2017
Authors
Mani, V; Delgado, C; Hazen, BT; Patel, P;
Publication
SUSTAINABILITY
Abstract
The use of big data analytics for forecasting business trends is gaining momentum among professionals. At the same time, supply chain risk management is important for practitioners to consider because it outlines ways through which firms can allay internal and external threats. Predicting and addressing the risks that social issues cause in the supply chain is of paramount importance to the sustainable enterprise. The aim of this research is to explore the application of big data analytics in mitigating supply chain social risk and to demonstrate how such mitigation can help in achieving environmental, economic, and social sustainability. The method involves an expert panel and survey identifying and validating social issues in the supply chain. A case study was used to illustrate the application of big data analytics in identifying and mitigating social issues in the supply chain. Our results show that companies can predict various social problems including workforce safety, fuel consumptions monitoring, workforce health, security, physical condition of vehicles, unethical behavior, theft, speeding and traffic violations through big data analytics, thereby demonstrating how information management actions can mitigate social risks. This paper contributes to the literature by integrating big data analytics with sustainability to explain how to mitigate supply chain risk.
2017
Authors
Rocha, C; Mendonca, T; Silva, ME; Gambus, P;
Publication
JOURNAL OF CLINICAL MONITORING AND COMPUTING
Abstract
2017
Authors
Cerqueira, V; Torgo, L; Oliveira, M; Pfahringer, B;
Publication
2017 IEEE INTERNATIONAL CONFERENCE ON DATA SCIENCE AND ADVANCED ANALYTICS (DSAA)
Abstract
This paper addresses the issue of learning time series forecasting models in changing environments by leveraging the predictive power of ensemble methods. Concept drift adaptation is performed in an active manner, by dynamically combining base learners according to their recent performance using a non-linear function. Diversity in the ensembles is encouraged with several strategies that include heterogeneity among learners, sampling techniques and computation of summary statistics as extra predictors. Heterogeneity is used with the goal of better coping with different dynamic regimes of the time series. The driving hypotheses of this work are that (i) heterogeneous ensembles should better fit different dynamic regimes and (ii) dynamic aggregation should allow for fast detection and adaptation to regime changes. We extend some strategies typically used in classification tasks to time series forecasting. The proposed methods are validated using Monte Carlo simulations on 16 real-world univariate time series with numerical outcome as well as an artificial series with clear regime shifts. The results provide strong empirical evidence for our hypotheses. To encourage reproducibility the proposed method is publicly available as a software package.
2017
Authors
Cerqueira, V; Torgo, L; Smailovic, J; Mozetic, I;
Publication
2017 IEEE INTERNATIONAL CONFERENCE ON DATA SCIENCE AND ADVANCED ANALYTICS (DSAA)
Abstract
Performance estimation denotes a task of estimating the loss that a predictive model will incur on unseen data. These procedures are part of the pipeline in every machine learning task and are used for assessing the overall generalisation ability of models. In this paper we address the application of these methods to time series forecasting tasks. For independent and identically distributed data the most common approach is cross-validation. However, the dependency among observations in time series raises some caveats about the most appropriate way to estimate performance in these datasets and currently there is no settled way to do so. We compare different variants of cross-validation and different variants of out-of-sample approaches using two case studies: One with 53 real-world time series and another with three synthetic time series. Results show noticeable differences in the performance estimation methods in the two scenarios. In particular, empirical experiments suggest that cross-validation approaches can be applied to stationary synthetic time series. However, in real-world scenarios the most accurate estimates are produced by the out-of-sample methods, which preserve the temporal order of observations.
2017
Authors
Rocha, A; Silva, A; Cardoso, M; Beirao, I; Alves, C; Teles, P; Coelho, T; Lobato, L;
Publication
AMYLOID-JOURNAL OF PROTEIN FOLDING DISORDERS
Abstract
2017
Authors
Teles, P; Sousa, PSA;
Publication
COMMUNICATIONS IN STATISTICS-SIMULATION AND COMPUTATION
Abstract
In time series analysis, Autoregressive Moving Average (ARMA) models play a central role. Because of the importance of parameter estimation in ARMA modeling and since it is based on aggregate time series so often, we analyze the effect of temporal aggregation on estimation accuracy. We derive the relationships between the aggregate and the basic parameters and compute the actual values of the former from those of the latter in order to measure and compare their estimation accuracy. We run a simulation experiment that shows that aggregation seriously worsens estimation accuracy and that the impact increases with the order of aggregation.
The access to the final selection minute is only available to applicants.
Please check the confirmation e-mail of your application to obtain the access code.