Implementing use cases with Splunk Artificial Intelligence
A key step in adopting artificial intelligence and machine learning is having use cases that align to your business priorities and technical capabilities. To begin implementing those use cases, you need to have data flowing into your Splunk deployment in a well thought-out manner. Therefore, before reviewing the use case documentation on this page, start with these two articles on planning and organizing your data flows.
Preparing data for use with the MLTK
Before starting to create models with the Splunk Machine Learning Toolkit (MLTK), you should first spend some time preparing your potential data. Preparing your data allows the relationships between the data to become more visible to you. Learn how with this article.
Organizing machine learning data flows
Depending on the complexity of your use cases, there are different ways to organize data flows for use in the Splunk Machine Learning Toolkit and the Splunk App for Data Science and Deep Learning. Learn about your options here so that you are well prepared to address your use cases.
After your deployment is ingesting the data you need, you can begin to work on use cases. The following links offer step-by-step guidance for only some of the hundreds of possible use cases for artificial intelligence and machine learning. Check back ofter as we continue to update this page with more guidance from Splunkers in the field.
Use cases
Machine Learning Toolkit
Start by reviewing the use cases described in the MLTK deep dives overview, and then move on to the following Splunk Lantern articles: