Bayesian approaches to failure prediction for disk drives

Hard disk drive failures are rare but are often costly. The ability to predict failures is important to consumers, drive manufacturers, and computer system manufacturers alike. In this paper we investigate the abilities of two Bayesian methods to predict disk drive failures based on measurements of drive internal conditions. We first view the problem from an anomaly detection stance. We introduce a mixture model of naive Bayes submodels (i.e. clusters) that is trained using expectation-maximization. The second method is a naive Bayes classifier, a supervised learning approach. Both methods are tested on realworld data concerning 1936 drives. The predictive accuracy of both algorithms is far higher than the accuracy of thresholding methods used in the disk drive industry today.

• Type: Conference
• Year: 2001
• Where: ICML
• Authors: Greg Hamerly, Charles Elkan
• Keywords: Disk Drive Failures, Disk Drive Industry, Hard Disk Drive, ICML 2001, Machine Learning