*Information Technology Department, Institute of Information Technology & Management, New Delhi, India
**Department of Computer Applications, Samrat Ashok Technological Institute, Vidisha, Madhya Pradesh, India
Online published on 21 November, 2013.
Bayesian classifier has gained wide popularity as a probability-based classification method despite its assumption that attributes are conditionally mutually independent given the class label. This paper makes a study into various algorithms to improve the classification accuracy of Bayesian methods with respect to real estate datasets. We have applied Bayesian methods on two variations of data sets in three different test modes. In the first instance we have taken complete data sets, our experimental results suggest that, Bayesian network Classifier seems to be the best performer compared to popular variants of Bayesian classifiers. In second instance we have applied the same techniques on selected attribute i.e. after removing demographic details of customers and and found that there is a drastic change in the results of various Bayesian techniques except Complement Naive Bayes which is giving near about same accuracy and error rate in both variations i.e. it is unaffected with the attribute sets.
Classification, Naïve bayes, Bayesian Network, Complement Naïve Bayes
