Modules

Welcome to the Modules section of the course. Each module is a short, guided sequence of lessons with examples and practice opportunities.

• Start here: Module 1 — Introduction
• Looking for practice? Go to Exercises

TipHow to navigate

Use the Modules sidebar to move lesson-by-lesson. Each lesson page includes explanations, code, and short checks to make sure ideas stick.

1 Prerequisites and setup

A dedicated setup page is coming soon. For now:

• Make sure you can open an .Rproj, run an {r} code chunk, and install packages in R.
• If something breaks, start with Module 1 — Introduction, which includes the course expectations and workflow.

2 Course map

2.1 Module 1: Forecasting models based on decomposition methods

You’ll build fundamentals: time series data structures, decomposition, and forecasting principles.

• 1.0 Introduction
• 1.1 RStudio, R, and Time Series
• 1.2 Time Series Decomposition
• 1.3 Forecasting principles
• 1.4 The Forecasting Workflow

What’s next? Start with 1.0 Introduction, then continue in order using the sidebar.

---

2.2 Module 2: Adding ETS and ARIMA filters

You’ll expand to classical statistical forecasting families and diagnostics.

• 2.1 Exponential Smoothing
• 2.2 Identifying Stationarity
• 2.3 ARIMA models (coming soon)
• 2.4 Decomposition & ETS/ARIMA (coming soon)

What’s next? After Module 1, begin with 2.1 Exponential Smoothing.

---

2.3 Module 3: Adding exogenous variables to the model

You’ll incorporate external drivers and build stronger, more realistic forecasts.

• 3.1 Linear Regression Models
• 3.2 Build dynamic regressions (coming soon)
• 3.3 Analyze the model’s performance (coming soon)
• 3.4 Choose the best variables for the model (coming soon)

What’s next? When available, start with 3.1 Linear Regression Models and follow the sequence.

---

2.4 Module 4: Forecasting at scale

You’ll learn approaches for multiple series, hierarchy, reconciliation, and scalable evaluation.

• 4.1 Understanding the challenges and approaches when dealing with multiple time series (coming soon)
• 4.2 Applying hierarchical and reconciliation models (coming soon)
• 4.3 Efficient forecasting workflow (coming soon)
• 4.4 Evaluation of the global performance (coming soon)

What’s next? Check back once lessons are published—this module will be best tackled after Modules 1–3.

3 Recommended study loop

1. Read the lesson (focus on why the method works).
2. Run the code and check outputs.
3. Tweak one assumption (horizon, transformation, features) and observe what changes.
4. Practice with the matching exercise set.