How To Build A Predictive "Poor Performance" Indicator Using Machine Learning & Python
-
Posted by Quest Customer Learning Team
- Last updated 6/05/23
- Share
Quest Forum Digital Event 2020
Complex performance situations are not always quickly diagnosable using an AWR time-based analysis or an ASH sample-based analysis. And certainly, the diagnosis will not be completed the second new data becomes available or before a support ticket has been received!
A solution is to use a supervised learning classification machine learning model. We can train the model to recognize and “understand” a virtually unlimited number of Oracle performance and business-related data.
Once trained, we will present the model with just-available data asking, for example, if a support ticket will likely be submitted. Or perhaps, if the performance will likely be green, yellow, or red.
Join me as I build a “Poor Performance” indicator using 100% free industry-standard tools, such as Python and the “Always Free” Oracle Autonomous Database with Oracle ML SQL Notebooks. All presentation slides, scripts, and a recording of the demonstration are available!
Watch the full-length video
Premium Content: access is limited to Quest Corporate and Professional members.
Membership has its perks. Get unlimited access to the latest Oracle updates, event session replays, strategic content centers and special members-only programming, plus big discounts on conference registration, with a Quest Corporate or Professional membership. Quest is where you learn.
