Cetelem: how to get to the right persona by combining machine learning and 1st party data?

Bidding on accepted credit requests instead of raw leads in Google Ads. Transformation rate up 35%, accepted leads up 40% and CPA 37% lower.

SEA

Measurement

AI & Automation

blue2purple - Woman with curly hair on the phone beside a window, holding a camera lens

35%

higher transformation rate from request to acceptance

40%

more accepted leads in conversion volume

37%

lower CPA than before the bidding change

client

Cetelem

Pillar

Data & ROI

short sumary

A credit lender whose conversion funnel breaks in two, an online credit request followed by a contract signed offline, was collecting more and more leads that failed the first automatic acceptance filter. blue2purple registered a second conversion in Google Ads, acceptance rather than submission, so machine learning could learn what separates the two groups. The transformation rate rose by 35 percent, the conversion volume of accepted leads by 40 percent, and the CPA came in 37 percent lower than before the change.

This advertiser is active in the financial sector, with their core business being all types of credit loans, car, renovation and others.

The specificity of this industry is related to the challenges they face regarding strict GDPR regulations, as well as technical difficulties inherited from a historic way of work. Those technical difficulties are strongly linked to closing the loop between an online credit request, a lead, and the actual contract, which is signed in a classical, offline way.

The conversion funnel is thus split over both online and offline channels

A potential customer first has to submit a credit request online. Once that is submitted, there is a first layer of qualification: if this person has a history of debts with the Belgian National Bank, or shows other signals of being a risk for giving out a loan, they are automatically refused. If they pass this first automatic filtering, they are allowed to actually request a credit loan online, which is sent via postal mail for signature. The rest of the process happens offline, meaning there is no way of identifying the transformation rate from requesting a credit to actually signing the contract and becoming a client.

For this client the business objective is to find new customers who are qualified in terms of reimbursement capabilities.

Over the years, a steady increase of incoming visitors applying for a credit request, which was the primary conversion, was noticed, but not necessarily passing through the first acceptance filter. This means machine learning is of extreme importance in order to identify the most compatible audiences on SEA. In other words, the focus needs to be put on the potential clients who will already pass through this first automated acceptance process.

To face this challenge and focus on the quality of leads rather than on a quantity of users entering the conversion funnel, the way the bid strategies were set up in Google Ads had to be adapted.

Two conversions were therefore registered as the main goal:

People submitting the credit request form.
People being accepted automatically for said credit request.

This resulted in the algorithm being fed with much more information than before, so it could really understand both groups and find out what differentiated them. That way, the most valuable clients were more easily identified and captured by Google Ads.

Transformation rate. The transformation rate, from sending a credit request to being accepted, increased by a whopping 35 percent.

Accepted leads. The conversion volume of accepted leads increased by 40 percent.

Cost per acquisition. This led to a CPA which was 37 percent lower than before the change was made in the bidding strategy.

Pushing the bidding strategy in a specific direction really showed off in the results.

What our clients say.

Alina BuckE-Commerce Manager

Strategy & Inisghts

Media Activation

Data Intelligence

An extension of the in-house team

What I appreciate most in our day-to-day collaboration is how straightforward and transparent the blue2purple team is. Campaigns are proactively optimised, questions are answered quickly, and even on short notice requests I can rely on a fast and thoughtful response. It feels less like working with an agency and more like working with an extension of our own team.

Leander SaileHead of Digital Marketing

Strategy & Inisghts

Media Activation

Data Intelligence

Media that answers to business goals

"In blue2purple, we've found a partner that doesn't treat digital media and performance marketing as an end in itself but consistently focuses on our goals. What makes the collaboration so valuable to us is the combination of strategic thinking and reliable execution. We receive honest recommendations instead of off-the-shelf solutions, and on every project, we can feel that our success is the team's own ambition too."

Quentin Ginoux

Strategy & Inisghts

Creative Content

A partner that challenges assumptions

At Cash Converters Belgium, we have worked with the MMKM team (now blue2purple) for several years and have always valued their strategic vision, their ability to challenge assumptions and to keep evolving their recommendations. We are excited to see what this new chapter has in store!

Margaux PierresCoordinatrice Marketing & Communication

Strategy & Inisghts

Media Activation

Creative Content

A social strategy that feels like Färm

"Our biggest challenge was creating content for all of our stores, each with the right social media codes. MKKM, now blue2purple, understood the essence and values of Färm and translated them into a strategy that feels like us. Creative, responsive support that we rely on every day to grow our community."