This proposed session would attempt to use the latest TimesFM-3 Multivariate Time series forecasting model on [agriculture and forestry time series from the German statistical office](https://www.destatis.de/EN/Themes/Economy/Prices/Price-Indices-In-Agriculture-And-Forestry/_node.html#266126). - TimesFM-3: A zero-shot foundation model for multivariate forecasting https://research.google/blog/timesfm-3-a-zero-shot-foundation-model-for-multivariate-forecasting/?ref=aisecret.us - For example monthly oak, beech, spruce and pine stemwood producer price indexes on https://genesis.destatis.de/datenbank/online?sequenz=statistikTabellen&selectionname=61231&language=en {width="900" height="554"} - Another example the monthly price indexes of wheat, barley, sugar beet and potato on https://genesis.destatis.de/datenbank/online?sequenz=statistikTabellen&selectionname=61211&language=en {width="900" height="562"} - Other data sources with higher frequencies welcomed. - How can we compare TimesFM-3 with econometric models on monthly agricultural price series? Specifically: which models and metrics should be used, and how should we handle issues like non‑stationarity, seasonality, and regime shifts?