@article {787, title = {Similarity-based and Iterative Label Noise Filters for Monotonic Classification}, journal = {Proceedings of the 53rd Hawaii International Conference on System Sciences}, year = {2020}, note = {TIN2017-89517-P; TEC2015-69496-R; BigDaP-TOOLS - Ayudas Fundaci{\'o}n BBVA a Equipos de Investigaci{\'o}n Cient{\'\i}fica 2016}, pages = {1698-1706}, abstract = {Monotonic ordinal classification has received an increasing interest in the latest years. Building monotone models from these problems usually requires datasets that verify monotonic relationships among the samples. When the monotonic relationships are not met, changing the labels may be a viable option, but the risk is high: wrong label changes would completely change the information contained in the data. In this work, we tackle the construction of monotone datasets by removing the wrong or noisy examples that violate monotonicity restrictions. We propose two monotonic noise filtering algorithms to preprocess the ordinal datasets and improve the monotonic relations between instances. The experiments are carried out over eleven ordinal datasets, showing that the application of the proposed filters improve the prediction capabilities over different levels of noise.}, keywords = {Monotonic classification, noise, noise filter, Ordinal classification, Soft Computing: Theory Innovations and Problem Solving Benefits}, doi = {https://doi.org/10.24251/HICSS.2020.210}, author = {J. R. Cano and Luengo, Juli{\'a}n and Garc{\'\i}a, Salvador} } @article {CANO2019, title = {Label noise filtering techniques to improve monotonic classification}, journal = {Neurocomputing}, volume = {353}, year = {2019}, note = {TIN2014-57251-P; TIN2017-89517-P; TEC2015-69496-R; BigDaP-TOOLS}, month = {08/2019}, pages = {83-95}, abstract = {The monotonic ordinal classification has increased the interest of researchers and practitioners within machine learning community in the last years. In real applications, the problems with monotonicity constraints are very frequent. To construct predictive monotone models from those problems, many classifiers require as input a data set satisfying the monotonicity relationships among all samples. Changing the class labels of the data set (relabeling) is useful for this. Relabeling is assumed to be an important building block for the construction of monotone classifiers and it is proved that it can improve the predictive performance. In this paper, we will address the construction of monotone datasets considering as noise the cases that do not meet the monotonicity restrictions. For the first time in the specialized literature, we propose the use of noise filtering algorithms in a preprocessing stage with a double goal: to increase both the monotonicity index of the models and the accuracy of the predictions for different monotonic classifiers. The experiments are performed over 12 datasets coming from classification and regression problems and show that our scheme improves the prediction capabilities of the monotonic classifiers instead of being applied to original and relabeled datasets. In addition, we have included the analysis of noise filtering process in the particular case of wine quality classification to understand its effect in the predictive models generated.}, keywords = {Monotonic classification, Noise filtering, Ordinal classification, Preprocessing}, issn = {0925-2312}, doi = {https://doi.org/10.1016/j.neucom.2018.05.131}, url = {http://www.sciencedirect.com/science/article/pii/S092523121930325X}, author = {J. R. Cano and J. Luengo and S. Garc{\'\i}a} } @article {785, title = {Monotonic classification: An overview on algorithms, performance measures and data sets}, journal = {Neurocomputing}, volume = {341}, year = {2019}, note = {TIN2017-89517-P; TIN2015-70308-REDT; TIN2014-54583-C2-1-R; TEC2015-69496-R}, month = {05/2019}, pages = {168-182}, abstract = {Currently, knowledge discovery in databases is an essential first step when identifying valid, novel and useful patterns for decision making. There are many real-world scenarios, such as bankruptcy prediction, option pricing or medical diagnosis, where the classification models to be learned need to fulfill restrictions of monotonicity (i.e. the target class label should not decrease when input attributes values increase). For instance, it is rational to assume that a higher debt ratio of a company should never result in a lower level of bankruptcy risk. Consequently, there is a growing interest from the data mining research community concerning monotonic predictive models. This paper aims to present an overview of the literature in the field, analyzing existing techniques and proposing a taxonomy of the algorithms based on the type of model generated. For each method, we review the quality metrics considered in the evaluation and the different data sets and monotonic problems used in the analysis. In this way, this paper serves as an overview of monotonic classification research in specialized literature and can be used as a functional guide for the field.}, keywords = {Monotonic classification, Monotonic data sets, Ordinal classification, Software Performance metrics, Taxonomy}, doi = {https://doi.org/10.1016/j.neucom.2019.02.024}, author = {J. R. Cano and Pedro Antonio Guti{\'e}rrez and Bartosz Krawczyk and Michat Wo{\'z}niak and Garc{\'\i}a, Salvador} } @article {CANO201794, title = {Training set selection for monotonic ordinal classification}, journal = {Data \& Knowledge Engineering}, volume = {112}, year = {2017}, pages = {94 - 105}, abstract = {In recent years, monotonic ordinal classification has increased the focus of attention for machine learning community. Real life problems frequently have monotonicity constraints. Many of the monotonic classifiers require that the input data sets satisfy the monotonicity relationships between its samples. To address this, a conventional strategy consists of relabeling the input data to achieve complete monotonicity. As an alternative, we explore the use of preprocessing algorithms without modifying the class label of the input data. In this paper we propose the use of training set selection to choose the most effective instances which lead the monotonic classifiers to obtain more accurate and efficient models, fulfilling the monotonic constraints. To show the benefits of our proposed training set selection algorithm, called MonTSS, we carry out an experimentation over 30 data sets related to ordinal classification problems.}, keywords = {Data preprocessing, machine learning, Monotonic classification, Ordinal classification, Training set selection}, issn = {0169-023X}, doi = {https://doi.org/10.1016/j.datak.2017.10.003}, url = {http://www.sciencedirect.com/science/article/pii/S0169023X16303585}, author = {J. R. Cano and S. Garc{\'\i}a} }