Cross-validation pitfalls when selecting and assessing regression and classification models. Krstajic, D., Buturovic, L. J., Leahy, D. E., & Thomas, S. Journal of Cheminformatics, 6(1):10, March, 2014. ![Cross-validation pitfalls when selecting and assessing regression and classification models [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex We address the problem of selecting and assessing classification and regression models using cross-validation. Current state-of-the-art methods can yield models with high variance, rendering them unsuitable for a number of practical applications including QSAR. In this paper we describe and evaluate best practices which improve reliability and increase confidence in selected models. A key operational component of the proposed methods is cloud computing which enables routine use of previously infeasible approaches.
@article{krstajic_cross-validation_2014,
title = {Cross-validation pitfalls when selecting and assessing regression and classification models},
volume = {6},
issn = {1758-2946},
url = {https://doi.org/10.1186/1758-2946-6-10},
doi = {10.1186/1758-2946-6-10},
abstract = {We address the problem of selecting and assessing classification and regression models using cross-validation. Current state-of-the-art methods can yield models with high variance, rendering them unsuitable for a number of practical applications including QSAR. In this paper we describe and evaluate best practices which improve reliability and increase confidence in selected models. A key operational component of the proposed methods is cloud computing which enables routine use of previously infeasible approaches.},
number = {1},
journal = {Journal of Cheminformatics},
author = {Krstajic, Damjan and Buturovic, Ljubomir J. and Leahy, David E. and Thomas, Simon},
month = mar,
year = {2014},
pages = {10},
}
Downloads: 0
{"_id":"9vkzBLig56PoAKmyq","bibbaseid":"krstajic-buturovic-leahy-thomas-crossvalidationpitfallswhenselectingandassessingregressionandclassificationmodels-2014","author_short":["Krstajic, D.","Buturovic, L. J.","Leahy, D. E.","Thomas, S."],"bibdata":{"bibtype":"article","type":"article","title":"Cross-validation pitfalls when selecting and assessing regression and classification models","volume":"6","issn":"1758-2946","url":"https://doi.org/10.1186/1758-2946-6-10","doi":"10.1186/1758-2946-6-10","abstract":"We address the problem of selecting and assessing classification and regression models using cross-validation. Current state-of-the-art methods can yield models with high variance, rendering them unsuitable for a number of practical applications including QSAR. In this paper we describe and evaluate best practices which improve reliability and increase confidence in selected models. A key operational component of the proposed methods is cloud computing which enables routine use of previously infeasible approaches.","number":"1","journal":"Journal of Cheminformatics","author":[{"propositions":[],"lastnames":["Krstajic"],"firstnames":["Damjan"],"suffixes":[]},{"propositions":[],"lastnames":["Buturovic"],"firstnames":["Ljubomir","J."],"suffixes":[]},{"propositions":[],"lastnames":["Leahy"],"firstnames":["David","E."],"suffixes":[]},{"propositions":[],"lastnames":["Thomas"],"firstnames":["Simon"],"suffixes":[]}],"month":"March","year":"2014","pages":"10","bibtex":"@article{krstajic_cross-validation_2014,\n\ttitle = {Cross-validation pitfalls when selecting and assessing regression and classification models},\n\tvolume = {6},\n\tissn = {1758-2946},\n\turl = {https://doi.org/10.1186/1758-2946-6-10},\n\tdoi = {10.1186/1758-2946-6-10},\n\tabstract = {We address the problem of selecting and assessing classification and regression models using cross-validation. Current state-of-the-art methods can yield models with high variance, rendering them unsuitable for a number of practical applications including QSAR. In this paper we describe and evaluate best practices which improve reliability and increase confidence in selected models. A key operational component of the proposed methods is cloud computing which enables routine use of previously infeasible approaches.},\n\tnumber = {1},\n\tjournal = {Journal of Cheminformatics},\n\tauthor = {Krstajic, Damjan and Buturovic, Ljubomir J. and Leahy, David E. and Thomas, Simon},\n\tmonth = mar,\n\tyear = {2014},\n\tpages = {10},\n}\n\n","author_short":["Krstajic, D.","Buturovic, L. J.","Leahy, D. E.","Thomas, S."],"key":"krstajic_cross-validation_2014","id":"krstajic_cross-validation_2014","bibbaseid":"krstajic-buturovic-leahy-thomas-crossvalidationpitfallswhenselectingandassessingregressionandclassificationmodels-2014","role":"author","urls":{"Paper":"https://doi.org/10.1186/1758-2946-6-10"},"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/kjelljorner","dataSources":["64RFiGdCa5JLg5kLH"],"keywords":[],"search_terms":["cross","validation","pitfalls","selecting","assessing","regression","classification","models","krstajic","buturovic","leahy","thomas"],"title":"Cross-validation pitfalls when selecting and assessing regression and classification models","year":2014}