The app is designed to provide an automated workflow for training machine learning models to identify frequently occurring types of tickets.
Within the app there is a pipeline on top of the Machine Learning Toolkit that allows users to follow some simple click-and-select steps to load their ticket data and select some important features in the data. The app then decides how it should be processed by an ML algorithm – including automatically deciding how the data should be pre-processed in preparation for an algorithm.
Ultimately the app provides non-expert users identify frequently occuring types of tickets
Prerequesites for this app:
- Splunk Machine Learning Toolkit installed: https://splunkbase.splunk.com/app/2890/
- Wordcloud Custom Visualization app installed: https://splunkbase.splunk.com/app/3212/
- Circlepack Viz app installed: https://splunkbase.splunk.com/app/4574/
There is also a webinar that describes the background to the app here:
https://events.splunk.com/machine_learning_deep_dive_081220
For details on how to use the app please refer to this blogpost:
https://www.splunk.com/en_us/blog/machine-learning/smart-ticket-insights-app-for-splunk.html
Updates for version 8.2 compatibility
A number of updates made for this version, including:
- Model naming updates to prevent version clashes
- Updated dashboards
- An additional option to decide to use the description statistics when training a model or not
- A submit button for training the models
- Error handling when training the models
- A new dashboard for viewing the ML models trained by the app
A few bugs related to special character handling in tokens have been fixed
As a Splunkbase app developer, you will have access to all Splunk development resources and receive a 10GB license to build an app that will help solve use cases for customers all over the world. Splunkbase has 1000+ apps from Splunk, our partners and our community. Find an app for most any data source and user need, or simply create your own with help from our developer portal.