Presented at virtual Activate 2020. Self-solve experience is not optional but the new default. Customers subscribe to Red Hat products with varying levels of operational complexity. Ensuring customers have the right resources such as knowledge base, tooling, and support for troubleshooting is the key to customer renewal. Self-solve options save time and reduce customer frustration. Automation around top problems, proactive diagnostics collection, support request routing are the ways to improve workflow efficiency of support personnel handling the increased case workload.
In this session, we will present challenges and techniques used to improve the findability in self-solve experience and patterns to improve the workflow efficiency. We will also cover the need to infer customer intent from search keywords. We will present a way to differentiate the search intents using machine learning and the steps involved in it such as problem framing, data collection, model building, and end to end integration.
Manikandan Sivanesan, Principal Software Engineer, Red Hat Inc. (subsidiary of IBM)
Jaydeep Rane, Senior Data Scientist, Red Hat Inc. (subsidiary of IBM)
Beginner to Intermediate skilled Data Scientists with an interest in building text-classification models using natural LAnguage Processing. Experience coding in Python is a pre-requisite.
Learn how to leverage these patterns to promote the self-solve experience of their site, and walk away with key lessons in building and deploying an end to end machine learning system in production.
Learn more about how Red Hat uses Fusion.