Case Study: Penske Media Corporation achieves ML-ready data infrastructure and streamlined Airflow operations with Astronomer, Inc.

Penske Media Corporation (PMC) Builds the Infrastructure They Need to Pursue Machine Learning and Data Scien

Penske Media Corporation (PMC), a leading digital media and information services company, needed a reliable data infrastructure to turn clickstream and other sources into actionable insights for recommendations, pageview predictions and subscriber modeling. Early efforts relied on cron jobs and ad-hoc job servers, and although Apache Airflow helped organize workflows, PMC still faced heavy operational overhead, fragile DAGs and no testing framework — challenges that threatened to require a full‑time manager. To address this, PMC turned to Astronomer, Inc.’s managed Airflow offering.

Astronomer, Inc. took over Airflow operations, providing best practices, DAG monitoring and on‑demand support via Intercom while PMC feeds task events into BigQuery and runs anomaly detection on workflow behavior. The result: fragile cron systems were replaced by reliable, monitored pipelines, operational burden was removed (avoiding the need for a dedicated manager), and PMC’s engineers and data scientists are now able to focus on machine learning work — powering recommendation engines, subscriber scoring and plans to move to real‑time streaming to further improve model accuracy.

Penske Media Corporation

Andy Maguire

Data Scientist