#mmm

5 notes tagged “mmm”.

• Evaluating a marketing mix model (and whether Robyn/Meridian are biased)Assume any MMM is wrong until it passes three checks — parameter recovery on simulated data, out-of-sample forecasting of a period with real budget changes, and agreement with lift tests; open-source Robyn and Meridian are not rigged for Meta/Google, but most MMM vendors are thin wrappers around them.
• Knowing if your ecommerce brand is winning — CTC's three pillars (source of truth, shared target, execution)Luke Austin's operating framework for ecommerce growth — one trusted source of truth joining financial, marketing, order and calendar data; one shared definition of success (contribution margin at the top, daily targets laddering down to every channel); and relentless execution through calendar, ad, email and creative workflows plus MMM/geo-holdout testing — built in that order.
• The measurement stack — last-click attribution, incrementality and MMM togetherWhy app advertisers need both deterministic last-click attribution (for platform optimisation and daily decisions) and incrementality testing (for budget allocation), where MMM fits, and how to reconcile them against top-line results.
• UA team and data stack by spend level — what to staff and what not to buildAnas Maqsood's view of subscription-app UA teams — ExpressVPN's ~$8–9M/month app setup run by 3–4 performance people plus creative, BI and CRM pods; a 3-person team at $50–200K/month; and what not to build under $50K/month (MTA, MMM, data warehouse, CDP, in-house paywall tool).
• When last-click attribution is good enough (and when to invest in incrementality)For small, performance-driven advertisers on one or two channels, last-touch attribution is often ~85% as good as experiments and better than a bad MMM; invest in incrementality tests as spend, channel count and brand effects grow.