On four public datasets, Gradient Boosting with hand-built features beat Chronos, Llama, and ARIMA on most accuracy metrics, while Chronos only led on financial sMAPE.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On Identifying Why and When Foundation Models Perform Well on Time-Series Forecasting Using Automated Explanations and Rating
On four public datasets, Gradient Boosting with hand-built features beat Chronos, Llama, and ARIMA on most accuracy metrics, while Chronos only led on financial sMAPE.