TY - JOUR
T1 - Forecasting with temporal hierarchies
AU - Athanasopoulos, George
AU - Hyndman, Rob J.
AU - Kourentzes, Nikolaos
AU - Petropoulos, Fotios
PY - 2017/10/1
Y1 - 2017/10/1
N2 - This paper introduces the concept of Temporal Hierarchies for time series forecasting. A temporal hierarchy can be constructed for any time series by means of non-overlapping temporal aggregation. Predictions constructed at all aggregation levels are combined with the proposed framework to result in temporally reconciled, accurate and robust forecasts. The implied combination mitigates modelling uncertainty, while the reconciled nature of the forecasts results in a unified prediction that supports aligned decisions at different planning horizons: from short-term operational up to long-term strategic planning. The proposed methodology is independent of forecasting models. It can embed high level managerial forecasts that incorporate complex and unstructured information with lower level statistical forecasts. Our results show that forecasting with temporal hierarchies increases accuracy over conventional forecasting, particularly under increased modelling uncertainty. We discuss organisational implications of the temporally reconciled forecasts using a case study of Accident & Emergency departments.
AB - This paper introduces the concept of Temporal Hierarchies for time series forecasting. A temporal hierarchy can be constructed for any time series by means of non-overlapping temporal aggregation. Predictions constructed at all aggregation levels are combined with the proposed framework to result in temporally reconciled, accurate and robust forecasts. The implied combination mitigates modelling uncertainty, while the reconciled nature of the forecasts results in a unified prediction that supports aligned decisions at different planning horizons: from short-term operational up to long-term strategic planning. The proposed methodology is independent of forecasting models. It can embed high level managerial forecasts that incorporate complex and unstructured information with lower level statistical forecasts. Our results show that forecasting with temporal hierarchies increases accuracy over conventional forecasting, particularly under increased modelling uncertainty. We discuss organisational implications of the temporally reconciled forecasts using a case study of Accident & Emergency departments.
KW - Forecast combination
KW - Forecasting
KW - Hierarchical forecasting
KW - Reconciliation
KW - Temporal aggregation
UR - http://www.scopus.com/inward/record.url?scp=85016026511&partnerID=8YFLogxK
U2 - 10.1016/j.ejor.2017.02.046
DO - 10.1016/j.ejor.2017.02.046
M3 - Article
AN - SCOPUS:85016026511
SN - 0377-2217
VL - 262
SP - 60
EP - 74
JO - European Journal of Operational Research
JF - European Journal of Operational Research
IS - 1
ER -