Exposure weighted coefficients for GLM models varimp

[genrichards]

Is your feature request related to a problem? Please describe.
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]

I noticed that the varimp() for h2o.glm is just the sum of the absolute values of standardised coefficients. Have you ever considered using the exposure weighted coefficients (eg a 5% increase on 50% of the book is more importance than a 100% increase on 1% of the book)
Describe the solution you'd like
A clear and concise description of what you want to happen.
e.g. a 5% increase on 50% of the book is more importance than a 100% increase on 1% of the book.
Describe alternatives you've considered
A clear and concise description of any alternative solutions or features you've considered, if applicable.

Additional context
Add any other context or screenshots about the feature request here. If there's a reference (paper, book, etc) for this feature, please add that here.

H2O.ai Devs only
If there is a support ticket associated with this issue, please post the link here.
Feedback from customer

[wendycwong]

@genrichards : Is there any reference on this method?