Nederlands 
English No black box.
Marginal Journey Simulation.
Most measurement solutions pick one: either attribution on customer journeys, or Marketing Mix Modeling on weekly totals. Datafy does both, and has the two check each other. We call that combined approach Marginal Journey Simulation, developed by Datafy. The result is not a credit split after the fact, but the answer to the only question that matters in a budget decision: what does the next euro return?
Attribution answers the wrong question
Classic attribution, from last-click to the most advanced data-driven models, divides the credit for realised conversions across channels. But in a budget round nobody asks who deserves the credit. The question is: where does the next euro pay off, and where does the last one no longer?
| Method | Answers | Usable for a budget decision? |
|---|---|---|
| Last-click / position rules | Which touchpoint is the conversion assigned to? | No, overvalues the last touch, ignores everything before it |
| Data-driven credit split | How do we split the credit “fairly” across the customer journey? | Limited, a fair split of yesterday says little about tomorrow's spend |
| One-off MMM study | What did each channel contribute on average over the past year? | Limited, average return ≠ return of the next euro, and the report ages |
| Datafy | What changes in revenue if you shift one euro, per channel, campaign and creative? | Yes, this is the budget question, recalculated weekly |
Two engines, one answer
Attribution on individual customer journeys
Datafy does not work with channel totals but with the actual journey of every visitor: every impression, click, TV spot and visit, in sequence. For each touchpoint the model calculates what would have happened without that moment: fewer visits, fewer returning visitors, a lower conversion probability? The difference, set against the cost, is the marginal return of that touchpoint. Added up across all journeys, this produces the return per channel, campaign and creative.
Econometric model across the entire mix
Brand effects from TV, radio and online video do not show up in an individual click today, but they do in the weekly totals of the months that follow. The econometric model explains your revenue from media spend, season, weather, price and market factors, and so separates what your media did from what the market was already doing. This is the engine behind scenario and budget planning.
The engines check each other
The long-term model corrects the customer-journey attribution for effects you cannot see in individual journeys, and the customer-journey outcomes feed the long-term model as an extra explanatory factor. Where most solutions pick one lens, Datafy forces two independent lenses to arrive at a consistent picture. If they diverge, that is the signal to zoom in, before any budget moves.
The four steps form one cycle.
The two engines deliver analysis and interpretation, the weekly recommendation delivers the decision, and the validation delivers the evaluation. Together they form a closed loop that runs again every week, and improves itself.
Do not believe. Test.
A model that never has to prove itself is an opinion with a dashboard. That is why every Datafy model is permanently held to account by reality. Put this page next to that of any other vendor and ask one question: who dares to place their weekly forecast openly next to the actuals?
Forecast next to actuals, every week
The model predicts next week's revenue, and a week later places that prediction next to what actually happened. That test is visible to everyone in the platform, even when the outcome disappoints.
Tested on data the model never saw
Predictive power is assessed on periods held out of the model build, the standard from statistics that prevents a model from merely parroting the past.
Assumptions on the table
Every model rests on assumptions, ours included. Instead of hiding them, we write them out in our methodology note. That way your analytics team can assess them before you steer on the outcomes.
Built by a mathematician, not by a marketing agency
Datafy was developed under the leadership of Dr. Auke Pot, who holds a PhD in mathematics (stochastics) from the Vrije Universiteit Amsterdam under Prof. Dr. Ger Koole. Customer journeys are stochastic processes and budget allocation is a mathematical optimisation problem, precisely the field in which he earned his doctorate. That background shapes the method: every calculation step in the platform is mathematically defined, every assumption explicit, and every result testable.
One design decision per article, defended by the founder
Every choice in Marginal Journey Simulation has a reason, and we explain it publicly. Three examples from the series:
Why marginal, not average
The average return answers an accounting question; the budget question is about the next euro. Why that difference shapes the entire model design.
Why we simulate customer journeys all-or-nothing
Counting a touchpoint half does not exist in reality. What happens when you simulate, per journey, what would have happened without that moment.
Why we estimate conservatively
A model that is too enthusiastic costs the client money. How the estimation choices prevent outliers in the data from taking over the recommendation.
Appears as a technical series on LinkedIn, follow Dr. Auke Pot or the Datafy company page.
The methodology note: the full story, signed
For the reader who wants to go further than this page: a technical note written by Dr. Pot, with the formal definition of marginal return, the model assumptions explicitly numbered, the validation approach and a comparison with common attribution and MMM methods. Written for your data scientist, usable in any RFP.
What is in it
The marginal-return definition and how it is calculated per customer journey · the assumptions, explicitly numbered · the weekly validation cycle · how the method relates to last-click, data-driven attribution and classic MMM.
Receive the note
Leave your email address and receive the methodology note as a PDF, together with an invitation to go through it in a 30 minute session with your analytics team.
Put our method next to what you use now
In a 30 minute demo we show on real data how the two engines arrive at one recommendation, and where our model hit or missed its own forecasts.