Great forecasting is an exercise in execution as much as it is in modeling. How CTC combines proprietary data science with daily operational discipline to make profit predictable.
The point of a forecast is not to predict the future perfectly. You will be wrong. The point is to understand where you are wrong so quickly that you can course correct before the damage is done.
If on the second or third day of the month you can figure out which input on your model is too high, too low, or unexpected, you have time to fix it. If you get to the end of the journey and realize you're off course, there is no time to fix it.
“Since all models are wrong, the scientist must be alert to what is importantly wrong. It is inappropriate to be concerned about mice when there are tigers abroad.”George E.P. Box, Statistician
Success in forecasting means two things:
Close approximation of reality. Plus or minus 10% to target is an effective forecast. It is equally damaging to miss to the upside by 40% as to the downside. You can die of indigestion as much as starvation.
Early detection of deviation. A great model has an expectation of every input, every day, allowing you to course correct along the way. That is what makes a model useful.
Focus on tigers, not mice. Bad gross margin is a tiger. Bloated OpEx is a tiger. The next headline variation on your ad creative is a mouse.
This is not a spreadsheet that spits out a number. This is an entire system for managing and growing your ecommerce business. It involves four steps that transform qualitative planning into daily operational precision.
Design the 12-month marketing calendar. Every promotion, launch, and cultural moment.
Three proprietary data science models predicting spend, revenue, and retention.
Every dollar, every day, every campaign laddering up to the financial goal.
Daily cadence. Track vs. expectation. Identify. Act. Course correct.
Revenue is never linear. In almost every business, moments drive outsized performance across the calendar. Black Friday is obvious. But every brand has at least one other natural peak built into the cultural calendar, and the best brands manufacture additional ones.
These peaks work because of how ad platforms price efficiency. When you drive unexpected increases in conversion rate through promotions, product releases, or cultural moments, you arbitrage Facebook's auction formula. Your best ROAS day is never an evergreen ad. It's a moment of urgent purchase demand where conversion rate spikes and you get outsized value return.
So the process starts here: build a 12-month marketing calendar with every email, promotion, product release, and cultural moment plotted. Identify the peaks, fill the valleys, and design the revenue shape before a single number enters a model.
We build customer-centric, cohort-specific forecasts. Not channel trends, not year-over-year extrapolation. Every forecast is built through the customer file, because cohorts are the atomic unit of ecommerce.
Analyzes the relationship between media spend and new customer acquisition efficiency (aMER) over time. We absorb all of a brand's historical data, then an individual human cleans it for anomalies: unrepeatable events, product launches, and one-time spikes that won't recur.
This produces a reliable spend-to-efficiency curve that predicts new customer revenue at any spend level, giving us the first building block of expected monthly revenue.
Models the retention curve of your customers over time to predict returning customer revenue. We track cohorts monthly, measuring active vs. lapsed customers. Lapse is defined at the point where 80% of second purchases have occurred.
A growing active customer file predicts revenue growth. A shrinking one signals trouble, no matter how large the total file looks. Many of those customers are lapsed and dead. They are not coming back.
Quantifies how marketing moments (emails, product releases, promotions) affect both new and returning customer revenue on any given day. This is what connects qualitative planning to quantitative output.
Your marketing calendar becomes a mathematical input, not just a content schedule. Each event carries a measured performance multiplier derived from historical data.
These three models produce a monthly expectation of spend and revenue. We then layer in all historical costs (variable and fixed) to build a full P&L-level forecast.
Using MMM, we allocate the monthly media expectation into channel-level, campaign-level daily targets that ladder up to the overall financial goal of the organization.
We provide a 24-month P&L-level forecast all the way down to net profit. But the model is built around driving contribution margin because it represents the closest proxy to profit where we control all the variables.
There are only ever two kinds of problems to solve: volume or efficiency. Every deviation from forecast falls into one of these categories, and each has a specific set of corresponding actions.
↑ Priority · Forecast output hierarchy · ↓ Granularity
Monthly goals are broken down into daily expectations in every channel. Every ad dollar, every email send, and every campaign has a target. We also model the exact amount of creative production required, so your team can align the creative supply chain to the plan.
On the first day of the month, you see exactly where you are relative to expectation, every single day:
The daily operating cadence that turns forecasts into outcomes.
Each morning, plot actual performance against daily expectations. Revenue, spend, MER, contribution margin, CAC, orders.
Identify the deviation. Is it volume or efficiency? Diagnose the root cause. Loosen caps, shift budget, adjust creative.
The Prophit Engineer takes corresponding action while there's still time. Course correct in days, not weeks.
Every campaign across every channel has a daily spend target, projected ROAS, and actual performance. Moments are tagged so you can see the effect of each marketing event in real time. Deviations are flagged immediately.
We forecast the exact number of ads required for each marketing moment, aligning creative production to the spend plan. Your team knows exactly how many videos and images are needed, for which moments, and by when.
Every morning, your Prophit Engineer follows this framework. No guessing, no hoping, no end-of-month surprises. You will feel like you begin every day with clarity of where you are relative to your goals and what we are doing to help make sure you reach them.
What is the data showing us? Yesterday's actuals vs. daily expectations across every metric and channel.
What does that mean? Is this a volume or efficiency problem? Which input is off? How material is it to the monthly target?
What are we going to do about it? A specific, corresponding action taken immediately. Not a meeting scheduled for next week.
The only thing we know to be true of every model we've ever created is that they are all wrong to some degree. The power in our system is how quickly you can recognize when you are off course, and that the Prophit Engineer drives you back on course with corresponding action. Here are the results.
CTC Core Methodology Series — Forecasting v1.0
