$\mathtt{tsGT}$: Stochastic Time Series Modeling With Transformer

arXiv:2403.05713v1 Announce Type: new
Abstract: Time series methods are of fundamental importance in virtually any field of science that deals with temporally structured data. Recently, there has been a surge of deterministic transformer models with time series-specific architectural biases. In this paper, we go in a different direction by introducing $\mathtt{tsGT}$, a stochastic time series model built on a general-purpose transformer architecture. We focus on using a well-known and theoretically justified rolling window backtesting and evaluation protocol. We show that …

abstract arxiv biases cs.lg data deals importance modeling paper science series stochastic structured data time series transformer transformer models type