Home > Workload Solutions > Data Analytics > White Papers > White Paper—Cloud Native Splunk Enterprise with SmartStore—Predictive Maintenance for IT Operations > Splunk stages of predictive maintenance
Predictive analysis requires an organization to be able to ascertain the state of their assets before it is too late to take preventative action. They need comprehensive tools that index data and conduct advanced analytics and machine learning.
Splunk suggests that there are four broad stages to implement predictive maintenance:
Stage 1–Data Collection and Ingestion. Use Splunk software to collect, store, and structure data and metrics from IT assets.
Stage 2–Data Exploration. Preprocessing and data exploration help you understand the type of data in use and the characteristics.
Stage 3–Methods of Analysis. Conduct anomaly detection using supervised and unsupervised machine learning for predictive maintenance analysis.
Stage 4–Operationalization. Apply predictive models to broader implementations, including creation of reports and alerts for operational actions.
With all your data in Splunk, you can leverage Splunk machine learning tools to understand your data and construct machine learning models to take predictive action in an actionable timeframe.