Case Study: Ferrari improves car testing efficiency with Andersen’s ML-driven predictive maintenance system

Ferrari improves car testing with Andersen’s ML system, achieving 92% model accuracy

The luxury car manufacturer Ferrari faced a significant challenge with its dyno stand testing equipment, which was prone to malfunctions that could halt the entire car design testing process. To move beyond reactive maintenance, Ferrari partnered with vendor Andersen to develop a machine learning-driven predictive maintenance system.

Andersen implemented an ML-based solution that analyzes equipment data to forecast failures and generate repair recommendations before breakdowns occur. This system, developed by Andersen, achieved a 92% accuracy rate for its predictions. The results for Ferrari included a 40% reduction in testing costs and a significant decrease in equipment idle time, all while staying fully within the project's budget and timeline.

Ferrari