A principled approach for building and evaluating neural network classification models

Authors:
Victor L. Berardi;B. Eddy Patuwo;Michael Y. Hu
Affiliations:
Department of Management and Information Systems, Graduate School of Management, Kent State University, 6000 Frank Road, Canton, OH;Department of Management and Information Systems, Graduate School of Management, Kent State University, 6000 Frank Road, Canton, OH;Department of Marketing, Kent State University, Canton, OH
Venue:
Decision Support Systems
Year:
2004

Citing 9
Cited 2

Multilayer feedforward networks are universal approximators

Neural Networks
Links between Markov models and multilayer perceptrons

Advances in neural information processing systems 1
Connectionist nonparametric regression: multilayer feedforward networks can learn arbitrary mappings

Neural Networks
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Approximation capabilities of multilayer feedforward networks

Neural Networks
Neural networks and the bias/variance dilemma

Neural Computation
Organizational Learning as a Foundation of Electronic Commerce in the Network Organization

International Journal of Electronic Commerce
Artificial Agents for Discovering Business Strategies for Network Industries

International Journal of Electronic Commerce
Application of Decision-Tree Induction Techniques to Personalized Advertisements on Internet Storefronts

International Journal of Electronic Commerce

An investigation of neural network classifiers with unequal misclassification costs and group sizes

Decision Support Systems
A methodology for comparing classification methods through the assessment of model stability and validity in variable selection

Decision Support Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a principled approach to building and evaluating neural network classification models for decision support system (DSS) implementations. First, the usefulness of neural networks for use with e-commerce data and for Bayesian classification is discussed. Next, the theory concerning model accuracy and generalization is presented. Then, the principled approach, which is developed with consideration of these issues, is described. Through an illustrative problem, it is seen that when problem complexity is considered, the classification performance of the neural networks can be much better than what is observed. Furthermore, it is seen that model order selection processes based upon a single dataset can lead to an incorrect conclusion concerning the best model, which impacts model error and utility.