The effect of attribute scaling on the performance of support vector machines

Authors:
Catherine Edwards;Bhavani Raskutti
Affiliations:
Telstra Research Laboratories, Telstra Corporation, Clayton, Victoria, Australia;Telstra Research Laboratories, Telstra Corporation, Clayton, Victoria, Australia
Venue:
AI'04 Proceedings of the 17th Australian joint conference on Advances in Artificial Intelligence
Year:
2004

Citing 8
Cited 1

Regularization theory and neural networks architectures

Neural Computation
Support-Vector Networks

Machine Learning
Data preparation for data mining

Data preparation for data mining
An introduction to support Vector Machines: and other kernel-based learning methods

An introduction to support Vector Machines: and other kernel-based learning methods
A Simple Generalisation of the Area Under the ROC Curve for Multiple Class Classification Problems

Machine Learning
Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond

Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond
Data Mining Techniques: For Marketing, Sales, and Customer Support

Data Mining Techniques: For Marketing, Sales, and Customer Support
The use of the area under the ROC curve in the evaluation of machine learning algorithms

Pattern Recognition

Effective recognition of control chart patterns in autocorrelated data using a support vector machine based approach

Computers and Industrial Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents some empirical results showing that simple attribute scaling in the data preprocessing stage can improve the performance of linear binary classifiers In particular, a class specific scaling method that utilises information about the class distribution of the training sample can significantly improve classification accuracy This form of scaling can boost the performance of a simple centroid classifier to similar levels of accuracy as the more complex, and computationally expensive, support vector machine and regression classifiers Further, when SVMs are used, scaled data produces better results, for smaller amounts of training data, and with smaller regularisation constant values, than unscaled data.