An intelligent model selection and forecasting system

In this paper we present an intelligent decision‐support system based on neural network technology for model selection and forecasting. While most of the literature on the application of neural networks in forecasting addresses the use of neural network technology as an alternative forecasting tool, limited research has focused on its use for selection of forecasting methods based on time‐series characteristics. In this research, a neural network‐based decision support system is presented as a method for forecast model selection. The neural network approach provides a framework for directly incorporating time‐series characteristics into the model‐selection phase. Using a neural network, a forecasting group is initially selected for a given data set, based on a set of time‐series characteristics. Then, using an additional neural network, a specific forecasting method is selected from a pool of three candidate methods. The results of training and testing of the networks are presented along with conclusions. Copyright © 1999 John Wiley & Sons, Ltd.     

改进的模糊神经网络算法在车型识别中的应用

FBP和FCNN网络是模式识别中应用最为广泛的两种神经网络,本文将这两种网络应用于车型识别,分别建立了车型识别模型。利用混沌对初值的极端敏感依赖提出了FCNN网络算法,通过对车型图像数据库进行仿真实验,对比分析它们各自的识别率和泛化能力等性能指标,证明了FCNN网络算法的有效性。     

利用AR模型参数和BP神经网络辨识微震信号

利用AR模型参数和BP神经网络,针对矿山微震信号具有频带较宽、谱成分丰富的特性,提出了时不同频率范围的信号和噪声进行滤波处理的方法.利用该方法可将噪声与信号分离以及将不同频段信号分解,从而达到滤波的目的.实验结果表明,利用AR模型参数和BP神经网络能够有效去除微震异常信号的噪声,可应用于微震信号的预处理和微震预测.     

Neural networks and the multinomial logit for brand choice modelling: a hybrid approach

The study of brand choice decisions with multiple alternatives has been successfully modelled for more than a decade using the Multinomial Logit model. Recently, neural network modelling has received increasing attention and has been applied to an array of marketing problems such as market response or segmentation. We show that a Feedforward Neural Network with Softmax output units and shared weights can be viewed as a generalization of the Multinomial Logit model. The main difference between the two approaches lies in the ability of neural networks to model non‐linear preferences with few (if any) a priori assumptions about the nature of the underlying utility function, while the Multinomial Logit can suffer from a specification bias. Being complementary, these approaches are combined into a single framework. The neural network is used as a diagnostic and specification tool for the Logit model, which will provide interpretable coefficients and significance statistics. The method is illustrated on an artificial dataset where the market is heterogeneous. We then apply the approach to panel scanner data of purchase records, using the Logit to analyse the non‐linearities detected by the neural network. Copyright © 2000 John Wiley & Sons, Ltd.     

Using a heterogeneous multinomial probit model with a neural net extension to model brand choice

The multinomial probit model introduced here combines heterogeneity across households with flexibility of the (deterministic) utility function. To achieve flexibility deterministic utility is approximated by a neural net of the multilayer perceptron type. A Markov Chain Monte Carlo method serves to estimate heterogeneous multinomial probit models which fulfill economic restrictions on signs of (marginal) effects of predictors (e.g., negative for price). For empirical choice data the heterogeneous multinomial probit model extended by a multilayer perceptron clearly outperforms all the other models studied. Moreover, replacing homogeneous by heterogeneous reference price mechanisms and thus allowing price expectations to be formed differently across households also leads to better model performance. Mean utility differences and mean elasticities w.r.t. price and price deviation from reference price demonstrate that models with linear utility and nonlinear utility approximated by a multilayer perceptron lead to very different implications for managerial decision making. Copyright © 2007 John Wiley & Sons, Ltd.     

Comparison of Near Neighbour and Neural Network in Travel Forecasting

In this paper we confirm the existence of nonlinear dynamics in a time series of airport arrivals. We subsequently propose alternative non‐parametric forecasting techniques to be used in a travel forecasting problem, emphasizing the difference between the reconstruction and learning approach. We compare the results achieved in point prediction versus sign prediction. The reconstruction approach offers better results in sign prediction and the learning approach in point prediction. Copyright © 2015 John Wiley & Sons, Ltd.     

Model uncertainty and forecast accuracy

In time-series analysis, a model is rarely pre-specified but rather is typically formulated in an iterative, interactive way using the given time-series data. Unfortunately the properties of the fitted model, and the forecasts from it, are generally calculated as if the model were known in the first place. This is theoretically incorrect, as least squares theory, for example, does not apply when the same data are used to formulates and fit a model. Ignoring prior model selection leads to biases, not only in estimates of model parameters but also in the subsequent construction of prediction intervals. The latter are typically too narrow, partly because they do not allow for model uncertainty. Empirical results also suggest that more complicated models tend to give a better fit but poorer ex-ante forecasts. The reasons behind these phenomena are reviewed. When comparing different forecasting models, the BIC is preferred to the AIC for identifying a model on the basis of within-sample fit, but out-of-sample forecasting accuracy provides the real test. Alternative approaches to forecasting, which avoid conditioning on a single model, include Bayesian model averaging and using a forecasting method which is not model-based but which is designed to be adaptable and robust.     

Forecasting and trading currency volatility: an application of recurrent neural regression and model combination

In this paper, we examine the use of non‐parametric Neural Network Regression (NNR) and Recurrent Neural Network (RNN) regression models for forecasting and trading currency volatility, with an application to the GBP/USD and USD/JPY exchange rates. Both the results of the NNR and RNN models are benchmarked against the simpler GARCH alternative and implied volatility. Two simple model combinations are also analysed. The intuitively appealing idea of developing a nonlinear nonparametric approach to forecast FX volatility, identify mispriced options and subsequently develop a trading strategy based upon this process is implemented for the first time on a comprehensive basis. Using daily data from December 1993 through April 1999, we develop alternative FX volatility forecasting models. These models are then tested out‐of‐sample over the period April 1999–May 2000, not only in terms of forecasting accuracy, but also in terms of trading efficiency: in order to do so, we apply a realistic volatility trading strategy using FX option straddles once mispriced options have been identified. Allowing for transaction costs, most trading strategies retained produce positive returns. RNN models appear as the best single modelling approach yet, somewhat surprisingly, model combination which has the best overall performance in terms of forecasting accuracy, fails to improve the RNN‐based volatility trading results. Another conclusion from our results is that, for the period and currencies considered, the currency option market was inefficient and/or the pricing formulae applied by market participants were inadequate. Copyright © 2002 John Wiley & Sons, Ltd.     

Predicting multistage financial distress: Reflections on sampling,feature and model selection criteria

This research proposes a prediction model of multistage financial distress (MSFD) after considering contextual and methodological issues regarding sampling, feature and model selection criteria. Financial distress is defined as a three‐stage process showing different nature and intensity of financial problems. It is argued that applied definition of distress is independent of legal framework and its predictability would provide more practical solutions. The final sample is selected after industry adjustments and oversampling the data. A wrapper subset data mining approach is applied to extract the most relevant features from financial statement and stock market indicators. An ensemble approach using a combination of DTNB (decision table and naïve base hybrid model), LMT (logistic model tree) and A2DE (alternative N dependence estimator) Bayesian models is used to develop the final prediction model. The performance of all the models is evaluated using a 10‐fold cross‐validation method. Results showed that the proposed model predicted MSFD with 84.06% accuracy. This accuracy increased to 89.57% when a 33.33% cut‐off value was considered. Hence the proposed model is accurate and reliable to identify the true nature and intensity of financial problems regardless of the contextual legal framework.     

Model selection and forecasting for long-range dependent processes

Fractionally integrated autoregressive moving-average (ARFIMA) models have proved useful tools in the analysis of time series with long-range dependence. However, little is known about various practical issues regarding model selection and estimation methods, and the impact of selection and estimation methods on forecasts. By means of a large-scale simulation study, we compare three different estimation procedures and three automatic model-selection criteria on the basis of their impact on forecast accuracy. Our results endorse the use of both the frequency-domain Whittle estimation procedure and the time-domain approximate MLE procedure of Haslett and Raftery in conjunction with the AIC and SIC selection criteria, but indicate that considerable care should be exercised when using ARFIMA models. In general, we find that simple ARMA models provide competitive forecasts. Only a large number of observations and a strongly persistent time series seem to justify the use of ARFIMA models for forecasting purposes.     

Choosing among competing econometric forecasts: Regression‐based forecast combination using model selection

Forecast combination based on a model selection approach is discussed and evaluated. In addition, a combination approach based on ex ante predictive ability is outlined. The model selection approach which we examine is based on the use of Schwarz (SIC) or the Akaike (AIC) Information Criteria. Monte Carlo experiments based on combination forecasts constructed using possibly (misspecified) models suggest that the SIC offers a potentially useful combination approach, and that further investigation is warranted. For example, combination forecasts from a simple averaging approach MSE‐dominate SIC combination forecasts less than 25% of the time in most cases, while other ‘standard’ combination approaches fare even worse. Alternative combination approaches are also compared by conducting forecasting experiments using nine US macroeconomic variables. In particular, artificial neural networks (ANN), linear models, and professional forecasts are used to form real‐time forecasts of the variables, and it is shown via a series of experiments that SIC, t‐statistic, and averaging combination approaches dominate various other combination approaches. An additional finding is that while ANN models may not MSE‐dominate simpler linear models, combinations of forecasts from these two models outperform either individual forecast, for a subset of the economic variables examined. Copyright © 2001 John Wiley & Sons, Ltd.     

Predicting LDC debt rescheduling: performance evaluation of OLS,logit, and neural network models

Empirical studies in the area of sovereign debt have used statistical models singularly to predict the probability of debt rescheduling. Unfortunately, researchers have made few efforts to test the reliability of these model predictions or to identify a superior prediction model among competing models. This paper tested neural network, OLS, and logit models' predictive abilities regarding debt rescheduling of less developed countries (LDC). All models predicted well out‐of‐sample. The results demonstrated a consistent performance of all models, indicating that researchers and practitioners can rely on neural networks or on the traditional statistical models to give useful predictions. Copyright © 2001 John Wiley & Sons, Ltd.     

一个网构软件可信实体模型及基于评估的信任度量

对于运行在开放、动态、难控的互联网环境的网构软件,其可信性保障与管理是一个重要课题．目前的研究多是基于信任网络思想的信任度量及演化模型,这种模型对于网构软件来说,在信任的来源、实体间信任关系的约束、信任传递参数的设置方面仍存在着不足．因此,本文引入可信计算中信任链模型的思想,提出了一个网构软件可信智能实体模型,并在此基础上构建了基于评估的信任度量方法．首先通过动态自省、显式自明和自主演化的机制保障了实体本身的可信,建立了信任的基点;并给出了形式化的描述及交互行为的动态监测;然后通过建立Bayes网络综合推荐信任并使用评估方法加以修正,以精确计算信任传递过程中的衰减参数,建立了信任链传递过程中的可信认证机制;最后通过实验验证了所提出方法的正确性．     

Predictive modeling of consumer color preference: Using retail data and merchandise images

The popularity of a fashion item depends on its color, shape, texture, and price. For different items (with all attributes identical except color) of a specific product, fashion retailers need to learn consumer color preference and decide their order quantities accordingly to match their products to consumer demand. This study aims to predict consumer color preference using the knowledge learned from merchandise images, historical retail data, and fashion trends. In our work, merchandise images are analyzed to extract color features, and the retail data of a sportswear retailer are used to reveal consumer choices among items with various colors. Choice behavior is described by a multinomial logit model, whose utility function captures the relationship between color features and popularity. Both linear functions and neural networks are applied to represent the utility function, and their out-of-sample prediction performances are compared. According to the out-of-sample performance test, our model shows reasonable predictive power and can outperform order decisions made by fashion buyers.     

Assessing the Macroeconomic Forecasting Performance of Boosting: Evidence for the United States,the Euro Area and Germany

The use of large datasets for macroeconomic forecasting has received a great deal of interest recently. Boosting is one possible method of using high‐dimensional data for this purpose. It is a stage‐wise additive modelling procedure, which, in a linear specification, becomes a variable selection device that iteratively adds the predictors with the largest contribution to the fit. Using data for the United States, the euro area and Germany, we assess the performance of boosting when forecasting a wide range of macroeconomic variables. Moreover, we analyse to what extent its forecasting accuracy depends on the method used for determining its key regularization parameter: the number of iterations. We find that boosting mostly outperforms the autoregressive benchmark, and that K‐fold cross‐validation works much better as stopping criterion than the commonly used information criteria. Copyright © 2014 John Wiley & Sons, Ltd.     

Probability distributions,trading strategies and leverage: an application of Gaussian mixture models

The purpose of this paper is twofold. Firstly, to assess the merit of estimating probability density functions rather than level or classification estimations on a one‐day‐ahead forecasting task of the EUR/USD time series. This is implemented using a Gaussian mixture model neural network, benchmarking the results against standard forecasting models, namely a naïve model, a moving average convergence divergence technical model (MACD), an autoregressive moving average model (ARMA), a logistic regression model (LOGIT) and a multi‐layer perceptron network (MLP). Secondly, to examine the possibilities of improving the trading performance of those models with confirmation filters and leverage. While the benchmark models perform best without confirmation filters and leverage, the Gaussian mixture model outperforms all of the benchmarks when taking advantage of the possibilities offered by a combination of more sophisticated trading strategies and leverage. This might be due to the ability of the Gaussian mixture model to identify successfully trades with a high Sharpe ratio. Copyright © 2004 John Wiley & Sons, Ltd.     

Gastrointestinal transit and digestibility of maltitol,sucrose and sorbitol in rats: A multicompartmental model and recovery study

Using data obtained with a dye marker and the gavage technique, the kinetics of gastrointestinal transit of different loads of sugar substitutes (maltitol, sorbitol) and sugar (sucrose) in the rat were analysed using a linear multicompartmental model over a range from the realistic to the non-physiologic high, of carbohydrate intake levels and using only a few experimental time points. The model gave detailed insight into intestinal propulsion and gastrocecal transit time. Rate constants of transport between the compartments investigated were determined; they showed characteristics which could be related to the substance and the dosage administered. Analyses of the gastrointestinal content and calculations of the intestinal net water movement showed that the digestibility and absorption of the disaccharide sugar alcohol, maltitol, in the small gut depended inversely on the dose ingested. For all substances tested, caloric availability in the small intestine was calculated. At a physiological low level of maltitol intake, the results also indicated an insignificant calorie-saving effect in comparison to sucrose, an effect based mainly on the slow absorption rate of the maltitol cleavage product sorbitol.