How Millennium bcp Uses BigQuery ML to Boost Loan Conversion Rates

Millennium bcp, Portugal's largest private bank, used Google Cloud's BigQuery machine learning tools to build predictive audience models for personal loan campaigns. By segmenting existing customers by propensity to borrow, the bank dramatically improved both owned and paid media performance. The result was a 2.6x higher conversion rate and a 36% drop in cost per acquisition.

Impact

2.6x higher

Conversion rate lift — owned media (BigQuery audiences vs. other first-party audiences)

2.4x greater

Conversion volume lift — owned media (BigQuery audiences vs. other first-party audiences)

2x (doubled)

Conversion volume lift — paid media

1.9x higher

Conversion rate lift — paid media

36% lower

Cost per acquisition (CPA) reduction

Challenge

Millennium bcp's reliance on in-branch processes for personal loan applications limited scalability and failed to meet modern customer expectations. The bank needed a way to digitally target only eligible existing customers with personalized loan offers at scale.

Solution

The bank's in-house digital marketing team built BigQuery ML-powered predictive models to segment existing customers by loan propensity, then activated those audiences across owned and paid channels via Google Analytics 4, Firebase, and Display & Video 360.

Tools & Technologies

What Leaders Say

We've been working with Google Cloud's technology for over six years. It has been a significant contributor to our technological advancements, driving innovation and challenging us with the latest trends. We're committed to remaining early adopters, exploring new features and uncovering opportunities, so as to expand our business.

Diogo Bernardo, Digital Analytics Lead, Millennium bcp

Since 2019, we've leveraged first-party audiences in paid and offline media. In 2023, we powered up these audiences with BigQuery's machine learning, expanding our audience pool, boosting efficiency in media efforts, and achieving digital sales goals for personal loans.

Rita Carvalho, Digital Media Lead, Millennium bcp

There's an ongoing commitment to learning. We have a lot of curious people and we want to maximize the potential of the Google Cloud tools at our disposal and drive continuous innovation. As a result, the team has successfully transitioned from a traditional approach to a fully digital mindset.

André Correia, Head of Digital Marketing, Millennium bcp
Get the full context.

Sign up to read complete case studies, access detailed metrics, and unlock all use cases.

Full Story

Millennium bcp, Portugal's largest private bank by business volume, had long relied on physical branch visits for personal loan applications — a model that constrained scalability and failed to meet the expectations of increasingly digital-first customers. Clients were required to visit in person during limited hours and endure slow, manual processes. By 2023, the bank set an ambitious goal: meaningfully grow digital sales of personal loans while ensuring outreach was limited to existing customers, the only segment eligible to complete the digital loan journey.

To address this challenge, Millennium bcp's in-house digital marketing team — spanning media, copywriting, design, and analytics — turned to Google Cloud, a platform the bank had already been building on for over six years. The team leveraged BigQuery's machine learning capabilities to analyze the behavioral patterns of existing clients who had previously taken out personal loans. These insights powered predictive models that identified other customers with a high likelihood of doing the same, segmenting the broader customer base into three tiers of interest: low, medium, and high.

With these audience models in place, the team integrated the outputs into Google Analytics 4 to dynamically generate tailored audience segments. These segments were then activated across multiple channels — Firebase for personalized in-app messaging and Display & Video 360 for precision-targeted paid media campaigns. Critically, the entire solution was built on first-party data, ensuring full compliance with evolving privacy regulations while maintaining a high degree of personalization and relevance.

The results significantly exceeded expectations. In owned media, BigQuery-powered audiences delivered a 2.6x higher conversion rate and 2.4x greater conversion volume compared to other first-party audiences. In paid media, conversion volume doubled, conversion rates were 1.9x higher, and cost per acquisition fell by 36%. The project demonstrated that a fully in-house team, armed with the right data infrastructure, could execute a sophisticated, end-to-end digital transformation.

Today, Millennium bcp stands as a benchmark in data-driven digital banking. The bank continues to deepen its use of Google Cloud tools, with a stated commitment to remaining an early adopter of new capabilities. The success of this initiative has accelerated a broader cultural shift — from a traditional, branch-centric mindset to a fully digital, analytics-led approach to customer engagement.

Similar Cases

CC
Chipper Cash
95%+
selfie verification accuracy

Chipper Cash, a fintech serving over five million customers across Africa, deployed a Pinecone-powered facial similarity search system to detect and block fraudulent duplicate sign-ups in real time. The solution slashed identity verification latency from up to 20 minutes down to under 2 seconds, and reduced fraudulent sign-ups by 10x across all markets.

Financial ServicesGCGoogle CloudSSnowflake
SB
State Bank of India
64 million
app downloads

State Bank of India partnered with IBM to build YONO, a comprehensive mobile platform combining banking, financial services, and marketplace that achieved 64 million downloads and a USD 40-50 billion valuation.

Financial ServicesIAIBM API ConnectICIBM Consulting
NB
Norges Bank Investment Management
20%
weekly time savings per employee

Norges Bank Investment Management deployed Claude Enterprise to 600+ employees across all departments, achieving 20% weekly time savings on analytical and operational tasks. The $1.7 trillion sovereign wealth fund uses Claude for investment research synthesis, ESG compliance across 9,000 portfolio companies, and multilingual information processing. Business users can now prototype AI solutions independently without IT bottlenecks.

Financial ServicesCEClaude Enterprise
C
Campfire
3 days
reduction in monthly close time

Campfire embedded Claude into its accounting platform to automate monthly closes, bank reconciliation, and financial reporting. Customers now close their books 3 days faster, reconcile bank statements 90% faster, and generate reports 50% faster. Claude powers Ember, Campfire's AI chat interface for natural language financial queries.

Financial ServicesCAClaude API
N
nCino
3.5x
faster document filing

nCino, a cloud-based banking platform serving 2,800+ financial institutions, built domain-specific AI tools on Databricks and AWS leveraging 13 years of proprietary banking data. Their Banking Advisor delivers role-based AI insights natively within the platform, while Continuous Credit Monitoring automates risk alerts across the loan lifecycle. The result is 3.5x faster document processing and a shift from reactive to proactive portfolio management.

Financial ServicesAAWSSSalesforce
N
N26
70%
task automation in targeted processes

N26 deployed Claude via AWS Bedrock across 15+ internal use cases in its first year, automating up to 70% of tasks in targeted customer service processes and cutting manual processing by 50% across 24 European markets. New AI implementations now go from ideation to evaluation in 1–2 weeks.

Financial ServicesABAmazon BedrockCEClaude Enterprise
F
Fiserv
$10M
sla penalties avoided

Fiserv built safe, scalable AI automation on UiPath Platform with built-in governance, avoiding $10M in SLA penalties and onboarding 20,000+ QSR locations on schedule.

Financial ServicesUPUiPath Platform
RB
Raiffeisen Bank International
3–4x
average sql query performance improvement

Raiffeisen Bank International (RBI), one of Central and Eastern Europe's largest banking groups, migrated its fragmented analytics estate across multiple countries to Databricks SQL. The result was a 3–4x improvement in average SQL query performance, 30–40% faster time to insight for analysts, and a 5x reduction in analytics total cost of ownership compared to its previous cloud solution.

Financial ServicesDSDatabricks SQL