The Most Useful Approach to Machine Learning

The quickest wins are always going to be the easiest algorithms, right? If you can map anything into a very simple machine learning algorithm, you know, with a prediction variable you're going for with some features. Yeah, I mean, you could do that pretty easily. But if you need to dynamically optimize a really complex system and you need to go to like a deep reinforcement algorithm, yeah,. That's going to take a lot more time in the amount of lift you might get there. It might be extremely incremental. So again, right, there's a trade off and all of these things.