Steven Struglia comments

Repositories
Issues
Comments

Results 13 comments of


                                            Steven Struglia

Contribution of Control variables (a.k.a Extra features)

Would also like to know as I'm incorporating feature data calculated from Prophet for holiday spikes that are crucial for our marketing.

using old model results as priors for new model?

Agreed that some sort of `warm_start` parameter in the model would be great

Is it normal for the baseline contribution to hit zero more often than being above 0?

@lorenze3 Please let me know if you come up with anything! I found that setting more informed priors (namely using the below `custom_priors`) to shrink the adstock `lag_weight` parameter for...