The world is changing around us, and deployed machine learning models are losing their power as current behaviors in the economy shift and change rapidly in these uncertain times. Join us as we walk through the practical steps you can take to ensure that your predictions remain relevant and value-generative, even in situations where your training data does not yet reflect this new world.
We will cover:
- It’s the end of the world as we know it: assessing what has changed compared to when you trained your model.
- The features, they are a-changing: quantitatively assessing how model drivers are changing
- Anchoring and proxying: using (economic) history to inform your assumptions
- Tactics and strategies for incorporating revised assumptions in your models
