%0 Conference Paper %1 Forman09featureShaping %A Forman, George %A Scholz, Martin %A Rajaram, Shyamsundar %B KDD '09: Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining %C New York, NY, USA %D 2009 %I ACM %K 09 Forman SVM classification feature selection shaping text %P 299--308 %R http://doi.acm.org/10.1145/1557019.1557057 %T Feature shaping for linear SVM classifiers %U http://portal.acm.org/citation.cfm?id=1557057&dl=ACM %X Linear classifiers have been shown to be effective for many discrimination tasks. Irrespective of the learning algorithm itself, the final classifier has a weight to multiply by each feature. This suggests that ideally each input feature should be linearly correlated with the target variable (or anti-correlated), whereas raw features may be highly non-linear. In this paper, we attempt to re-shape each input feature so that it is appropriate to use with a linear weight and to scale the different features in proportion to their predictive value. We demonstrate that this pre-processing is beneficial for linear SVM classifiers on a large benchmark of text classification tasks as well as UCI datasets. %@ 978-1-60558-495-9

@inproceedings{Forman09featureShaping, abstract = {Linear classifiers have been shown to be effective for many discrimination tasks. Irrespective of the learning algorithm itself, the final classifier has a weight to multiply by each feature. This suggests that ideally each input feature should be linearly correlated with the target variable (or anti-correlated), whereas raw features may be highly non-linear. In this paper, we attempt to re-shape each input feature so that it is appropriate to use with a linear weight and to scale the different features in proportion to their predictive value. We demonstrate that this pre-processing is beneficial for linear SVM classifiers on a large benchmark of text classification tasks as well as UCI datasets.}, added-at = {2010-01-14T17:55:54.000+0100}, address = {New York, NY, USA}, author = {Forman, George and Scholz, Martin and Rajaram, Shyamsundar}, biburl = {https://www.bibsonomy.org/bibtex/26eab469522a9f90fe40f3837b7a9cfd3/lee_peck}, booktitle = {KDD '09: Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining}, description = {Feature shaping for linear SVM classifiers}, doi = {http://doi.acm.org/10.1145/1557019.1557057}, interhash = {6be034bd1eca68dcfe9aef7e1be479b5}, intrahash = {6eab469522a9f90fe40f3837b7a9cfd3}, isbn = {978-1-60558-495-9}, keywords = {09 Forman SVM classification feature selection shaping text}, location = {Paris, France}, pages = {299--308}, publisher = {ACM}, timestamp = {2010-01-14T17:55:54.000+0100}, title = {Feature shaping for linear SVM classifiers}, url = {http://portal.acm.org/citation.cfm?id=1557057&dl=ACM}, year = 2009 }