@misc{Kubus_Mariusz_Evaluation_2020,
 author={Kubus, Mariusz},
 identifier={DOI: 10.15611/eada.2020.1.04},
 year={2020},
 rights={Pewne prawa zastrzeżone na rzecz Autorów i Wydawcy},
 publisher={Wydawnictwo Uniwersytetu Ekonomicznego we Wrocławiu},
 description={Econometrics = Ekonometria, 2020, Vol. 24, No. 1, s. 39-50},
 language={eng},
 abstract={The purpose of many real world applications is the prediction of rare events, and the training sets are then highly unbalanced. In this case, the classifiers are biased towards the correct prediction of the majority class and they misclassify a minority class, whereas rare events are of the greater interest. To handle this problem, numerous techniques were proposed that balance the data or modify the learning algorithms. The goal of this paper is a comparison of simple random balancing methods with more sophisticated resampling methods that appeared in the literature and are available in R program. Additionally, the authors ask whether learning on the original dataset and using a shifted threshold for classification is not more competitive. The authors provide a survey from the perspective of regularized logistic regression and random forests. The results show that combining random under-sampling with random forests has an advantage over other techniques while logistic regression can be competitive in the case of highly unbalanced data},
 title={Evaluation of resampling methods in the class unbalance problem},
 type={artykuł},
 keywords={class unbalance, resampling, regularized logistic regression, random forests, klasy niezbilansowane, repróbkowanie, regularyzowana regresja logistyczna, lasy losowe},
}