Forecasting for Marketing

Units and bites

1. Unit 1·4 bites·About 12 min

   Why marketers forecast

   Budgets, targets and the question "what do we get if we spend more?".

   1. Forecast, target and plan

      Three numbers that get mixed up in marketing meetings, and why to keep them apart.

      3 min

   2. What marketing can forecast

      Traffic, leads and sales can be estimated; going viral can't.

      3 min

   3. Start with the baseline

      What would arrive without any campaign: the starting point of every marketing forecast.

      3 min

   4. Forecasting for the budget meeting

      Preparing numbers you can defend in front of finance.

      3 min
2. Unit 2·4 bites·About 12 min

   Forecasting traffic and leads

   Reading search trends, seasons and the funnel to estimate how many will come.

   1. Search demand and Google Trends

      Using search interest as an early signal of demand, and where it stops working.

      3 min

   2. Seasonality in marketing

      Ramadan, Harbolnas, the new school year and year-end in your traffic data.

      3 min

   3. Funnel-based forecasts

      From visitors to leads to customers, one conversion rate at a time.

      3 min

   4. Organic vs paid

      Why organic and paid traffic need separate forecasts.

      3 min
3. Unit 3·4 bites·About 12 min

   Forecasting campaign results

   The maths of impressions, clicks and conversions, and media costs that rise in peak season.

   1. Campaign funnel maths

      Budget ÷ CPM × CTR × conversion rate: a campaign forecast in one line.

      3 min

   2. Ranges from past campaigns

      Using your best and worst past campaigns to build a realistic range.

      3 min

   3. Media costs in peak season

      Why CPMs rise before 11.11, 12.12 and Lebaran, and how to build that into the forecast.

      3 min

   4. New channels without history

      Forecasting a channel you've never tried with a small test and benchmarks.

      3 min
4. Unit 4·4 bites·About 12 min

   Budget and channel planning

   Diminishing returns, incrementality and the idea behind marketing mix modelling.

   1. Diminishing returns

      Why the hundred-millionth rupiah in a channel returns less than the first.

      3 min

   2. Incrementality

      How much the ads actually caused, not what would have come anyway.

      3 min

   3. Marketing mix modelling, without the code

      The idea behind MMM and open-source tools such as Meridian and Robyn, for those who read the results.

      3 min

   4. Splitting the budget across channels

      Allocating budget on the marginal forecast, not last year's habit.

      3 min
5. Unit 5·4 bites·About 12 min

   Scenarios and uncertainty

   Best, base and worst cases, and how to present them.

   1. Three scenarios

      Building best, base and worst cases from assumptions you can check.

      3 min

   2. Which assumption matters most

      Changing one assumption at a time to find the one that moves the result most.

      3 min

   3. Presenting a forecast

      One slide that shows the range, the assumptions and the risks without confusing anyone.

      3 min

   4. AI for scenario drafts

      Asking AI to draft scenarios and challenge your assumptions, then checking its maths.

      3 min
6. Unit 6·4 bites·About 12 min

   Tracking against the forecast

   Pacing, variance analysis and updating the forecast mid-flight.

   1. Pacing

      Checking mid-month whether a campaign is on track.

      3 min

   2. Explaining the variance

      Breaking a forecast miss into volume, media price and conversion.

      3 min

   3. Reforecasting

      When a forecast needs updating, and why not every day.

      3 min

   4. Learning from each forecast

      Recording assumptions and results so the next forecast is closer.

      3 min

Read while you wait

Guides from the Datamew team, free on the web today.

AI fundamentals

How to Write a Good Prompt: A 5-Part Framework for Work

A good prompt gives the AI five things: context, task, input, format and limits. It says who the work is for, what to do, which material to use, how the answer should look and what to avoid. Then you check the answer and ask a follow-up.

7 min read

AI from zero

How to Learn AI From Zero, Without Coding

Yes, you can learn AI without writing any code. To use AI well at work you need four things: a basic idea of how it works, a sense of where it fails, practice with one or two free tools, and the habit of checking every answer before you use it.

8 min read