Multiple-input neural networks for time series forecasting incorporating historical and prospective context

• Published in: Data mining and knowledge discovery Vol. 38; no. 1; pp. 315 - 341
• Main Authors: Palet, João, Manquinho, Vasco, Henriques, Rui
• Format: Journal Article
• Language: English
• Published: New York Springer US 2024; Springer Nature B.V
• Subjects: Artificial Intelligence; Chemistry and Earth Sciences; Computer Science; Context; Data Mining and Knowledge Discovery; Emergency medical services; Information Storage and Retrieval; Neural networks; Open systems; Physics; S.I. : ECML PKDD 2023; Statistics for Engineering; Time series; Weather forecasting; Time series forecasting; Situational context; Multiple-input neural networks
• ISSN: 1384-5810; 1573-756X
• DOI: 10.1007/s10618-023-00984-y

Individual and societal systems are open systems continuously affected by their situational context. In recent years, context sources have been increasingly considered in different domains to aid short and long-term forecasts of systems’ behavior. Nevertheless, available research generally disregards the role of prospective context, such as calendrical planning or weather forecasts. This work proposes a multiple-input neural architecture consisting of a sequential composition of long short-term memory units or temporal convolutional networks able to incorporate both historical and prospective sources of situational context to aid time series forecasting tasks. Considering urban case studies, we further assess the impact that different sources of external context have on medical emergency and mobility forecasts. Results show that the incorporation of external context variables, including calendrical and weather variables, can significantly reduce forecasting errors against state-of-the-art forecasters. In particular, the incorporation of prospective context, generally neglected in related work, mitigates error increases along the forecasting horizon.