Support Vector Machines for Differential Prediction
Abstract
Machine learning is continually being applied to a growing set of fields, including the social sciences, business, and medicine. Some fields present problems that are not easily addressed using standard machine learning approaches and, in particular, there is growing interest in differential prediction . In this type of task we are interested in producing a classifier that specifically characterizes a subgroup of interest by maximizing the difference in predictive performance for some outcome between subgroups in a population. We discuss adapting maximum margin classifiers for differential prediction. We first introduce multiple approaches that do not affect the key properties of maximum margin classifiers, but which also do not directly attempt to optimize a standard measure of differential prediction. We next propose a model that directly optimizes a standard measure in this field, the uplift measure. We evaluate our models on real data from two medical applications and show excellent results.
Cite
Text
Kuusisto et al. "Support Vector Machines for Differential Prediction." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2014. doi:10.1007/978-3-662-44851-9_4Markdown
[Kuusisto et al. "Support Vector Machines for Differential Prediction." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2014.](https://mlanthology.org/ecmlpkdd/2014/kuusisto2014ecmlpkdd-support/) doi:10.1007/978-3-662-44851-9_4BibTeX
@inproceedings{kuusisto2014ecmlpkdd-support,
title = {{Support Vector Machines for Differential Prediction}},
author = {Kuusisto, Finn and Costa, Vítor Santos and Nassif, Houssam and Burnside, Elizabeth S. and Page, David and Shavlik, Jude W.},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2014},
pages = {50-65},
doi = {10.1007/978-3-662-44851-9_4},
url = {https://mlanthology.org/ecmlpkdd/2014/kuusisto2014ecmlpkdd-support/}
}