Your achievements

Level 1

0% to

Level 2

Tip /
Sign in

Sign in to Community

to gain points, level up, and earn exciting badges like the new
BedrockMission!

Learn more

View all

Sign in to view all badges

SOLVED

How much model coverage is adequate?

1 Accepted Solution
Community_Admin
Correct answer by
Employee
Employee

The necessary amount of cost model coverage and revenue model coverage is qualitative and varies by portfolio; in general, the portfolio needs a reasonable number of bid units with cost models and revenue models relative to the portfolio budget. For example, a portfolio with a daily budget of $10,000 and only 10 bid units with models would not have enough coverage unless the portfolio contains only brand ads/keywords. If the same portfolio has several million bid units and only 1% cost model coverage and .05% revenue model coverage, it would not have enough revenue model coverage, but you may be able to increase the revenue coverage by setting reasonably high bids for the bid units that have cost model coverage to see if they subsequently earn revenue (thereby creating revenue models that help AdLens predict future revenue).

View solution in original post

1 Reply
Community_Admin
Correct answer by
Employee
Employee

The necessary amount of cost model coverage and revenue model coverage is qualitative and varies by portfolio; in general, the portfolio needs a reasonable number of bid units with cost models and revenue models relative to the portfolio budget. For example, a portfolio with a daily budget of $10,000 and only 10 bid units with models would not have enough coverage unless the portfolio contains only brand ads/keywords. If the same portfolio has several million bid units and only 1% cost model coverage and .05% revenue model coverage, it would not have enough revenue model coverage, but you may be able to increase the revenue coverage by setting reasonably high bids for the bid units that have cost model coverage to see if they subsequently earn revenue (thereby creating revenue models that help AdLens predict future revenue).

View solution in original post