Anomaly Detection is the identification of rare items, events, or observations in data that differ significantly from the expectation. This can be used for several scenarios like asset monitoring, maintenance and prognostic surveillance in industries such as utility, aviation and manufacturing.
The core algorithm of our Anomaly Detection service is an Oracle-patented multivariate time-series anomaly detection algorithm originally developed by Oracle Labs and had been successfully used in several industries for prognosis analysis.
The Oracle Cloud Infrastructure Anomaly Detection will create customized Machine Learning models by taking the data uploaded by users, using the core algorithm to train the model, and hosted in the cloud to be ready for detection. Users can then send new data to the detection endpoints to get detected anomaly results.
In this workshop, we want to help users achieve the following objectives:
Understand a high level overview of the OCI Anomaly Detection Service
Understand the full cycle/workflow of univariate anomaly detection service provided in the OCI Anomaly Detection
Understand the full cycle/workflow of multivariate anomaly detection service provided in the OCI Anomaly Detection
Hand-on activities to experience the whole pipeline of machine learning model development from training to detecting
(In Advanced Sessions) Learn to use REST API to interact with Anomaly Detection service
(In Advanced Sessions) Learn basic data analysis preprocessing techniques to prepare data for model training