BASTION: A Bayesian Framework for Trend and Seasonality Decomposition

Jason B. Cho, David S. Matteson

TL;DR: BASTION, a Bayesian framework for decomposing time series into trend and seasonality while handling abrupt changes, outliers, and time-varying volatility.

Abstract: We introduce BASTION (Bayesian Adaptive Seasonality and Trend Decomposition Incorporating Outliers and Noise), a flexible Bayesian framework for decomposing time series into trend and multiple seasonality components. We cast the decomposition as a penalized nonparametric regression and establish formal conditions under which the trend and seasonal components are uniquely identifiable, an issue only treated informally in the existing literature. BASTION offers three key advantages over existing decomposition methods: (1) accurate estimation of trend and seasonality amidst abrupt changes, (2) enhanced robustness against outliers and time-varying volatility, and (3) robust uncertainty quantification. We evaluate BASTION against established methods, including TBATS, STR, and MSTL, using both simulated and real-world datasets. By effectively capturing complex dynamics while accounting for irregular components such as outliers and heteroskedasticity, BASTION delivers a more nuanced and interpretable decomposition. To support further research and practical applications, BASTION is available as an R package at \url{https://anonymous.4open.science/r/BASTION-Anonym-0D40}.

Submission Number: 2070