Web Navigation Prediction Using Multiple Evidence Combination and Domain Knowledge

Predicting users´ future requests in the World Wide Web can be applied effectively in many important applications, such as web search, latency reduction, and personalization systems. Such application has traditional tradeoffs between modeling complexity and prediction accuracy. In this paper, we study several hybrid models that combine different classification techniques, namely, Markov models, artificial neural networks (ANNs), and the All-Kth-Markov model, to resolve prediction using Dempster´s rule. Such fusion overcomes the inability of the Markov model in predicting beyond the training data, as well as boosts the accuracy of ANN, particularly, when dealing with a large number of classes. We also employ a reduction technique, which uses domain knowledge, to reduce the number of classifiers to improve the predictive accuracy and the prediction time of ANNs. We demonstrate the effectiveness of our hybrid models by comparing our results with widely used techniques, namely, the Markov model, the All-Kth-Markov model, and association rule mining, based on a benchmark data set.