← All domainsCASE STUDIES

Cross-domain

Foundational time-series technology that is not tied to a single field. Models and methods from our own research that underpin case studies in every domain.

2026-08-18

DecompSSM: A Decomposition-Based State Space Model for Multivariate Time-Series Forecasting

Our forecasting model learns to decompose series into trend, seasonal and residual components end-to-end. Accepted at ICASSP 2026, it achieved the best accuracy in 28 of 32 standard benchmark settings.