مقایسهٔ روش‌ها

	مدل خطی تجزیه‌پذیر برای پیش‌بینی سری‌های زمانی (DLinear)	مدل آریما (میانگین متحرک یکپارچه خودرگرسیو)	پچ‌تی‌اس‌تی
حوزه	یادگیری عمیق	اقتصادسنجی	یادگیری عمیق
خانواده	Machine learning	Regression model	Machine learning
سال پیدایش	2023	2015	2023
پدیدآور	Ailing Zeng et al.	Box & Jenkins (Box-Jenkins methodology)	Nie, Y. et al.
نوع	Decomposition-based linear forecasting model	Univariate time-series model	Transformer for time series forecasting
منبع بنیادین	Zeng, A., Chen, M., Zhang, L., & Xu, Q. (2023). Are transformers effective for time series forecasting? AAAI.	Box, G. E. P., Jenkins, G. M., Reinsel, G. C. & Ljung, G. M. (2015). Time Series Analysis: Forecasting and Control (5th ed.). Wiley. ISBN: 978-1118675021	Nie, Y., Nguyen, N. H., Sinthong, P. & Kalagnanam, J. (2023). A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. ICLR.
نام‌های دیگر	Decomposition Linear, DLinear Forecaster, Linear Decomposition Model, Ayrışım Doğrusal Modeli	Box-Jenkins model, ARIMA(p,d,q), ARIMA Modeli	PatchTST — Yama Tabanlı Zaman Serisi Transformer, patch-based time series transformer, channel-independent transformer
مرتبط	3	5	3
خلاصه	DLinear is a lightweight time series forecasting model introduced by Zeng et al. at AAAI 2023. It challenges the prevailing assumption that Transformer-based architectures are necessary for accurate long-horizon forecasting. The model decomposes an input sequence into trend and seasonal components using a moving average filter, then applies separate single-layer linear transformations to each component before summing their outputs to produce the final forecast.	ARIMA is a univariate time-series forecasting model that combines autoregressive, integrated (differencing), and moving-average components to predict a single continuous series from its own past. It is the centrepiece of the Box-Jenkins methodology set out in Box, Jenkins, Reinsel & Ljung's Time Series Analysis (5th ed., 2015).	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.