A STATISTICAL COMPARISON OF LOGISTIC REGRESSION AND DIFFERENT BAYES CLASSIFICATION METHODS FOR MACHINE LEARNING

Recent Machine Learning algorithms are widely available for various purposes. But which classifier is suitable for particular data is not yet defined. To consider this into account, well known classifiers Logistics Regression and Bayesian Classifier is taken to validate the work. To validate this, consider some factor such as Asymptotic error (i.e Normally Naive Bayes reaches its asymptotic error very quickly with regards to the number of training samples), how performance takes place when we increase the data set size etc.. Here we discuss how various bayes classifiers like Bayes Network, Naive Bayes, Naïve Bayes Multinomial Text, and Naïve Bayes Updateable are working and how they differ with each other based on given data and these results are effectively compared with Logistics Regression. Moreover, proposed work is compared using Naïve Bayes and Logistic Regression by using some standard dataset results as input. Finally it shows how the Bayes classifier methods and Logistic Regression differs each other in terms of performance factor. Keyword: classification, logistic regression, Bayes classifier, projection.

[1]  Andrea Esuli,et al.  Evaluation Measures for Ordinal Regression , 2009, 2009 Ninth International Conference on Intelligent Systems Design and Applications.

[2]  David Madigan,et al.  Constructing informative prior distributions from domain knowledge in text classification , 2006, SIGIR.

[3]  John Halloran.  Classification: Naive Bayes vs Logistic Regression , 2009 .

[4]  B. Parvathavarthini,et al.  Integrating rough clustering with Fuzzy sets , 2011 .

[5]  Guy N. Brock,et al.  Classification of clinical outcomes using high-throughput informatics: Part 1 - nonparametric method reviews , 2015, Model. Assist. Stat. Appl..

[6]  L. Mary Gladence,et al.  An enhanced method for detecting congestive heart failure - Automatic Classifier , 2014, 2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies.

[7]  Heart Disease Prediction using Naive Bayes Classification in Data Mining , 2014 .

[8]  Bevish Jinila,et al.  Cluster Oriented ID Based Multi-signature Scheme for Traffic Congestion Warning in Vehicular Ad Hoc Networks , 2015 .

[9]  Yiming Yang,et al.  Recovering genetic regulatory networks from micro-array data and location analysis data. , 2004, Genome informatics. International Conference on Genome Informatics.

[10]  Leonard E. Trigg,et al.  Technical Note: Naive Bayes for Regression , 2000, Machine Learning.

[11]  James O. Berger,et al.  Bayesian and Frequentist Approaches to Parametric Predictive Inference , 1999 .

[12]  David Madigan,et al.  Large-Scale Bayesian Logistic Regression for Text Categorization , 2007, Technometrics.

[13]  Dmitriy Fradkin,et al.  Bayesian Multinomial Logistic Regression for Author Identification , 2005, AIP Conference Proceedings.

[14]  Michael I. Jordan,et al.  On Discriminative vs. Generative Classifiers: A comparison of logistic regression and naive Bayes , 2001, NIPS.

[15]  D. Madigan,et al.  The role of data mining in pharmacovigilance , 2005, Expert opinion on drug safety.