Stanza: A Nonlinear State Space Model for Probabilistic Inference in Non-Stationary Time Series

TL;DR

Stanza is a nonlinear, non-stationary state space model that balances traditional probabilistic inference with deep learning performance for complex, structured time series forecasting.

Contribution

It introduces Stanza, a novel model bridging traditional state space models and deep learning for improved accuracy and interpretability in non-stationary time series.

Findings

Competitive forecasting accuracy with deep LSTMs

Effective for multi-step ahead forecasting

Provides probabilistic, interpretable inference

Abstract

Time series with long-term structure arise in a variety of contexts and capturing this temporal structure is a critical challenge in time series analysis for both inference and forecasting settings. Traditionally, state space models have been successful in providing uncertainty estimates of trajectories in the latent space. More recently, deep learning, attention-based approaches have achieved state of the art performance for sequence modeling, though often require large amounts of data and parameters to do so. We propose Stanza, a nonlinear, non-stationary state space model as an intermediate approach to fill the gap between traditional models and modern deep learning approaches for complex time series. Stanza strikes a balance between competitive forecasting accuracy and probabilistic, interpretable inference for highly structured time series. In particular, Stanza achieves forecasting accuracy competitive with deep LSTMs on real-world datasets, especially for multi-step ahead forecasting.