Abstract
Imbalanced domains are an important problem frequently arising in real world predictive analytics. A significant body of research has addressed imbalanced distributions in classification tasks, where the target variable is nominal. In the context of regression tasks, where the target variable is continuous, imbalanced distributions of the target variable also raise several challenges to learning algorithms. Imbalanced domains are characterized by: (1) a higher relevance being assigned to the performance on a subset of the target variable values; and (2) these most relevant values being underrepresented on the available data set. Recently, some proposals were made to address the problem of imbalanced distributions in regression. Still, this remains a scarcely explored issue with few existing solutions. This paper describes three new approaches for tackling the problem of imbalanced distributions in regression tasks. We propose the adaptation to regression tasks of random over-sampling and introduction of Gaussian Noise, and we present a new method called WEighted Relevance-based Combination Strategy (WERCS). An extensive set of experiments provides empirical evidence of the advantage of using the proposed strategies and, in particular, the WERCS method. We analyze the impact of different data characteristics in the performance of the methods. A data repository with 15 imbalanced regression data sets is also provided to the research community.

Abstract

Abstract

Abstract

Abstract
Interval time series occur when real intervals of some variable of interest are registered as an ordered sequence along time. We address the problem of clustering interval time series (ITS), for which different approaches are proposed. First, clustering is performed based on point-to-point comparisons. Time-domain and wavelet features also serve as clustering variables in alternative approaches. Furthermore, autocorrelation matrix functions, gathering the autocorrelation and cross-correlation functions of the ITS upper and lower bounds, may be compared using adequate distances (e.g. the Frobenius distance) and used for clustering ITS. An improved procedure to determine the autocorrelation function of ITS is proposed, which also serves as a basis for clustering. The different alternative approaches are explored and their performances compared for ITS simulated under different setups. An application to sea level daily ranges, observed at different locations in Australia, illustrates the proposed methods.

Abstract
While the predictive advantage of ensemble methods is nowadays widely accepted, the most appropriate way of estimating the weights of each individual model remains an open research question. Meanwhile, several studies report that combining different ensemble approaches leads to improvements in performance, due to a better trade-off between the diversity and the error of the individual models in the ensemble. We contribute to this research line by proposing an aggregation framework for a set of independently created forecasting models, i.e. heterogeneous ensembles. The general idea is to, instead of directly aggregating these models, first rearrange them into different subsets, creating a new set of combined models which is then aggregated into a final decision. We present this idea as constructive aggregation, and apply it to time series forecasting problems. Results from empirical experiments show that applying constructive aggregation to state of the art dynamic aggregation methods provides a consistent advantage. Constructive aggregation is publicly available in a software package. Data related to this paper are available at: https://github.com/vcerqueira/timeseriesdata. Code related to this paper is available at: https://github. com/vcerqueira/tsensembler.