Using Feature Construction to Improve the Performance of Neural Networks

Authors:
Selwyn Piramuthu;Harish Ragavan;Michael J. Shaw
Affiliations:
-;-;-
Venue:
Management Science
Year:
1998

Citing 0
Cited 20

Understanding the Philosophical Underpinnings of Software Engineering Research in Information Systems

Information Systems Frontiers
Connectionist and evolutionary models for learning, discovering and forecasting software effort

Managing data mining technologies in organizations
Technical efficiency-based selection of learning cases to improve forecasting accuracy of neural networks under monotonicity assumption

Decision Support Systems
An empirical study of impact of crossover operators on the performance of non-binary genetic algorithm based neural approaches for classification

Computers and Operations Research
Toward Global Optimization of Case-Based Reasoning Systems for Financial Forecasting

Applied Intelligence
A threshold-varying artificial neural network approach for classification and its application to bankruptcy prediction problem

Computers and Operations Research
A Data Envelopment Analysis-Based Approach for Data Preprocessing

IEEE Transactions on Knowledge and Data Engineering
Comparison of FCM, PCA and WT techniques for classification ECG arrhythmias using artificial neural network

Expert Systems with Applications: An International Journal
A process model to develop an internal rating system: sovereign credit ratings

Decision Support Systems
Bankruptcy forecasting: An empirical comparison of AdaBoost and neural networks

Decision Support Systems
Application of complex discrete wavelet transform in classification of Doppler signals using complex-valued artificial neural network

Artificial Intelligence in Medicine
Predicting bank financial failures using neural networks, support vector machines and multivariate statistical methods: A comparative analysis in the sample of savings deposit insurance fund (SDIF) transferred banks in Turkey

Expert Systems with Applications: An International Journal
Effects of feature construction on classification performance: An empirical study in bank failure prediction

Expert Systems with Applications: An International Journal
Combined neural networks for diagnosis of erythemato-squamous diseases

Expert Systems with Applications: An International Journal
Combined neural network model employing wavelet coefficients for EEG signals classification

Digital Signal Processing
Predicting bankruptcy using neural networks and other classification methods: The influence of variable selection techniques on model accuracy

Neurocomputing
Disaggregation & aggregation of time series components: A hybrid forecasting approach using generalized regression neural networks and the theta method

Neurocomputing
Predicting corporate bankruptcy using a self-organizing map: An empirical study to improve the forecasting horizon of a financial failure model

Decision Support Systems
A tuning method for the architecture of neural network models incorporating GAM and GA as applied to bankruptcy prediction

Expert Systems with Applications: An International Journal
Metafraud: a meta-learning framework for detecting financial fraud

MIS Quarterly

Quantified Score

Hi-index	0.01

Visualization

Abstract

Recent years have seen the growth in popularity of neural networks for business decision support because of their capabilities for modeling, estimating, and classifying. Compared to other AI methods for problem solving such as expert systems, neural network approaches are especially useful for their ability to learn adaptively from observations. However, neural network learning performed by algorithms such as back-propagation (BP) are known to be slow due to the size of the search space involved and also the iterative manner in which the algorithm works. In this paper, we show that the degree of difficulty in neural network learning is inherent in the given set of training examples. We propose a technique for measuring such learning difficulty, and then develop a feature construction methodology that helps transform the training data so that both the learning speed and classification accuracy of neural network algorithms are improved. We show the efficacy of the proposed method for financial risk classification, a domain characterized by frequent data noise, lack of functional structure, and high attribute interactions. Moreover, the empirical studies also provide insights into the structural characteristics of neural networks with respect to the input data used as well as possible mechanisms to improve the learning performance.