TY - JOUR
T1 - The Trade-offs Between Forecasting Performance and Computational Cost
AU - Petropoulos, Fotios
AU - Spiliotis, Evangelos
PY - 2025/1/13
Y1 - 2025/1/13
N2 - Forecasting performance is typically evaluated by statistical measures of forecast error, ignoring the computational cost of producing the forecast. Yet these costs, in both computer time and environmental impact, can be huge. Building upon previous research, Petropoulos and Spiliotis show how forecast computation time can be dramatically reduced without significant impact on forecast accuracy.
AB - Forecasting performance is typically evaluated by statistical measures of forecast error, ignoring the computational cost of producing the forecast. Yet these costs, in both computer time and environmental impact, can be huge. Building upon previous research, Petropoulos and Spiliotis show how forecast computation time can be dramatically reduced without significant impact on forecast accuracy.
M3 - Article
SN - 1555-9068
JO - Foresight: the International Journal of Applied Forecasting
JF - Foresight: the International Journal of Applied Forecasting
ER -