networks or autoregressive integrated moving average based models. This study proposes a hybrid model that combines wavelet-based feature extractions with RVM models to forecast stock indices. The time series of explanatory variables are decomposed using some wavelet bases and the extracted time-scale features serve as inputs of an RVM to perform the non-parametric regression and forecasting. Compared with traditional forecasting models, our proposed method performs best. The root-mean-squared forecasting errors are significantly reduced.