Порівняння методів

	TimesFM: Декодер-орієнтована базова модель для прогнозування часових рядів	Chronos: Токенізована базова модель для прогнозування часових рядів	PatchTST
Галузь	Глибоке навчання	Глибоке навчання	Глибоке навчання
Родина	Machine learning	Machine learning	Machine learning
Рік появи	2024	2024	2023
Автор методу	Abhimanyu Das et al. (Google)	Abdul Fatir Ansari et al. (Amazon)	Nie, Y. et al.
Тип	Pre-trained decoder-only transformer for zero-shot time-series forecasting	Pre-trained language-model-based time-series forecaster	Transformer for time series forecasting
Основоположне джерело	Das, A., Kong, W., Sen, R., & Zhou, Y. (2024). A decoder-only foundation model for time-series forecasting. ICML.	Ansari, A. F., Stella, L., Turkmen, C., Zhang, X., Mercado, P., Shen, H., et al. (2024). Chronos: Learning the language of time series. Transactions on Machine Learning Research.	Nie, Y., Nguyen, N. H., Sinthong, P. & Kalagnanam, J. (2023). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. ICLR.
Інші назви	Time-series Foundation Model, Google TimesFM, TimesFM forecaster, Zaman Serisi Temel Modeli	Chronos Forecasting Model, Amazon Chronos, Tokenized Time-Series LLM, Kronos Zaman Serisi Modeli	PatchTST — Yama Tabanlı Zaman Serisi Transformer, patch-based time series transformer, channel-independent transformer
Пов'язані	3	2	3
Підсумок	TimesFM is a pre-trained foundation model for univariate time-series forecasting introduced by Abhimanyu Das, Weihao Kong, Rajat Sen, and Yichen Zhou from Google in 2024. The model adopts a decoder-only transformer architecture, similar in spirit to large language models, and is trained on a large corpus of real-world and synthetic time-series data. Its central innovation is the ability to perform accurate zero-shot forecasting across diverse domains without task-specific fine-tuning.	Chronos is a family of pre-trained probabilistic forecasting models introduced by Ansari et al. at Amazon in 2024. It adapts the language-model paradigm to time series by quantizing continuous values into discrete tokens, enabling a standard transformer to be trained on a large heterogeneous corpus of time-series data. The result is a zero-shot forecasting model that generalizes across domains without requiring dataset-specific retraining.	PatchTST is a patch-based Transformer architecture for time series forecasting, introduced by Nie and colleagues in 2023, that cuts each series into overlapping patches treated as tokens and processes channels independently. It balances computational efficiency with strong accuracy on long-horizon forecasting.