docs/refs.bib
@inproceedings{sklearn_api,
author = {Lars Buitinck and Gilles Louppe and Mathieu Blondel and
Fabian Pedregosa and Andreas Mueller and Olivier Grisel and
Vlad Niculae and Peter Prettenhofer and Alexandre Gramfort
and Jaques Grobler and Robert Layton and Jake VanderPlas and
Arnaud Joly and Brian Holt and Ga{\"{e}}l Varoquaux},
title = {{API} design for machine learning software: experiences from the scikit-learn
project},
booktitle = {ECML PKDD Workshop: Languages for Data Mining and Machine Learning},
year = {2013},
pages = {108--122},
}
@article{scikit-learn,
title={Scikit-learn: Machine Learning in {P}ython},
author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
journal={Journal of Machine Learning Research},
volume={12},
pages={2825--2830},
year={2011}
}
@article{slakey,
author = {Austin Slakey and
Daniel Salas and
Yoni Schamroth},
title = {Encoding Categorical Variables with Conjugate Bayesian Models for
WeWork Lead Scoring Engine},
journal = {CoRR},
volume = {abs/1904.13001},
year = {2019},
url = {http://arxiv.org/abs/1904.13001},
eprinttype = {arXiv},
eprint = {1904.13001},
timestamp = {Thu, 02 May 2019 15:13:44 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1904-13001.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{larionov,
author = {Michael Larionov},
title = {Sampling Techniques in Bayesian Target Encoding},
journal = {CoRR},
volume = {abs/2006.01317},
year = {2020},
url = {https://arxiv.org/abs/2006.01317},
eprinttype = {arXiv},
eprint = {2006.01317},
timestamp = {Sat, 23 Jan 2021 01:11:28 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-01317.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@misc{pargent,
title={Regularized target encoding outperforms traditional methods in supervised machine learning with high cardinality features},
author={Florian Pargent and Florian Pfisterer and Janek Thomas and Bernd Bischl},
year={2021},
eprint={2104.00629},
archivePrefix={arXiv},
primaryClass={stat.ML}
}
@article{lightgbm,
title={Lightgbm: A highly efficient gradient boosting decision tree},
author={Ke, Guolin and Meng, Qi and Finley, Thomas and Wang, Taifeng and Chen, Wei and Ma, Weidong and Ye, Qiwei and Liu, Tie-Yan},
journal={Advances in neural information processing systems},
volume={30},
pages={3146--3154},
year={2017}
}
@inproceedings{xgboost,
author = {Chen, Tianqi and Guestrin, Carlos},
title = {{XGBoost}: A Scalable Tree Boosting System},
booktitle = {Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
series = {KDD '16},
year = {2016},
isbn = {978-1-4503-4232-2},
location = {San Francisco, California, USA},
pages = {785--794},
numpages = {10},
url = {http://doi.acm.org/10.1145/2939672.2939785},
doi = {10.1145/2939672.2939785},
acmid = {2939785},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {large-scale machine learning},
}