Batch and incremental dynamic factor machine learning for multivariate and multi-step-ahead forecasting
| العنوان: | Batch and incremental dynamic factor machine learning for multivariate and multi-step-ahead forecasting |
|---|---|
| المؤلفون: | Olivier Caelen, Jacopo De Stefani, Dalila Hattab, Yann-Aël Le Borgne, Gianluca Bontempi |
| المصدر: | International Journal of Data Science and Analytics. 7:311-329 |
| بيانات النشر: | Springer Science and Business Media LLC, 2018. |
| سنة النشر: | 2018 |
| مصطلحات موضوعية: | 0301 basic medicine, Multivariate statistics, Series (mathematics), Computer science, business.industry, Applied Mathematics, Big data, Machine learning, computer.software_genre, Computer Science Applications, Set (abstract data type), 03 medical and health sciences, Nonlinear system, Management information systems, 030104 developmental biology, 0302 clinical medicine, Computational Theory and Mathematics, Dimension (vector space), 030220 oncology & carcinogenesis, Modeling and Simulation, Dynamic factor, Artificial intelligence, business, computer, Information Systems |
| الوصف: | Most multivariate forecasting methods in the literature are restricted to vector time series of low dimension, linear methods and short horizons. Big data revolution is instead shifting the focus to problems (e.g., issued from the IoT technology) characterized by very large dimension, nonlinearity and long forecasting horizons. This paper discusses and compares a set of state-of-the-art methods which could be promising in tackling such challenges. Also, it proposes DFML, a machine-learning version of the dynamic factor model, a successful forecasting methodology well-known in econometrics. The DFML strategy is based on a out-of-sample selection of the nonlinear forecaster, the number of latent components and the multi-step-ahead strategy. We will discuss both a batch and an incremental version of DFML, and we will show that it can consistently outperform state-of-the-art methods in a number of Synthetic and real forecasting tasks. |
| تدمد: | 2364-4168 2364-415X |
| الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_________::0adc46eb7e7535e9551d34738ff5129aTest https://doi.org/10.1007/s41060-018-0150-xTest |
| حقوق: | CLOSED |
| رقم الانضمام: | edsair.doi...........0adc46eb7e7535e9551d34738ff5129a |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 23644168 2364415X |
|---|