Creating and Running a Model

Dexda identifies hidden patterns within the text features of alert data and analyzes and dynamically manages their correlation. This correlation of data is called models. Models let you specifically target business scenarios for which you want to generate actionable insights to be managed in your workflow. For more info on models, correlation, and model testing, see About Models.

Prerequisite

Procedure

1. On the Dexda Home page, select Models. A list of models appears. For info on navigating the models page, see the Models page.
2. Select Create Model.
3. On the configuration page, enter the following details:
   • Name: Enter a name for the model.
   • GroupBy: Add a GroupBy, or grouping item combining similarity correlation value between 0 and 1 (0-100%) with a field, for example, 0,8 and CI. The resource (CI) must be at least 80% similar for a correlation to occur. Select the desired field from the dropdown, available options come from the alerts data, see About Filters. Select Add item to add more items to the grouping, if needed.
   • Add expression: Select Add expression to add a filter to narrow down the correlation, for example, Description-Contains-Kubernetes.
     Note: The right-hand view updates to reflect the current settings to give you an idea of the resulting correlation.
   • Timeout: Define the Timeout duration of the correlation time window, default is 15 minutes (900,000 msecs). After this time, new incoming alerts will be grouped into a new alert cluster and insight
   • MinClusterDensity: Define the MinClusterDensity, which is how many incoming alerts are required to form a cluster within the timeout period. By default, it is set to 2, meaning that at least two incoming alerts are required to form an alert cluster. The value here depends on the type of correlation, see About Models.
   • Stopwords: Select Add item to add a Stopword excluding parts of the message text string, preventing correlation overmatching. For example, adding stopwords for company.com to exclude this from the text to prevent matching bias. You can add multiple Stopwords.
   • RemoveNumbers: Select RemoveNumbers to remove numbers from a string to only match letters in a text string.
   • CaseSensitive: Select CaseSensitive to match the upper and lower case of words in a text string.
   • Trim: Select Trim to remove white spaces at the end of a text spring.
   • Locale: Set the Locale for the model.
4. Select Submit. Once submitted the model will display in the overview with status ready.
5. Select the drop-down under Status and change to Running to start running a model. 
   Note: Models could not be deleted. However, you could change the Status to Archive to stop using a model.