Integrating classical and ART models for data mining

With a focus on classification problem, in this paper, we present an integrated approach to improve the performance of classification using adaptive resonance theory (ART) neural network and logistic regression classifiers. In our approach, the neural network classifier is trained first and then regression analysis is applied to each individual class. In testing phase, the data is applied to the regression classifier and, if any deviation exists, the neural network classifier is retrained. The study reveals that effective data mining can be achieved by combining the power of neural networks with the rigor of more traditional statistical tools.