Video produced by Steve Nathans-KellyGoogle AI/ML Specialist Skander Hannachi defines explainable AI and outlines its predictive power and overall value proposition for organizations during his presentation at Data Summit Connect 2021.
ML ops from a business perspective is being able to explain your predictions, he explained. Business stakeholders need to understant why an advanced deep learning model or an advanced XG boost model is making predictions and how it is doing so.
"You want to be able to confirm in some situations, there will be regulatory considerations," Hannachi said.
AI and ML models are only as good as the data and the humans who train them. However, there is still bias involved data and processing the data. In order to be able to remove the bias companies need to be able to understand why a model is making prediction.