If you’ve worked in mobile AdTech for longer than a week, you’ve likely been pitched by an agency or ad platform that claims to have machine learning algorithms or AI-based campaign automation.
This has become the differentiator-of-the-day over the last couple years, and I always get skeptical when every vendor is suddenly pitching the same thing.
I always wonder, who cares if AI is optimizing my campaigns or if it’s a team of monkeys, as long as they deliver ROAS. And if ML-based optimization means you cut your overhead and lowered your fees, then I’m all ears. But this is obviously never the case.
So naturally, I was happy to come across a case study on MobileDevMemo by Jacques Frisch, Director of Digital Marketing at Glovo. Jacques outlines how they approached a common problem of allocating a limited budget while optimizing for ROAS, and how they automated this with ML algorithms.
“When defining and managing quarterly and monthly digital marketing budgets, each new launch adds more variables to the equation. Each new city launched means your total budget is being broken down further. Allocating budgets across multiple combinations represents an approach known as Multi-Armed Bandit (Robbins, 1952). It got its name from the famous one-arm bandit slot machines and it describes the problem each Las Vegas gambler faces: which machine gives the highest return of investment for my budget?”
Read the full case study on MobileDevMemo