AI Roadmaps
← All roadmaps
IntermediateRoadmap 17 · 11 steps · 3h 48m of video

Time Series & Forecasting

Predict what happens next: trend, seasonality, ARIMA, boosted trees, deep models, and today's pretrained forecasting models.

Before this: Machine Learning. Deep Learning helps for the later steps.

  1. 10 min
    Step 1

    Stationarity

    Why most classical models need a steady mean and variance.

    Time Series Talk : Stationarity

    ritvikmath

  2. 5 min
    Step 2

    Trend, seasonality, and decomposition

    Split a series into parts you can reason about.

    What is Time Series Decomposition

    Aric LaBarr

  3. 10 min
    Step 3

    Exponential smoothing and Holt-Winters

    A strong baseline that handles trend and seasons.

    What is Holt Winters Method? - Time Series Forecasting

    Egor Howell

    Nixtla/statsforecast★ 5k
  4. 16 min
    Step 4

    ARIMA

    Autoregression, differencing, and moving averages in one model.

    ARIMA Model Explained | Time Series Forecasting

    Egor Howell

  5. 11 min
    Step 5

    Cross-validation for time series

    Validate forward in time so you never peek at the future.

    Cross-Validation for Time Series Forecasting | Python Tutorial

    Egor Howell

  6. 23 min
    Step 6

    Forecasting with XGBoost

    Lag and calendar features with gradient-boosted trees.

    Time Series Forecasting with XGBoost - Use python and machine learning to predict energy consumption

    Rob Mulla

  7. 30 min
    Step 7

    LSTM forecasting

    A first neural forecaster, with its limits shown clearly.

    LSTM Time Series Forecasting Tutorial in Python

    Greg Hogg

  8. 21 min
    Step 8

    Temporal Fusion Transformer

    Multi-horizon forecasts with attention and interpretable features.

    Temporal Fusion Transformers, EXPLAINED. Advanced Time Series Forecasting

    Data Heroes

    Nixtla/neuralforecast★ 4.3k
  9. 19 min
    Step 9

    Time series foundation models

    Why pretrained forecasters can work zero-shot.

    Time Series Foundation Models

    Anastasia Borovykh

  10. 49 min
    Step 10

    Chronos: pretrained forecasting

    Forecast with a pretrained model and read its probabilistic output.

    Chronos: Time series forecasting in the age of pretrained models

    AutoML Space

    amazon-science/chronos-forecasting★ 6.3k
  11. 34 min
    Step 11

    Anomaly detection basics

    Spot unusual points with robust statistics and isolation forests.

    Anomaly detection in time series with Python | Data Science with Marco

    Data Science with Marco

Build it

Watching isn't learning. Pick one and put it on GitHub.

Where to go next