At GE Aerospace, we build predictive models to optimize utilization of aircraft engines against the cost of maintaining them. These models may be applied to many engine families within which exist multiple combinations of hardware configuration. To complicate things further, there are myriad other labels we apply to various groups or fleets of engines (e.g., airline, region, etc.). 

Parallel plots provide a relatively simple means to visualize and manage these models’ applicability to specific engine serial numbers based on their specific configuration and grouping. As an additional model metric, this visual management helps prioritize updates and tuning of individual models based on inpact.