“…Time series modeling has historically been a key area of academic research, forming an integral part of applications in topics such as climate modeling (Mudelsee, 2019), biological sciences (Stoffer and Ombao, 2012), and medicine (Topol, 2019), as well as commercial decision making in retail (Böse et al, 2017), finance (Andersen et al, 2005), and net-load consumption for customer (Thayer et al, 2020) to name a few. While traditional methods have focused on parametric models informed by domain expertise such as autoregressive (AR) (Box and Jenkins, 1976), exponential smoothing (Winters, 1960;Gardner, 1985), or structural time series models (Harvey, 1990), modern machine learning methods provide a means to learn temporal dynamics in a purely data-driven manner (Ahmed et al, 2010).…”