Failure label
A failure label is a recorded outcome assigned to an observation under an explicit rule defining which event counts as failure and when it occurs.
Specify the event, counting unit and timestamp. Lu et al. use the operator's disk replacement decision after failed I/O and unsuccessful restart. [1] Narya instead targets customer-impacting host failures later attributed to hardware faults; a permanent component failure can occur later. [2]
Relations
- related
- prediction-horizon, temporal-validation, grouped-cross-validation, smart, right-censoring
Limitations
- A replacement record is not automatically a physical failure or a service outage; changing the target changes the prediction task. [1, 2]