What challenges did epaka.pl face before AI implementation?

Data was fragmented across local servers and rigid SQL databases. Reports often arrived two to three months late, slowing campaign decisions and creating inconsistent metrics across departments.

What was the impact of the AI solution?

Reporting freshness improved from months to minutes or real time. The company says it could spot performance dips within an hour and that the data foundation contributed to a 153% rise in customer orders year-over-year since 2024.

Source

GCPEvidence: Medium50/100

epaka.pl: BigQuery + Looker real-time analytics and BigQuery ML churn prediction

Use case typeData platform modernizationUpdated 1 day ago

epaka.pl built a unified data platform with BigQuery and Looker for real-time insights. The company migrated fragmented data from local servers and rigid SQL databases into BigQuery and used Looker for reporting and analysis. epaka.pl is planning BigQuery ML models to predict churn and connect risk scores back to CRM workflows.

Organization: epaka.pl
Industry: Logistics
Location: Poland
Published: July 2026

Reported outcomes

Reporting freshness: +97%

Other quantified impact

Customer orders year-over-year: More than 153% higher

Strategic outcomes

Better decisions & insightEnabled real-time operational decision-makingOther strategic outcomeCreated a single source of truth for revenue and performanceCustomer experience & trustImproved confidence in business metrics across departments

Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Reporting freshness: 97% increase

Google Cloud Customer StoriesJul 31, 2026Customer storyExplicit claimMedium evidence strength

Reports often arrived two to three months late

Normalized claim

Customer orders year-over-year: 153% increase

Google Cloud Customer StoriesJul 31, 2026Customer storyExplicit claimMedium evidence strength

a 153% rise in customer orders year-over-year since 2024

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks

Customer: epaka.pl
Provider: GCP
Maturity: Unknown
Linked source: Google Cloud Customer Stories

No explicit deployment-stage evidence found.

Customer identity supportedSource describes one deploymentMaturity evidence evaluated

Primary read

Use case focus

Showing 2 of 2

1Data platform modernization
2Customer targeting

Data was fragmented across local servers and rigid SQL databases.
Reports often arrived two to three months late, slowing campaign decisions and creating inconsistent metrics across departments.

epaka.pl migrated order data from online channels and more than 300 offline franchise locations into BigQuery as a unified data foundation.
Looker provides real-time dashboards and analysis, while BigQuery ML is being developed to predict churn from transactional and historical behavior data.
The solution is connected back into CRM so sales teams can act on churn risk insights.

Technologies

BigQuery Looker BigQuery ML

Reporting freshness improved from months to minutes or real time.
The company says it could spot performance dips within an hour and that the data foundation contributed to a 153% rise in customer orders year-over-year since 2024.

Sources & evidence1

Evidence: Medium50/100Evidence strength