Win Tun Lin has completed
Designing Forecasting Pipelines for Production
Start course For Free4 hr
4,000 XP

Loved by learners at thousands of companies
Course Description
Learn how to design, automate, and monitor scalable forecasting pipelines in Python. This advanced course walks you through the entire production workflow - from sourcing data and training models to deployment and monitoring - using tools like MLflow and Airflow.You'll start by connecting to live data sources and building your first forecast with U.S. electricity demand data. Next, you'll discover experimentation fundamentals, including backtesting, evaluation, and model registration using MLflow.Then you'll build automated forecasting pipelines with ETL processes, model registration, and Airflow orchestration. Finally, you'll learn production deployment essentials, including monitoring pipeline health, detecting model drift, and maintaining forecasting systems in real-world environments.
Training 2 or more people?
Get your team access to the full DataCamp platform, including all the features.- 1
General Architecture
FreeLearn how to connect to live data sources and prepare time series data for forecasting. You’ll pull hourly electricity demand data from the U.S. EIA API and build your first forecast.
Productionizing your forecast model50 xpForecasting project architecture50 xpBenefits of experimentation frameworks50 xpReviewing the input data50 xpMaking an API request100 xpPreparing and visualizing the data100 xpInterpreting time series visualizations50 xpWorking with a forecast object50 xpForecasting with ML Models100 xpEvaluating forecast performance100 xpVisualizing forecast performance100 xp - 2
Experimentation
Discover the fundamentals of experimentation, including backtesting, evaluation, and model registration using MLflow!
Experimentation50 xpForecast evaluation & experimentation100 xpExploring experimentation process50 xpWorkflow of experimentation100 xpBacktesting50 xpDefining the forecasting models100 xpTraining models with backtesting100 xpVisualizing forecast results100 xpModel Scoring50 xpTransforming backtesting output100 xpBuilding a model leaderboard100 xpModel Registration with MLflow50 xpLogging tuned models100 xpSearching experiment results100 xp - 3
Setting Automation
Learn how to build automated forecasting pipelines that refresh data and predictions daily. You'll set up ETL processes, register models with MLflow, and orchestrate everything with Airflow. Create a production-ready system with data validation and logging to monitor pipeline health.
Pipeline architecture50 xpDefining the forecasting pipeline100 xpFitting the model100 xpRegistering the model100 xpData ingestion50 xpData parity checks50 xpDefining the schema100 xpPerforming data validation100 xpAirflow50 xpSetting up the DAG100 xpCreating the DAG100 xpDefining pipeline execution order100 xpLogs50 xpMonitoring ETL logs50 xpMonitoring forecasting logs50 xp - 4
From Deployment to Production
Discover the essentials of production deployment, from monitoring the pipeline health to detecting model drift. You'll learn best practices for reproducibility, scaling, and maintaining forecasting systems in real-world environments.
Pipeline Deployment to Production50 xpWhat could go wrong?100 xpMonitoring vs Observability100 xpPipeline Monitoring50 xpCategorizing API risks100 xpBuilding a mitigation plan50 xpModel Drift50 xpCalculating a threshold and moving averages100 xpIdentifying model drift100 xpBest practices50 xpDevelopment best practices50 xpScaling forecasting pipelines50 xpCongratulations!50 xp
Training 2 or more people?
Get your team access to the full DataCamp platform, including all the features.collaborators


Senior Manager - Data Science and Engineering at Apple
I'm a senior data science and engineering manager at Apple, author, open-source contributor, Docker Captain, and Instructor. I enjoy teaching about data science in production, MLOps, and Docker.
Join over 18 million learners and start Designing Forecasting Pipelines for Production today!
Create Your Free Account
or
By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.