Search papers, labs, and topics across Lattice.
This paper systematically investigates the impact of seven distinct calendar feature encodings on the forecasting accuracy of four state-of-the-art time series foundation models (TSFMs) across nine diverse datasets. The study reveals that encoding choices significantly influence forecast performance, particularly around holidays where calendar information provides unique predictive signals not present in target history. Findings highlight that current TSFM benchmarks may be biased by fixed encoding strategies, potentially distorting model comparisons.
Calendar encoding choice can degrade holiday forecasts by over 80% in state-of-the-art TSFMs, revealing a critical blind spot in current covariate-informed model evaluation.
Time series foundation models (TSFMs) increasingly offer covariate support, with calendar information being the most common type of categorical covariate in practice, as it is available for every point in time. However, how these features are encoded is largely treated as an implementation detail rather than as an object of study, despite encoding being one of the few design choices left for pretrained models at inference time. With the present study, we demonstrate that the way information is propagated into the model substantially affects forecast accuracy of TSFMs. Therefore, we systematically compare seven calendar encodings, including three conventional target-agnostic representations (ordinal, one-hot, and cyclic) and four target encodings, across four state-of-the-art TSFMs on nine datasets from multiple domains in a zero-shot rolling evaluation. The nine datasets are influenced by social activities, such as weekends and holidays, making calendar information particularly relevant for forecasting. We find that encoding choice affects forecast accuracy across all models, with MASE differences of up to 9.9 % on non-holidays and 83 % on holidays within a single model. Effectiveness and utilization vary substantially across models. Improvements are concentrated around holidays, where calendar information provides signals unavailable from target history, while some model encoding combinations also improve non-holiday forecasts. A SHAP-based attribution analysis locates the contribution of the covariates relative to the autoregressive component and explains why some model-encoding combinations degrade performance. Our findings suggest that current benchmarks for covariate-informed TSFMs can distort model comparisons by imposing fixed encoding strategies.
