AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
How Do You Determine if Data Is Clean?
In real time, you have no historical model. You're just looking at the data as it currently is and trying to determine whether something is good or bad. The two ways that I've found very effective for dealing with that environment is you can train the system. Another example is just that the system go on and eventually learn that this is not a normalist behavior. This is without any input from an individual, I'm going to just assume this is normal.