Unverified50% confidenceFactExact time
Google TimesFM is a foundation model dedicated to time series forecasting, capable of zero-shot prediction without requiring specialized training on specific business data.
1
Sources
50%
Confidence
Long-term
Relevance
9/10/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGoogle officially disclosed that TimesFM was pre-trained on 200B time points of data, covering multiple domains including finance, retail, energy, and healthcare.78% similarUnverified谷歌发布了两款基础模型TabFM（面向表格数据）和TimesFM（面向时间序列）77% similarUnverifiedRepresentative time-series foundation models include Google's TimesFM, Amazon's Chronos, and Salesforce's Moirai.72% similarUnverifiedGoogle Research introduced TabFM, a zero-shot tabular data foundation model employing three mechanisms—alternating row-column attention, row compression, and in-context learning Transformer—and TabFM Ensemble ranked first on both classification and regression tasks on the Tab Arena benchmark (38 classification datasets and 13 regression datasets).65% similarUnverifiedGoogle's TimesFM is built on the PatchTST approach and performs well on multiple public benchmarks64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/888673API
curl https://kongchang.com/api/v1/knowledge/claims/888673MCP
get_claim(id=888673)