Machine Learning Models Aren't Creating a Lot of Value

Most machine learning models are not creating a lot of value. How do you identify when or if it's time to stop working on the model? It was a big part of my job in insect, figuring for the ten thousand different problems that we faced and which ones were reasonable to try using machine learning on. Until we have fundamentally new ideas or fundamentally new data to bring to the problem, we need to stop, says John Defterios.

Transcript

Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.