Financial time series prediction using polynomial pipelined neural networks

This paper proposes a novel type of higher-order pipelined neural network: the polynomial pipelined neural network. The proposed network is constructed from a number of higher-order neural networks concatenated with each other to predict highly nonlinear and nonstationary signals based on the engineering concept of divide and conquer. The polynomial pipelined neural network is used to predict the exchange rate between the US dollar and three other currencies. In this application, two sets of experiments are carried out. In the first set, the input data are pre-processed between 0 and 1 and passed to the neural networks as nonstationary data. In the second set of experiments, the nonstationary input signals are transformed into one step relative increase in price. The network demonstrates more accurate forecasting and an improvement in the signal to noise ratio over a number of benchmarked neural networks.     

SOM time series clustering and prediction with recurrent neural networks

Local models for regression have been the focus of a great deal of attention in the recent years. They have been proven to be more efficient than global models especially when dealing with chaotic time series. Many models have been proposed to cluster time series and they have been combined with several predictors. This paper presents an extension for recurrent neural networks applied to local models and a discussion about the obtained results.     

基于RBF神经网络的非线性时间序列在线预测

针对非线性非高斯时间序列, 提出观测噪声服从隐马尔可夫模型(HMM)的径向基函数(RBF)神经网络(RBF-HMM)预测模型, 其特点在于模型输入包含误差反馈项、RBF网络隐含层节点数的可变性和观测噪声的隐马尔可夫性; 并采用序列蒙特卡罗(SMC)方法实现基于RBF-HMM模型的时间序列在线预测. 最后采用太阳黑子数平滑月均值数据和CRU国际钢材价格指数月数据进行实证研究, 结果表明该模型的有效性.     

Statistical fuzzy interval neural networks for currency exchange rate time series prediction

In this paper, the statistical fuzzy interval neural network with statistical interval input and output values is proposed to perform statistical fuzzy knowledge discovery and the currency exchange rate prediction. Time series data sets are grouped into time series data granules with statistical intervals. The statistical interval data sets including week-based averages, maximum errors of estimate and standard deviations are used to train the fuzzy interval neural network to discover fuzzy IF-THEN rules. The output of the fuzzy interval neural network is an interval value with certain percent confidence. Simulations are completed in terms of the exchange rates between US Dollar and other three currencies (Japanese Yen, British Pound and Hong Kong Dollar). The simulation results show that the fuzzy interval neural network can provide more tolerant prediction results.     

Sugarcane yield prediction in Brazil using NDVI time series and neural networks ensemble

The objective of this study is to predict the sugarcane yield in São Paulo State, Brazil, using metrics derived from normalized difference vegetation index (NDVI) time series from the Moderate Resolution Imaging Spectroradiometer (MODIS) sensor and an ensemble model of artificial neural networks (ANNs). Sixty municipalities were selected and spectral metrics were extracted from the NDVI time series for each municipality from 2003 to 2012. A neural network wrapper with sequential backward elimination was applied to remove irrelevant and/or redundant features from the initial data set, reducing over-fitting and improving the prediction performance. Afterwards the sugarcane yield was predicted using a stacking ensemble model with ANN. At the predicted yield, the relative root mean square error (RRMSE) was 6.8% and the coefficient of determination (R²) was 0.61. The last three months were removed from the initial time-series data set to forecast the final sugarcane yield, and the process was repeated. The feature selection (FS) improved again the prediction performance and Stacking improved the FS results: RRMSE increased to 8% and R² to 0.43. The yield was also estimated for the entire State, based on the average of the 60 selected municipalities, which were compared to the official data surveys. The Stacking method was able to estimate the sugarcane yield for São Paulo State with a smaller RMSE than the official data surveys, anticipating the crop forecast by three months before the harvest.     

Operations and learning in neural networks for robust prediction

We consider stochastic neural networks, the objective of which is robust prediction for spatial control. We develop neural structures and operations, in which the representations of the environment are preprocessed and provided in quantized format to the prediction layer, and in which the response of each neuron is binary. We also identify the pertinent stochastic network parameters, and subsequently develop a supervised learning algorithm for them. The on-line learning algorithm is based an the Kullback-Leibler performance criterion, it induces backpropagation, and guarantees fast convergence to the prediction probabilities induced by the environment, with probability one.     

BP神经网络和模糊时间序列组合预测模型及其应用

为了解决非线性的时间序列预测问题,提出了BP神经网络和模糊时间序列相结合的预测模型.利用BP神经网络自学习和模糊集能够更客观反应实际情况,通过对时间序列差分模糊化建立数学模型,BP神经网络进行训练,最后去模糊化还原实际.将这种预测方法应用到矿产资源镍价格中,取得了较好的效果.     

Discounted least squares-improved circular back-propogation neural networks with applications in time series prediction

Summary As a generalization of the multi-layer perceptron (MLP), the circular back-propagation neural network (CBP) possesses better adaptability. An improved version of the CBP (the ICBP) is presented in this paper. Despite having less adjustable weights, the ICBP has better adaptability than the CBP, which quite equals the famous Occams razor principle for model selection. In its application to time series, considering both structural changes and correlations of time series itself, we introduce the principle of the discounted least squares (DLS) in CBP and ICBP, respectively, and investigate their predicting capacity further. Introduction of DLS improves the predicting performance of both on a benchmark time series data set. Finally, the comparison of experimental results shows that ICBP with DLS (DLS-ICBP) has better predicting performance than DLS-CBP.Supported by Natural Science (grant No.BK2002092) and QingLan project foundations of Jiangsu province and Returnee foundation of China.     

Application of interval type-2 fuzzy neural networks in non-linear identification and time series prediction

Neural networks (NNs), type-1 fuzzy logic systems and interval type-2 fuzzy logic systems (IT2FLSs) have been shown to be important methods in real world applications, which range from pattern recognition, time series prediction, to intelligent control. Recent research shows that embedding an IT2FLS on an NN can be very effective for a wide number of non-linear complex systems, especially when handling imperfect or incomplete information. In this paper we are presenting several models of interval type-2 fuzzy neural networks (IT2FNNs) that use a set of rules and interval type-2 membership functions for that purpose. Simulation results of non-linear function identification using the IT2FNN for one and three variables and for the Mackey–Glass chaotic time series prediction are presented to illustrate that the proposed models have potential for real world applications.     

Nonlinear time series forecasting with Bayesian neural networks

The Bayesian learning provides a natural way to model the nonlinear structure as the artificial neural networks due to their capability to cope with the model complexity. In this paper, an evolutionary Monte Carlo (MC) algorithm is proposed to train the Bayesian neural networks (BNNs) for the time series forecasting. This approach called as Genetic MC is based on Gaussian approximation with recursive hyperparameter. Genetic MC integrates MC simulations with the genetic algorithms and the fuzzy membership functions. In the implementations, Genetic MC is compared with the traditional neural networks and time series techniques in terms of their forecasting performances over the weekly sales of a Finance Magazine.     

Optimizing wavelet neural networks using modified cuckoo search for multi-step ahead chaotic time series prediction

Determining the optimal number of hidden nodes and their proper initial locations are essentially crucial before the wavelet neural networks (WNNs) start their learning process. In this paper, a novel strategy known as the modified cuckoo search algorithm (MCSA), is proposed for WNNs initialization in order to improve its generalization performance. The MCSA begins with an initial population of cuckoo eggs, which represent the translation vectors of the wavelet hidden nodes, and subsequently refines their locations by imitating the breeding mechanism of cuckoos. The resulting solutions from the MCSA are then used as the initial translation vectors for the WNNs. The feasibility of the proposed method is evaluated by forecasting a benchmark chaotic time series, and its superior prediction accuracy compared with that of conventional WNNs demonstrates its potential benefit.     

Artificial neural networks for earthquake prediction using time series magnitude data or Seismic Electric Signals

The aim of this study is to evaluate the performance of artificial neural networks in predicting earthquakes occurring in the region of Greece with the use of different types of input data. More specifically, two different case studies are considered: the first concerns the prediction of the earthquake magnitude (M) of the following day and the second the prediction of the magnitude of the impending seismic event following the occurrence of pre-seismic signals, the so-called Seismic Electric Signals (SES), which are believed to occur prior to an earthquake, as well as the time lag between the SES and the seismic event itself. The neural network developed for the first case study used only time series magnitude data as input with the output being the magnitude of the following day. The resulting accuracy rate was 80.55% for all seismic events, but only 58.02% for the major seismic events (M ? 5.2 on the Richter scale). Our second case study for earthquake prediction uses SES as input data to the neural networks developed. This case study is separated in two parts with the differentiating element being the way of constructing the missing SES. In the first part, where the missing SES were constructed randomly for all the seismic events, the resulting accuracy rates for the magnitude of upcoming seismic events were just over 60%. In the second part, where the missing SES were constructed for the major seismic events (M ? 5.0 on the Richter scale) only by the use of neural networks reversely, the resulting accuracy rate by predicting only the magnitude was 84.01%, and by predicting both the magnitude and time lag was 83.56% for the magnitude and 92.96% for the time lag. Based on the results we conclude that, when the neural networks are trained by using the appropriate data they are able to generalise and predict unknown seismic events relatively accurately.     

Combining Singular-Spectrum Analysis and neural networks for time series forecasting

In this paper, we propose a combination of an adaptive noise-reduction algorithm based on Singular-Spectrum Analysis (SSA) and a standard feedforward neural prediction model. We test the forecast skill of our method on some short real-world and computergenerated time series with different amounts of additive noise. The results show that our combined technique has better performances than those offered by the same network directly applied to raw data, and therefore is well suited to forecast short and noisy time series with an underlying deterministic data generating process (DGP).     

Residential property price time series forecasting with neural networks

The residential property market accounts for a substantial proportion of UK economic activity. Professional valuers estimate property values based on current bid prices (open market values). However, there is no reliable forecasting service for residential values with current bid prices being taken as the best indicator of future price movement. This approach has failed to predict the periodic market crises or to produce estimates of long-term sustainable value (a recent European Directive could be leading mortgage lenders towards the use of sustainable valuations in preference to the open market value). In this paper, we present artificial neural networks, trained using national housing transaction time series data, which forecasts future trends within the housing market.     

基于集成预测的稀有时间序列检测

为了解决误判问题,从预测的角度给出了离群点的定义,并提出了预测可信度和离群度的概念;同时,提出采用置换技术来降低离群点对预测模型的影响,并提出了基于集成预测的稀有时间序列检测算法。针对真实数据集的实验表明,可信度和离群度的定义是合理的,稀有时间序列检测算法是有效的。     

Hybrid intelligent systems for time series prediction using neural networks, fuzzy logic, and fractal theory

In this paper, we describe a new method for the estimation of the fractal dimension of a geometrical object using fuzzy logic techniques. The fractal dimension is a mathematical concept, which measures the geometrical complexity of an object. The algorithms for estimating the fractal dimension calculate a numerical value using as data a time series for the specific problem. This numerical (crisp) value gives an idea of the complexity of the geometrical object (or time series). However, there is an underlying uncertainty in the estimation of the fractal dimension because we use only a sample of points of the object, and also because the numerical algorithms for the fractal dimension are not completely accurate. For this reason, we have proposed a new definition of the fractal dimension that incorporates the concept of a fuzzy set. This new definition can be considered a weaker definition (but more realistic) of the fractal dimension, and we have named this the "fuzzy fractal dimension." We can apply this new definition of the fractal dimension in conjunction with soft computing techniques for the problem of time series prediction. We have developed hybrid intelligent systems combining neural networks, fuzzy logic, and the fractal dimension, for the problem of time series prediction, and we have achieved very good results.     

A method for selecting similar learning data in the prediction of time series using neural networks

This paper explores a method of improving the predictive performance by the multi-layer feedforward neural network in time series predicting. For the similar data selective learning method, we propose a method of weighting the distance by a power function of correlation coefficients for the time series (CSDS method). The results of numerical experiments show that with the case of a time series whose nature is rather choppy or chaotic, using the CSDS method appropriately is considerably effective to improve the predictive performance and its performance is considerably better than that by the previously proposed other methods.     

On efficient multistep non-linear time series prediction in chaotic diode resonator circuits by optimizing the combination of non-linear time series analysis and neural networks

An improved novel non-linear time series prediction method is presented based on optimizing the combination of non-linear signal analysis and deterministic chaos techniques with Artificial Neural Networks of the Multilayer Perceptron (MLP) type. The proposed methodology has been applied to the non-linear time series produced by a diode resonator chaotic circuit. Multisim is used to simulate the circuit and show the presence of chaos. The first stage of the proposed approach employs a non-linear time series analysis module applying the method proposed by Grasberger and Procaccia, involving estimation of the correlation and minimum embedding dimension as well as of the corresponding largest Lyapunov exponent in combination with a nearest neighbour-based non-linear signal predictor. The two previously mentioned modules are used to construct the first stage of a one-step/multistep predictor while a back-propagation MLP is involved in the second stage to enhance prediction results. The novelty of the proposed two-stage predictor lies on that the back-propagation MLP is employed as an error predictor of the nearest neighbour-based first-stage non-linear signal forecasting application following an efficient strategy for optimizing the combination of nearest neighbour prediction based on deterministic chaos techniques and MLP neural networks. This novel two-stage predictor is evaluated through an extensive experimental study and is favourably compared with rival approaches.     

Combinatorial time series forecasting based on clustering algorithms and neural networks

Time series analysis utilising more than a single forecasting approach is a procedure originated many years ago as an attempt to improve the performance of the individual model forecasts. In the literature there is a wide range of different approaches but their success depends on the forecasting performance of the individual schemes. A clustering algorithm is often employed to distinguish smaller sets of data that share common properties. The application of clustering algorithms in combinatorial forecasting is discussed with an emphasis placed on the formulation of the problem so that better forecasts are generated. Additionally, the hybrid clustering algorithm that assigns data depending on their distance from the hyper-plane that provides their optimal modelling is applied. The developed cluster-based combinatorial forecasting schemes were examined in a single-step ahead prediction of the pound-dollar daily exchange rate and demonstrated an improvement over conventional linear and neural based combinatorial schemes.     

离散过程神经网络在时间序列预测中的应用

为解决复杂时间序列的预测问题,针对目前过程神经网络的输入为多个连续的时变函数,而许多实际问题的输入为多个序列的离散值,提出一种基于离散输入的过程神经网络模型及学习算法;并以太阳黑子数实际数据为例对太阳黑子数时间序列进行预测,仿真结果表明该模型具有很好的逼近和预测能力。