Abstract

Abstract

Abstract
Planning strategies play an important role in companies' management. In the decision-making process, one of the main important goals is sales forecasting. They are important for stocks planing, shop space maintenance, promotions, etc. Sales forecasting use historical data to make reliable projections for the future. In the retail sector, data has a hierarchical structure. Products are organized in hierarchical groups that reflect the business structure. In this work we present a case study, using real data, from a Portuguese leader retail company. We experimentally evaluate standard approaches for sales forecasting and compare against models that explore the hierarchical structure of the products. Moreover, we evaluate different methods to combine predictions for the different hierarchical levels. The results show that exploiting the hierarchical structure present in the data systematically reduces the error of the forecasts.

Abstract

Abstract
Several real world prediction problems involve forecasting rare values of a target variable. When this variable is nominal, we have a problem of class imbalance that was thoroughly studied within machine learning. For regression tasks, where the target variable is continuous, few works exist addressing this type of problem. Still, important applications involve forecasting rare extreme values of a continuous target variable. This paper describes a contribution to this type of tasks. Namely, we propose to address such tasks by resampling approaches that change the distribution of the given data set to decrease the problem of imbalance between the rare target cases and the most frequent ones. We present two modifications of well-known resampling strategies for classification tasks: the under-sampling and the synthetic minority over-sampling technique (SMOTE) methods. These modifications allow the use of these strategies on regression tasks where the goal is to forecast rare extreme values of the target variable. In an extensive set of experiments, we provide empirical evidence for the superiority of our proposals for these particular regression tasks. The proposed resampling methods can be used with any existing regression algorithm, which means that they are general tools for addressing problems of forecasting rare extreme values of a continuous target variable.

Abstract
We consider interval-valued time series, that is, series resulting from collecting real intervals as an ordered sequence through time. Since the lower and upper bounds of the observed intervals at each time point are in fact values of the same variable, they are naturally related. We propose modeling interval time series with space-time autoregressive models and, based on the process appropriate for the interval bounds, we derive the model for the intervals' center and radius. A simulation study and an application with data of daily wind speed at different meteorological stations in Ireland illustrate that the proposed approach is appropriate and useful.