Naïve bayes vs. support vector machine: resilience to missing data

Authors:
Hongbo Shi;Yaqin Liu
Affiliations:
School of Information Management, Shanxi University of Finance and Economics, Taiyuan, China;School of Information Management, Shanxi University of Finance and Economics, Taiyuan, China
Venue:
AICI'11 Proceedings of the Third international conference on Artificial intelligence and computational intelligence - Volume Part II
Year:
2011

Citing 7
Cited 0

Bayesian Network Classifiers

Machine Learning - Special issue on learning with probabilistic representations
Data mining: practical machine learning tools and techniques with Java implementations

Data mining: practical machine learning tools and techniques with Java implementations
Robust Bayes classifiers

Artificial Intelligence
The Problem of Missing Values in Decision Tree Grafting

AI '98 Selected papers from the 11th Australian Joint Conference on Artificial Intelligence on Advanced Topics in Artificial Intelligence
Handling missing values in support vector machine classifiers

Neural Networks - 2005 Special issue: IJCNN 2005
Fuzzy c-Means Classifier for Incomplete Data Sets with Outliers and Missing Values

CIMCA '05 Proceedings of the International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce Vol-2 (CIMCA-IAWTIC'06) - Volume 02
Pattern classification with missing data: a review

Neural Computing and Applications - Special Issue - KES2008

Quantified Score

Hi-index	0.00

Visualization

Abstract

The naïve Bayes and support vector machine are the typical generative and discriminative classification models respectively, which are two popular classification approaches. Few studies have been done comparing their resilience to missing data. This paper provides an experimental comparison of the naïve Bayes and support vector machine regarding the resilience to missing data on 24 UCI data sets. The experimental results show that when the missing rate is very small (e.g. 1%), the resilience of the naïve Bayes classifiers to missing data are approximately similar to that of support vector machine classifiers. With the increase of the missing rate, however, the resilience of the naïve Bayes classifiers to missing data are slowly decreased and that of support vector machine classifiers to missing data are rapidly decreased. This demonstrates that the naïve Bayes classifiers have better resilience to missing data than support vector machine classifiers.