Skip to content

How a bank reduced CPA 37% by optimizing paid media spend using real-time predictive modelling.



increase in click-through rate (CTR) YoY


increase in conversion rate


savings in cost per acquisition (CPA)

Use Cases

  • Real-time segmentation
  • Predictive analytics
  • Paid media optimization
  • Lead generation


The bank’s loan department wanted to grow their portfolio through
digital marketing efforts. As part of that process, they needed to
measure the current performance of their preferred advertising
agencies. To support the analysis, they wanted to create an end-to-end
conversion funnel analysis report. The primary goal for the bank was to
optimize their paid advertising spend.




years in business



Celebrus was chosen because it’s a comprehensive data solution with the ability to close the digital data loop and provide full visibility of every customer journey from paid media referral to new  account opening and beyond. The bank also saw the value of using an enterprise real-time data hub for internal and external systems to reduce effort and cost.

Initially, Celebrus was purchased and deployed for analytical purposes. The retail bank then enabled the real-time capabilities of Celebrus to integrate with their advertising partners and take them to the next stage of their development. A propensity model was built to predict intent to apply for a personal loan by analyzing each visitor who starts to browse pages of the retail loan section of the channel. The model continuously scores in real-time, according to defined goals.

The model was built in a way that defined three segments – high, medium, and low propensity. The top segment had 12 times the average response rate and the bottom segment had 5% of the average response rate.

The bank integrated three preferred advertising vendors, including two local vendors who cover Facebook and Google DoubleClick Networks, and a third who manages Google Keyword Search and Yahoo Advertising. The Bank adopted their standard of advertisement tracking code for both campaigns and promotions, thus reducing deployment time and mapping/conversion effort in the analysis.

Using Celebrus data collection, one year of historical customer data was used from the website to compile start, visitor, device, page, and form interactions. These data points were used for prediction variables. The data was augmented with loan application data as a prediction target, reconciled with a unique identifier (in this case, mobile phone number which was included in both data sets).

In the final phase of testing, two additional sub-models were built: one for visitors being driven by vendor advertising, and the other for direct website visitors. In-session scoring was implemented using goals tied to score rules, with each goal only counted once per session.

The Celebrus Personalization Connector was used to build triggers that integrated with the advertising vendors’ systems when the score was reached. Trigger rules were configured for low, medium, or high score based on session value metrics. Score-based segment information was passed to advertising platforms using scripts within the actions, enabling the bank to use a different advertising strategy for each segment.

For the low score segment, the bank didn’t spend any budget on retargeting. For the medium score segment, they spent less cost per thousand impressions (CPM) and ran the ads for a shorter duration. For the high score segment, they spent more on CPM and increased deployment duration. The advertising agencies handled the creative elements of the projects in line with the bank’s instructions, derived from the model decisions.


The main purpose of the project was to optimize paid advertising spend for the bank. After a 3-month pilot run, the results were impressive.


The main purpose of the project was to optimize paid advertising spend for the bank. After a 3-month pilot run, the results were impressive. With their targeted advertising approach, fueled by data-driven segmentation thanks to Celebrus, the bank realized a 4.6x increase in Click Through Rate (CTR) versus the previous year. They also achieved a 1.6x increase in Conversion rate and 36.6% savings in Cost Per Acquisition (CPA).

In addition to the massive improvements in paid media optimization, the bank uses comprehensive Celebrus data to benefit lead generation and telemarketing efforts. For example, when a visitor has submitted the loan application online, the bank adds them to a “completed” segment which is then used as a conversion signal pool to find similar audiences in the vendor’s database. Additionally, many visitors choose to leave their mobile number and wait for the bank to contact them. The bank leverages scoring to set a contact priority and unique conversion KPIs for each segment to improve the effectiveness of their telemarketing team.


portrait-happy-woman-with-digital-tablet 1

This bank did it, and you can too!

Celebrus is the radical data solution that uncovers the deepest insight to reveal true customer context and identity - with a single line of code!

Finally solve gaps in data, identity, and connectivity with full compliance to elevate your marketing and personalization efforts and explode revenue. 

Connect with us today to experience the power of Celebrus for yourself!