Generally speaking, the more data you have, the better your machine learning model is going to be.

However, stockpiling vast amounts of data also carries a certain privacy, security, and regulatory risks.

With new privacy-preserving techniques, however, data scientists can move forward with their AI projects without putting privacy at risk.

To get the low down on privacy-preserving machine learning (PPML), we talked to Intel’s Casimir Wierzynski, a senior director in the office of the CTO in the company’s AI Platforms Group. Wierzynski leads Intel’s research efforts to “identify, synthesize, and incubate” emerging technologies for AI.

In part 2 of a 3 part series, focused on the Bot Framework, this episode looks at how you can use the telemetry capture capabilities built into the Bot Framework to analyze your bots usage and gain actionable insights by exploring data such as user / conversation trends, channel breakdown and dialog completion vs abandonment.

We discuss why bot analytics are crucial, take a look at how easy it is to enable telemetry capture within your bot and how to drill into your data using Azure and Power BI.

Index

  • [00:40] – Discussion about why bot analytics are important
  • [02:15] – Demo showing how telemetry is wired up within a .NET Core sample bot
  • [04:40] – Viewing telemetry captured during a debug session within Visual Studio
  • [06:40] – Analyzing your telemetry within Application Insights in Azure and creating a dashboard
  • [10:20] – Open source Power BI dashboard for advanced bot analytics

For More Info: