The study introduces Local and Global Trend Bayesian Exponential Smoothing Models as extensions to classical ETS models. It discusses the motivation, model specifications, implementation details, and prior distributions. The models aim to address shortcomings in traditional ETS models by offering more flexibility in trend modeling and error distribution. The study provides insights into the application of Bayesian methods for accurate forecasting.
Til et andet sprog
fra kildeindhold
arxiv.org
Vigtigste indsigter udtrukket fra
by Slawek Smyl,... kl. arxiv.org 03-25-2024
https://arxiv.org/pdf/2309.13950.pdfDybere Forespørgsler