E EREACE
Back
Improve margin and mixAdvertising Agency / AdTech - Marketing and Advertising

Real-Time Bidding (RTB) and Conversion Prediction in an Advertising Agency

A digital media agency manages programmatic campaigns and must decide in under 20 milliseconds whether to bid to show an ad to a user, based on their real probability of converting.

Estimated annual impact on EBITDA
+€2.60M
Agency managing €20M of programmatic spend. Illustrative example with indicative figures: replace them with your own company figures.

Where the money comes from

Less spend on impressions that do not convert
+€2.20M
More conversions on the same budget (variable fee)
+€700k
System cost
-€300k
Annual EBITDA impact
+€2.60M
Adds profitReduces profitSystem cost

What to do now

  1. 1Agree with the client on the conversion that is worth money (purchase with margin, not sign-up).
  2. 2Train the model with bidding logs and incorporate the value per conversion.
  3. 3A/B test against the current bidding strategy with the same budget.

For your committee

One page with the decision, the impact, the risks, the steps and the KPI to track.

The print dialog opens: choose "Save as PDF".

Watch out: more volume is not always more profit

Optimising for cheap conversions can bring low-value customers or customers who return products. Bid according to the expected customer value (margin and LTV), not just the probability of conversion.

KPI for the committee

Return on ad spend (ROAS) in margin, not in sales.

Detail for your data team

Proposed technique: XGBoost

Why: XGBoost is the gold standard for large-scale structured tabular data. It learns from the errors of previous models sequentially to reach the highest possible accuracy.

Cost of getting it wrong: Bidding on users who never buy exhausts the client's marketing budget with no return.

Data needed: DSP / Auction Logs: History of billions of impressions, clicks and conversions.; User Context: Device, operating system, time, location, browsing history and website category.

The Ereace system

Test decisions with synthetic people before you test them with real ones.

This tool helps you decide with numbers. Before you invest, understand, test and rehearse the decision with the people involved: your customers, your team or your committee.

Understand
QualiSynth

Before you invest, find out what your customers think, need or reject about the initiative.

Test
StrataSynth

Put the offer, the message or the journey in front of synthetic people who do not always follow the happy path.

Train
ArenaSynth

Rehearse the committee presentation or the vendor negotiation against synthetic decision-makers.

See all Ereace products

About this tool. It is free and made by Ereace, an AI-native product studio and human intelligence ecosystem: it connects real human signals, synthetic people and the systems built around them, so teams can understand, test and act on human behavior before decisions reach the real world. About Ereace

Comments or suggestions? info@ereace.es