Marketing measurement
Where does the next euro go?
Marketing mix modeling built to allocate budget: Bayesian MMM, incrementality, response curves and budget allocation, deployed as a system your team runs on a monthly cadence.
Spend on the horizontal axis, incremental revenue on the vertical. The band is the model's uncertainty. The distance between today's spend and saturation is the headroom the allocation buys, or the money it stops wasting.
Play with the curveWhat this usually looks like
- Attribution and MMM disagree, and nobody can say which one to act on.
- The model reports ROI by channel, but the budget meeting still runs on last year plus ten percent.
- A model was delivered once, as a deck. Nobody has rerun it since.
- Finance and marketing are arguing about incrementality with no shared definition of baseline.
What you get
A calibrated MMM
Adstock and saturation fitted per channel, with priors that hold up when a channel goes dark. Uncertainty reported, not hidden.
An allocation you can act on
Marginal ROI equalised across channels under real constraints: minimum spends, contracted commitments, agency lead times.
A monthly operating cadence
Refresh, review, reallocate. The model earns its keep by being rerun, not by being right once.
The handover
Code, documentation, drift checks and the training to run it without me.
Selected work
Marketing Science
Consumer healthcare marketing mix model & budget optimizer
Proprietary Marketing Mix Model with budget optimization replacing intuitive allocation with data-driven decision making across multiple countries and touchpoints.
Media budget set from marginal ROI across 10+ countries; marketing and finance on one number
Marketing Science
CLV-driven acquisition & budget allocation
Predictive CLV modeling combined with lookalike audience optimization to shift acquisition from volume metrics to value-based targeting.
Acquisition budget targeted on predicted subscriber value instead of installs
Marketing Science
Automated credit decisioning system
Machine learning-powered credit decisioning system leveraging alternative data from social media and digital footprints combined with traditional credit data to improve risk assessment accuracy and speed.
Decisions 10x faster, operating cost ↓60%, default prediction +25%
Try the mechanics
Adstock Calculator
Model carryover effects in marketing using geometric decay.
Hill Function Explorer
Explore saturation curves from C-curves to S-curves.
Response Curve Explorer
Visualize marketing response curves and efficiency zones.
MROI Optimizer
Compare revenue maximization vs efficiency strategies.
Baseline vs Incremental Sales
Understand baseline demand vs marketing-driven lift.
Depth
Oct 15, 2024
MMM Implementation Guide: From Data to Production in 5 Phases
A structured breakdown of deploying an MMM solution, covering project initiation, data foundation, modeling, and operationalization based on real-world implementation patterns.
Aug 21, 2025
Practical optimizer scenarios in MMM: A step-by-step guide
Walk through real-world MMM optimization scenarios using Mixed Integer Programming. See how to discretize response curves, formulate constraints, and solve practical reallocation problems with actual numbers.
Mar 7, 2025
Causal Identification, Uplift, and Contribution: The Three Pillars of Marketing Mix Modeling
Understanding the critical distinctions between causal identification, uplift, and contribution—and why conflating them leads to bad marketing decisions
Jun 3, 2025
Understanding Diminishing Returns: The Five Zones of Marketing Efficiency
Master the economics of marketing spend through the five zones of efficiency, from minimum threshold to market saturation. Learn when to scale, optimize, or reallocate budget for maximum ROI.
Sep 27, 2026
Optimiser Meta sur la Lifetime Value : du modèle pLTV à l'expérimentation
Comment transformer une prédiction de Lifetime Value en boucle d'optimisation Meta, instrumenter l'expérience et mesurer la valeur incrémentale réellement créée.
Sep 20, 2026
Meta Conversions API : construire un pipeline de tracking fiable en production
Architecture Pixel et Conversions API, event_id, déduplication, idempotence, watermark et monitoring : comment industrialiser un pipeline Meta réellement fiable.
How it starts
Diagnostic first, build second.
01 · Decision System Diagnostic · From €12,000
Three months, one critical decision. We establish the baseline, test whether MMM is the right instrument, and design the decision system around it. You get evidence, a target architecture, and a costed roadmap.
02 · Design and build
The model, the allocation logic, the pipeline, the review cadence. Scoped from the roadmap, priced on the engagement rather than by the day.
03 · Operate and hand over
Monitoring, drift controls, documentation. The goal is a system your team owns.