05 — Time Series
Modelling ordered, time-indexed data: classical statistical approaches, probabilistic state-space models, and machine-learning-based forecasting.
Sublayers
01 — Classical Forecasting
ARIMA, seasonal decomposition (STL), exponential smoothing, VAR models.
02 — State-Space and Probabilistic Models
Kalman filter, structural time series models, Dynamic Linear Models (DLMs).
03 — ML and DL Forecasting
Gradient boosting for time series (feature engineering approach), LSTMs, temporal convolutional networks, N-BEATS, temporal fusion transformers.