Such an obvious thing, but often forgotten. I make a point to include such updating instructions in everything I delivered. No data, except from physics, is static. Estimate, at least, the risk involved in not updating a model consistently. It also applies to all analytical models, beyond AI/ML models. We did it in common optimization models in the enterprise.
Why is re-training ML Models Important?
A Product Manager’s Perspective in Towards Data Science
By Humberto Corona (totó pampín)
As a product manager, you are responsible for measuring the continuous success of your product. That might include validation before launching, measuring uplifts in an A/B test while launching, and keeping track of core KPIs. If you are managing a Machine Learning product, the long-term success of your product will depend on keeping your models up-to-date. In this post I explain why this is important problem and how can you ensure that continuous success through model re-training. ... "
No comments:
Post a Comment