n Improved Aggregated One-Dependence Estimator:On Not So Rigid Cross Validation

1The naive Bayesian classifier is a simple and effective approach to classifier learning. However, its conditionally independent assumption doesn’t often hold in the real world and this will lead to accuracy decrease in some applications. LBR, TAN and AODE are several representative algorithms that seek to relax this assumption and have exhibited noticeable prediction performance. However, the computational cost of LBR and TAN is considerable. AODE is creditably an effective classification learning algorithm without increasing computational cost improperly. However, to intently debase computational complexity, AODE avoids model selection and adopts all SPODEs , this may result in insufficiency to improve the prediction accuracy because of the included SPODEs which bring negative effect. Therefore, we propose an improved algorithm in this paper which will improve classification accuracy and classification speed by filtering out those SPODEs which bring negative effect base on original algorithms.