5.3.2 Programmable Alerts
7.3 Data Management and Data Model Handling
7.3.4 Working with Data Model
7.4 Control Center
7.4.1 License Entitlements
7.5 Platform Settings
Configuring RCABot and ML Models > Time Series Analysis
It is an anomaly detection technique based on forecasting. We perform forecasting based on time series decomposition (signal=trend+seasonality+residual).
Classical decomposition is used here making it computationally fast and extremely lightweight compared to other methods.
Click on vuCoreML on the left tab and navigate to the Workspaces section.
The workspaces page shows a list of previously configured Workspaces. Click on the + icon to create a new Workspace.
You can now configure the workspace; the workspace comprises 5 major sections
Enter the Workspace Name, Description, and choose the Category as Time Series Analysis, and choose the Run Type as Online or Offline as per the requirement.
Note: Choose Run Type as Online for live data and Offline for third-party systems or files.
Click on Create to create the Workspace.
Once Workspace is created, you will be directed to the Schema page, where you can configure the schema which comprises of Journey section only. The schema is the place where you’ll have to define the business journey and its metrics.
Metrics can be categorized into three types,
Note: You must categorize the metrics accurately because the incidents will be detected only for the lead indicators.
The journey will be the super-set of all metrics and components (i.e. you can think of this as a business journey). You can categorize the metrics at the journey level if they don’t specifically come under any particular component.
You can now click Journey and add a new signal.
For each signal you will be adding, you’ll have to specify the data model and metric column in that model for this signal. Only metric columns in a data model are eligible to be indicators.
You can use the listing option to specify the data model and respective metric column and then categorize that metric using the category listing option. Similarly, you can add other signals.
Click on Save and then click on Submit Schema.
After successfully submitting the Schema, click on the right arrow mark at the top right and you will be directed to the Signalizers page.
The signalizers page contains the list of metrics configured in the Schema page along with information on ML methods that will be running for the respective metrics.
If you want to change the hyper-parameters for a particular metrics ML method, you can click the edit button of the metrics ML method.
It will direct you to the hyper-parameter editing page. On completion of editing, you can click the update for it to override the default parameters.
Now you can either globally activate the signalizers or activate only specific metric signalizers as per requirement locally (at the action section of each metric listed on this page)
After activation, a pop-up will come up where you can click the Activate button.
After clicking, the Time Series Analyser will start creating the required pipelines. Once the pipelines are created.
Click the right arrow to go to the next section > Storyboards.
The storyboard contains insights into a Workspace.
Browse through our resources to learn how you can accelerate digital transformation within your organisation.
VuNet Systems is a next-gen visibility and analytics company that uses full-stack AI & Big Data analytics to accelerate digital transformation within an organisation. We provide deep observability into business journeys to reduce failures and enhance overall customer experience.
© 2023 VuNet. All Rights Reserved.