Evaluating models without test data (Practical AI #194)
Changelog Master Feed
How to Evaluate a Model Without a Test Set
There are many problems in generating, and we're generating things. A lot of data is out-of-sample; you can't really evaluate it without human judgments or it's very expensive. And there are all sorts of biases that exist in the data,. People tend to click on things that are in the first element, and that screws the model up. There are many cases and other good examples when you're trying to predict the stock market.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
