Re:Machine learning is still too hard for software engineers
by disgruntledphd2 on Thursday February 24, 2022 @08:30AM
(#30454408)
To be fair, any competent data team would have done the same analysis first, before attempting to build complicated models.
As I keep saying to people, sometimes the best model is a well chosen graph.
Could the Data/ML team have done something cool and likely complex to show clearer patterns and maybe get something in place to continually refine that data? Probably. Would it have saved more money for the company eventually? Unknown. Would it have cost substantially more money to design and implement? Pretty sure.