Application of the Back Propagation Neural Network Algorithm with Monotonicity Constraints for Two-Group Classification Problems*

Neural network techniques are widely used in solving pattern recognition or classification problems. However, when statistical data are used in supervised training of a neural network employing the back-propagation least mean square algorithm, the behavior of the classification boundary during training is often unpredictable. This research suggests the application of monotonicity constraints to the back propagation learning algorithm. When the training sample set is preprocessed by a linear classification function, neural network performance and efficiency can be improved in classification applications where the feature vector is related monotonically to the pattern vector. Since most classification problems in business possess monotonic properties, this technique is useful in those problems where any assumptions about the properties of the data are inappropriate.     

Theoretical Distributions of Optima for Univariate Discrimination of Random Data*

Optimal linear discriminant models maximize percentage accuracy for dichotomous classifications, but are rarely used because a theoretical framework that allows one to make valid statements about the statistical significance of the outcomes of such analyses does not exist. This paper describes an analytic solution for the theoretical distribution of optimal values for univariate optimal linear discriminant analysis, under the assumption that the data are random and continuous. We also present the theoretical distribution for sample sizes up to N= 30. The discovery of a statistical framework for evaluating the performance of optimal discriminant models should greatly increase their use by scientists in all disciplines.     

A Cross-Validation Analysis of Neural Network Out-of-Sample Performance in Exchange Rate Forecasting

Econometric methods used in foreign exchange rate forecasting have produced inferior out-of-sample results compared to a random walk model. Applications of neural networks have shown mixed findings. In this paper, we investigate the potentials of neural network models by employing two cross-validation schemes. The effects of different in-sample time periods and sample sizes are examined. Out-of-sample performance evaluated with four criteria across three forecasting horizons shows that neural networks are a more robust forecasting method than the random walk model. Moreover, neural network predictions are quite accurate even when the sample size is relatively small.     

Separation Failure in Linear Programming Discriminant Models

Linear programming discriminant analysis (LPDA) models are designed around a variety of objective functions, each representing a different measure of separation of the training samples by the resulting discriminant function. A separation failure is defined to be the selection of an “optimal” discriminant function which incompletely separates a pair of completely separable training samples. Occurrence of a separation failure suggests that the chosen discriminant function may have an unnecessarily low classification accuracy on the actual populations involved. In this paper, a number of the LPDA models proposed for the two-group case are examined to learn which are subject to separation failure. It appears that separation failure in any model can be avoided by applying the model twice, reversing group designations.     

A learning vector quantization neural network model for the classification of industrial construction projects

In several key functional areas of contemporary engineering and management science, neural networks have steadily been gaining recognition as robust and reliable tools for classification problems. This paper describes a new application of the learning vector quantization neural network: the classification of the degree of modularization appropriate for the construction of an industrial facility. This neural network uses variables related to plant location, labor issues, organizational issues, plant characteristics, project risks, and environmental issues as inputs to perform the classification. The neural network training and performance evaluation is also discussed.     

基于改进GMDH的目标客户选择模型研究

近年来,目标客户选择建模成为客户关系管理领域的研究热点。为了解决用于目标客户选择建模的训练样本类别分布高度不平衡的问题,本文首先提出了混合抽样方法。进一步地,将数据分组处理(GMDH)神经元网络引入到客户特征选择中,提出新的特征选择算法Log-GMDH。该算法分别从传递函数的选择和新的外准则的构建两个方面对传统GMDH网络模型进行了改进。最后,将提出的混合抽样、Log-GMDH和Logistic回归分类算法相结合,构建目标客户选择模型LogGMDH-Logistic。在CoIL2000预测竞赛中某汽车保险公司的目标客户选择数据集上进行实证分析,结果表明,LogGMDH-Logistic模型不仅在性能上优于已有的一些目标客户选择模型,而且具有很好的可解释性。     

Leveraging the Strengths of Choice Models and Neural Networks: A Multiproduct Comparative Analysis*

Choice models and neural networks are two approaches used in modeling selection decisions. Defining model performance as the out‐of‐sample prediction power of a model, we test two hypotheses: (i) choice models and neural network models are equal in performance, and (ii) hybrid models consisting of a combination of choice and neural network models perform better than each stand‐alone model. We perform statistical tests for two classes of linear and nonlinear hybrid models and compute the empirical integrated rank (EIR) indices to compare the overall performances of the models. We test the above hypotheses by using data for various brand and store choices for three consumer products. Extensive jackknifing and out‐of‐sample tests for four different model specifications are applied for increasing the external validity of the results. Our results show that using neural networks has a higher probability of resulting in a better performance. Our findings also indicate that hybrid models outperform stand‐alone models, in that using hybrid models guarantee overall results equal or better than the two stand‐alone models. The improvement is particularly significant in cases where neither of the two stand‐alone models is very accurate in prediction, indicating that the proposed hybrid models may capture aspects of predictive accuracy that neither stand‐alone model is capable of on their own. Our results are particularly important in brand management and customer relationship management, indicating that multiple technologies and mixture of technologies may yield more accurate and reliable outcomes than individual ones.     

基于ARTⅡ网络的煤炭资源资产分类研究

本文建立了用于煤炭资源资产分类的ARTⅡ神经网络模型,编制了相应的计算机和软件,并将ARTⅡ模型与模糊分类模型和基于BP网络的分类模型进行了对比分析,实例运行结果表明,用ARTⅡ网络进行分类具有分类稳定、结果可靠等特点。     

遗传算法优化神经网络及信用评价研究

研究关于公司神经网络信用评估问题的现状,提出遗传算法辅助网络训练策略(优化后的网络称为进化网络),克服传统网络建模中产生的局部极小缺陷。建立了适合于我国商业企业的信用评分指标体系;然后依据该指标体系建立了基于进化神经网络的信用评估模型;最后,利用样本公司实际指标数据对该模型的评分效果进行了比较研究。     

Refining Two-Group Multivariable Classification Models Using Univariate Optimal Discriminant Analysis*

Fisher's discriminant analysis (FDA) is often used to obtain a prediction model for dichotomous classifications on the basis of two or more independent variables. FDA provides an equation whereby values on independent variables are combined into a single predicted value (Y*) that is compared against a cutpoint and direction in order to make classifications. Theoretically, univariate optimal discriminant analysis employed on these Y* will maximize training classification accuracy. This methodology is illustrated using three examples.     

An empirical study of design and testing of hybrid evolutionary–neural approach for classification

We propose a hybrid evolutionary–neural approach for binary classification that incorporates a special training data over-fitting minimizing selection procedure for improving the prediction accuracy on holdout sample. Our approach integrates parallel global search capability of genetic algorithms (GAs) and local gradient-descent search of the back-propagation algorithm. Using a set of simulated and real life data sets, we illustrate that the proposed hybrid approach fares well, both in training and holdout samples, when compared to the traditional back-propagation artificial neural network (ANN) and a genetic algorithm-based artificial neural network (GA-ANN).     

The Effect of Misclassification Costs on Neural Network Classifiers

The potential of neural networks for classification problems has been established by numerous successful applications reported in the literature. One of the major assumptions used in almost all studies is the equal cost consequence of misclassification. With this assumption, minimizing the total number of misclassification errors is the sole objective in developing a neural network classifier. Often this is done simply to ease model development and the selection of classification decision points. However, it is not appropriate for many real situations such as quality assurance, direct marketing, bankruptcy prediction, and medical diagnosis where misclassification costs have unequal consequences for different categories. In this paper, we investigate the issue of unequal misclassification costs in neural network classifiers. Through an application in thyroid disease diagnosis, we find that different cost considerations have significant effects on the classification performance and that appropriate use of cost information can aid in optimal decision making. A cross-validation technique is employed to alleviate the problem of bias in the training set and to examine the robustness of neural network classifiers with regard to sampling variations and cost differences.     

Management of school locations allowing for free school choice

Nearly without exception, we find in literature (school) location models with exogenously given demand. Indeed, we know from a large number of empirical studies that this assumption is unrealistic. Therefore, we propose a discrete location model for school network planning with free school choice that is based on simulated utility values for a large average sample. The objective is to maximize the standardized expected utility of all students taking into account capacity constraints and a given budget for the school network. The utility values of each student for the schools are derived from a random utility model (RUM). The proposed approach is general in terms of the RUM used. Moreover, we do not have to make assumptions about the functional form of the demand function. Our approach, which combines econometric and mathematical methods, is a linear 0–1 program although we consider endogenous demand by a highly non-linear function. The proposed program enables practicing managers to consider student demand adequately within their decision making. By a numerical investigation we show that this approach enables us to solve instances of real size optimally – or at least close to optimality – within few minutes using GAMS/Cplex.     

A Comparison of Linear Programming and Parametric Approaches to the Two-Group Discriminant Problem*

Recent simulation-based studies of linear programming models for discriminant analysis have used the Fisher linear discriminant function as the benchmark for parametric methods. This article reports experimental evidence which suggests that, while some linear programming models may match or even exceed the Fisher approach in classification accuracy, none of the fifteen models tested is as accurate on normally distributed data as the Smith quadratic discriminant function. At the minimum, further testing is warranted with an emphasis on data sets that arise from significantly non-Gaussian populations.     

Neural Network Earnings per Share Forecasting Models: A Comparative Analysis of Alternative Methods

In this paper, we present a comparative analysis of the forecasting accuracy of univariate and multivariate linear models that incorporate fundamental accounting variables (i.e., inventory, accounts receivable, and so on) with the forecast accuracy of neural network models. Unique to this study is the focus of our comparison on the multivariate models to examine whether the neural network models incorporating the fundamental accounting variables can generate more accurate forecasts of future earnings than the models assuming a linear combination of these same variables. We investigate four types of models: univariate‐linear, multivariate‐linear, univariate‐neural network, and multivariate‐neural network using a sample of 283 firms spanning 41 industries. This study shows that the application of the neural network approach incorporating fundamental accounting variables results in forecasts that are more accurate than linear forecasting models. The results also reveal limitations of the forecasting capacity of investors in the security market when compared to neural network models.     

客户信用评估半监督协同训练模型研究

在现实的很多信用评估问题中,由于对样本进行类别标记需要花费大量的人力、财力和物力,往往只能获取少量有类别标签的样本来训练分类模型,而把数据库中大量无类别标签的客户样本舍弃。为解决这一问题,本研究引入半监督学习技术,并将其与多分类器集成技术中的随机子空间方法(Random Subspace, RSS)相结合,构建了类别不平衡环境下基于RSS的半监督协同训练模型RSSCI。该模型主要包括三个阶段:1)使用RSS方法训练得到若干基本分类器;2)从大量无类别标签数据集中选择性标记一部分最合适的样本加入到原始训练集中;3)在最终的训练集上训练分类模型,并对测试集样本进行分类。在三个客户信用评估数据集上进行实证分析,结果表明,RSSCI模型的信用评估性能不仅优于常用的监督式集成信用评估模型,也优于已有的一些半监督协同训练信用评估模型。     

Insights into neural-network forecasting of time series corresponding to ARMA(p,q) structures

Motivated by the lack of evidence supporting the conjecture that the back-propagation neural network (BPNN) is a universal approximator thus it can perform at least comparably to linear models on linear data, this study is designed to answer two primary research questions, namely, “how does the BPNN perform with respect to various underlying ARMA(p,q) structures?” and “how does the level of noise in the training time series affect the BPNN’s performance?” The goal is to understand better the modelling and forecasting ability of BPNNs on a special class of time series and suggest proper training strategies to improve performance. Using Box–Jenkins models’ performance as a benchmark, it is concluded that BPNNs generally performed well and consistently for time series corresponding to ARMA(p,q) structures. BPNNs’ ability to model and forecast is not affected by the number of parameters but by the magnitude of the coefficients of the underlying structure. Overall, BPNNs perform significantly better for most of the structures when a particular noise level is considered during network training. Therefore, a proper strategy is to train networks at a noise level consistent in magnitude with the time series’ sample standard deviation.     

Solving the Classification Problem in Discriminant Analysis Via Linear and Nonlinear Programming Methods*

This paper demonstrates the feasibility of applying nonlinear programming methods to solve the classification problem in discriminant analysis. The application represents a useful extension of previously proposed linear programming-based solutions for discriminant analysis. The analysis of data obtained by conducting a Monte Carlo simulation experiment shows that these new procedures are promising. Future research that should promote application of the proposed methods for solving classification problems in a business decision-making environment is discussed.     

Combining Neural Networks and Statistical Predictions to Solve the Classification Problem in Discriminant Analysis*

A number of recent studies have compared the performance of neural networks (NNs) to a variety of statistical techniques for the classification problem in discriminant analysis. The empirical results of these comparative studies indicate that while NNs often outperform the more traditional statistical approaches to classification, this is not always the case. Thus, decision makers interested in solving classification problems are left in a quandary as to what tool to use on a particular data set. We present a new approach to solving classification problems by combining the predictions of a well-known statistical tool with those of an NN to create composite predictions that are more accurate than either of the individual techniques used in isolation.     

基于遗传技术辅助设计的神经网络期货市场预测

本文在对期货市场的历史数据进行预分析的基础上,建立了神经网络期货市场预测模型．文中不仅对神经网络进行了改进研究,还利用遗传技术优化网络的结构和参数．运运实例对模型进行学习与测试的实验结果表明,利用遗传技术辅助设计的神经网络预测模型能较准确地预报期货价格的波动趋势.