Порівняння методів

	PatchTST	Конформне прогнозування для прогнозування часових рядів	Випадковий ліс
Галузь	Глибоке навчання	Економетрика	Машинне навчання
Родина	Machine learning	Regression model	Machine learning
Рік появи	2023	2021	2001
Автор методу	Nie, Y. et al.	Angelopoulos & Bates (tutorial); Xu & Xie (time-series EnbPI)	Breiman, L.
Тип	Transformer for time series forecasting	Distribution-free prediction interval wrapper	Ensemble (bagging of decision trees)
Основоположне джерело	Nie, Y., Nguyen, N. H., Sinthong, P. & Kalagnanam, J. (2023). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. ICLR.	Angelopoulos, A. N. & Bates, S. (2023). Conformal Prediction: A Gentle Introduction. Foundations and Trends in Machine Learning, 16(4), 494-591.	Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32.
Інші назви	PatchTST — Yama Tabanlı Zaman Serisi Transformer, patch-based time series transformer, channel-independent transformer	conformal prediction, distribution-free prediction intervals, EnbPI, Konformal Tahmin (Conformal Prediction — Zaman Serisi)	Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble
Пов'язані	3	4	4
Підсумок	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.	Conformal prediction is a distribution-free wrapper that turns any point forecaster — ARIMA, a neural network, or a machine-learning model — into valid prediction intervals using only its residuals. The time-series form was popularised by Xu & Xie (2021) and the modern tutorial treatment by Angelopoulos & Bates (2023).	Random Forest is an ensemble learning method, introduced by Leo Breiman in 2001, that grows many decision trees on bootstrap samples of the data and combines their votes to produce strong classification and regression. By pooling many slightly different trees, it produces more accurate and more stable predictions than any single tree.