Compliance
Data Product Identity Resolution

Redica Systems resolves business entities to improve quality and compliance for life sciences

Building a globally unique Redica ID across 10 million pharmaceutical records, resolving manufacturing sites, investigators, and distribution centers from 50+ agency sources.

"Redica ID is a key component of our data and it is a value proposition to our customers. We are very serious about it and want to ensure we’re doing everything possible to set it as a global standard."

Arijit Saha, Chief Technology Officer
Redica Systems

Customer image
10M → 330K
Raw records resolved to golden Redica IDs
>90%
Accuracy improvement vs prior rule-based approach
50+
Source Systems
Background

Redica Systems is a data and analytics company in the life sciences sector, helping pharmaceutical and medtech clients improve quality and compliance. They analyze inspection reports, regulatory documents, and data from global health agencies, all without standardized identifiers, to generate meaningful compliance intelligence.

Challenge

With 10 million raw records from global health agencies, spanning manufacturing sites, investigators, and distribution centers, each source uses different identifiers, formats, and address conventions. Building a persistent, globally unique Redica ID required resolving entities across all sources at scale, with accuracy high enough for regulatory and patient safety decisions.

Solution

Redica Systems built a three-layer pipeline around Zingg, pre-processing reduces raw volume, Zingg handles the hardest matches that rules can’t, and domain-specific post-processing finalizes the Redica ID. Setup took just two engineering sprints.

  • 10 million records pre-processed to 1 million, Zingg further resolves to 350–400K clusters
  • Domain rules in post-processing finalize at ~330K golden Redica IDs
  • Human-in-the-loop review integrated for edge cases at each stage
"We spent a couple of sprints on Zingg, just to set it up and quickly get it running. Out of the box, the benefit we saw was good enough for us to get started."

Arijit Saha, Chief Technology Officer
Redica Systems

Results
  • Redica ID established as a persistent global identifier across the pharma industry, a key product differentiator
  • Pipeline runtime reduced from 5-6 hours to 40-45 minutes, running twice a week with plans for event-driven incremental processing
  • Inspection, supplier, and regulatory monitoring intelligence now built on a reliable golden record foundation
  • Human-in-the-loop workflow integrated for edge cases, with automation and review working together
Platform
Snowflake
Edition
Enterprise
Customer
Redica Systems
Full Transcript
Read the complete transcript
15 min read
→
FULL VIDEO
Watch the complete interview
→

See how Zingg powers Master Data Management at scale, from millions to golden records.

See how it works →