How Are You Managing Your Experiments Before?

i come originally from doing mostly physics, base modelling. When i started migrating to more and more data science work, i started looking for the methodologies. It was almost upsetting at first o realize we actually use models that aren't in the 95 plus % accuracy range. And then it dawned on me, wait a minute. I'm spoiled by the neering realm. If you get a model in place, and you had no model before, 65% accuracies at godsend. Then you can improve things from there as you collect more data.