Interval Estimation Na¨ ive Bayes

Recent work in supervised learning has shown that a sur- prisingly simple Bayesian classifier called na¨ ive Bayes is competitive with state of the art classifiers. This simple approach stands from assumptions of conditional independence among features given the class. In this pa- per a new na¨ ive Bayes classifier called Interval Estimation na¨ ive Bayes is proposed. Interval Estimation na¨ ive Bayes is performed in two phases. First, an interval estimation of each probability necessary to specify the na¨ ive Bayes is calculated. On the second phase the best combination of values inside these intervals is calculated using a heuristic search that is guided by the accuracy of the classifiers. The founded values in the search are the new parameters for the na¨ ive Bayes classifier. Our new approach has shown to be quite competitive related to simple na¨ ive Bayes. Exper- imental tests have been done with 21 data sets from the UCI repository.

[1]  Geoffrey I. Webb,et al.  Adjusted Probability Naive Bayesian Induction , 1998, Australian Joint Conference on Artificial Intelligence.

[2]  Ron Kohavi,et al.  Improving simple Bayes , 1997 .

[3]  Ron Kohavi,et al.  Supervised and Unsupervised Discretization of Continuous Features , 1995, ICML.

[4]  Marco Zaffalon,et al.  Credal Classification for Dementia Screening , 2001, AIME.

[5]  D G T Denison,et al.  Weighted naive Bayes modelling for data miningJ , 2001 .

[6]  Paola Sebastiani,et al.  c ○ 2001 Kluwer Academic Publishers. Manufactured in The Netherlands. Robust Learning with Missing Data , 2022 .

[7]  Pedro Larrañaga,et al.  Estimation of Distribution Algorithms , 2002, Genetic Algorithms and Evolutionary Computation.

[8]  Nir Friedman,et al.  Bayesian Network Classifiers , 1997, Machine Learning.

[9]  D. Hand,et al.  Idiot's Bayes—Not So Stupid After All? , 2001 .

[10]  Ron Kohavi,et al.  Scaling Up the Accuracy of Naive-Bayes Classifiers: A Decision-Tree Hybrid , 1996, KDD.

[11]  Marco Zaffalon.  A Credal Approach to Naive Classification , 1999, ISIPTA.

[12]  Irving John Good,et al.  The Estimation of Probabilities: An Essay on Modern Bayesian Methods , 1965 .

[13]  Catherine Blake,et al.  UCI Repository of machine learning databases , 1998 .

[14]  Pat Langley,et al.  Induction of Recursive Bayesian Classifiers , 1993, ECML.

[15]  João Gama,et al.  Iterative Bayes , 2000, Intell. Data Anal..

[16]  Ron Kohavi,et al.  MLC++: a machine learning library in C++ , 1994, Proceedings Sixth International Conference on Tools with Artificial Intelligence. TAI 94.

[17]  Michael J. Pazzani,et al.  Searching for Dependencies in Bayesian Classifiers , 1995, AISTATS.

[18]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[19]  Usama M. Fayyad,et al.  Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning , 1993, IJCAI.

[20]  Russell GreinerDepartment.  Learning Accurate Belief Nets , 1999 .

[21]  Pat Langley,et al.  Induction of Selective Bayesian Classifiers , 1994, UAI.

[22]  Igor Kononenko,et al.  Semi-Naive Bayesian Classifier , 1991, EWSL.

[23]  Nils J. Nilsson,et al.  MLC++, A Machine Learning Library in C++. , 1995 .

[24]  Kai Ming Ting,et al.  Discretization of Continuous-Valued Attributes and Instance-Based Learning , 1994 .

[25]  Heinz Mühlenbein,et al.  The Equation for Response to Selection and Its Use for Prediction , 1997, Evolutionary Computation.

[26]  Pedro M. Domingos,et al.  Beyond Independence: Conditions for the Optimality of the Simple Bayesian Classifier , 1996, ICML.

[27]  J. A. Lozano,et al.  Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation , 2001 .