Abstract
We describe GPU implementations of the matrix recommender algorithms CCD++ and ALS. We compare the processing time and predictive ability of the GPU implementations with existing multi- core versions of the same algorithms. Results on the GPU are better than the results of the multi- core versions (maximum speedup of 14.8).

Abstract
Temporal information retrieval has been a topic of great interest in recent years. Its purpose is to improve the effectiveness of information retrieval methods by exploiting temporal information in documents and queries. In this article, we present a survey of the existing literature on temporal information retrieval. In addition to giving an overview of the field, we categorize the relevant research, describe the main contributions, and compare different approaches. We organize existing research to provide a coherent view, discuss several open issues, and point out some possible future research directions in this area. Despite significant advances, the area lacks a systematic arrangement of prior efforts and an overview of state-of-the-art approaches. Moreover, an effective end-to-end temporal retrieval system that exploits temporal information to improve the quality of the presented results remains undeveloped.

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.