https://kobybibas.github.io/tags/forecasting/Recent content in Forecasting on Koby BibasHugo -- gohugo.ioenSat, 04 Apr 2026 00:00:00 +0000https://kobybibas.github.io/posts/20260404_timesfm_decoder_only_time_series/summary/Sat, 04 Apr 2026 00:00:00 +0000https://kobybibas.github.io/posts/20260404_timesfm_decoder_only_time_series/summary/TL;DR TimesFM is a 200M-parameter decoder-only transformer trained on ~100B timepoints. It treats time-series patches the way LLMs treat tokens. In zero-shot, it matches or beats supervised SOTA on standard benchmarks while costing a fraction of LLM-based approaches like LLMTime. Motivation Classical methods (ARIMA, ETS) fit per-series and cannot transfer across datasets. LLMTime repurposes GPT-3/LLaMA-2 as zero-shot forecasters but is expensive and underperforms supervised models. NLP and CV have foundation models, but time series is harder: no discrete vocabulary, variable context/horizon/granularity, and far less public data.