Skip to main content
Intermediate ~18 hours

Time-Series Forecasting with Modern Tools

Forecast demand or revenue using Prophet, statsforecast, or temporal fusion transformers. Practical and high-impact.

PythonProphetstatsforecast or sktimePyTorch (for TFT)

About this project

Time-series forecasting is constantly in demand: revenue forecasting, demand planning, capacity planning. This project teaches the modern toolkit: Prophet for quick wins, statsforecast for classical baselines, and a Transformer-based model (TFT) for harder cases. Use a real dataset (ecommerce sales, electricity demand) and benchmark multiple approaches.

Why build this in 2026?

Forecasting is one of the highest-business-impact DS specialties — most teams need it but few do it well.

What you'll ship

  • Jupyter notebook
Benchmark table (3+ methods on same data)
Writeup recommending one method

Sign up to see the full project brief

Full deliverables, success criteria, and AI Career Tutor support — free.

You'll unlock:Complete project brief, AI tutor that knows this project, and progress tracking when you start.

Skills you'll practice

pythonmachine learningpandas