Use Case Intelligence Browse use cases
DB Databricks Manufacturing Global

HP Indigo

Data Lake / Data Warehouse Modernization · Predictive Maintenance · Real-time Analytics

HP Indigo's industrial print business was managing 3,500+ data volumes (~10TB) across hundreds of jobs spanning ERPs, manufacturing platforms, and field data sources, with critical data tracked in manual spreadsheets. Teams spent days tracing parts and analyzing data across disconnected systems, sometimes halting production while waiting for answers, and there was no single source of truth.

Read the original story Back to explorer
3,500+ data volumes (~10 TB) under management
Ad hoc requests replaced with instant natural-language answers via AI/BI Genie
Consumable traceability cut from 3 days to about 1 hour
Manufacturing yield improved from 60% to 92% via prediction model

Solution

HP Indigo is unifying more than 3,500 data volumes (~10TB) from ERPs, manufacturing platforms, field data sources, and previously-manual spreadsheets onto Databricks under Unity Catalog governance, replacing fragmented legacy warehouses. Lakehouse Federation covers data that still lives outside Databricks, while Unity Catalog provides end-to-end lineage that tracks consumables from manufacturing through customer-site consumption — collapsing a 2-3 day traceability process to 60 minutes. Databricks AI/BI and AI/BI Genie deliver trusted analytics alongside existing Tableau and Power BI, with Genie surfacing natural-language access on top of Unity Catalog-governed data using role-level security and simplified naming conventions. Delta Sharing distributes governed data internally, with plans to extend to external vendors. A first prediction model running on Databricks lifted manufacturing yield from 60% to 92%.

Data flow

More than 3,500 data volumes (~10TB) from ERPs, manufacturing platforms, field data sources, and previously-manual spreadsheets are migrating into Databricks under Unity Catalog governance, with Lakehouse Federation covering data that still lives outside the Lakehouse. End-to-end lineage links manufacturing, field, and customer data so consumables can be traced from the line through customer-site consumption. Tableau, Power BI, and AI/BI surface curated analytics to business users; Genie adds natural-language access on top of Unity Catalog-governed data with role-level security; Delta Sharing distributes governed datasets internally with plans to extend to external vendors. A first prediction model running on Databricks improved manufacturing yield from 60% to 92%.

Solution architecture

5 components · 2 layers
  1. Serving
    • Delta Sharing Governed data sharing inside HP Indigo with planned extension to external vendors
    • Databricks AI/BI Trusted, governed analytics layer running alongside existing Tableau and Power BI
    • Databricks AI/BI Genie Natural-language access to Unity Catalog-governed data with role-level security and simplified naming conventions
  2. Governance
    • Unity Catalog End-to-end manufacturing/field/customer data lineage and role-level security; tracks consumables from line through customer-site consumption
    • Lakehouse Federation Governs data that still lives outside Databricks alongside in-Lakehouse data

Architecture clues

  • AI/BI Genie alongside Tableau and Power BI
  • Delta Sharing for governed external-vendor sharing
  • Lakehouse Federation to govern non-Databricks data
  • Role-level security in Unity Catalog with simplified naming conventions
  • Runs on AWS
  • Unity Catalog lineage across manufacturing, field, and customer data

Evidence from the source

60% → 92% Manufacturing yield improvement with prediction models
Leveraging this prediction model in Databricks, we increased the yield from 60% to 92%.
With Unity Catalog, that process now takes just 60 minutes.

Related

Similar use cases

See all like this
DB Databricks Trackunit Manufacturing · Denmark Construction is one of the least digitized industries in the world, with stagnant productivity despite heavy IT investment. Internally, Trackunit had to handle 6 million connected machines generating 3 billion data… 3 billion data points processed daily Data Lake / Data Warehouse ModernizationPredictive Maintenance Agent Bricks / Mosaic AI · Databricks AI/BI · Databricks Data Intelligence Platform DB Databricks Amagi Media and Entertainment · Global Amagi supports 8,000+ streaming channels, 300+ distributors, and 26B annual ad impressions for 45% of the world's top media companies, but its legacy stack (Dataproc for batch, Snowflake for analytics, in-house… 15x faster time to market for new data products Data Lake / Data Warehouse ModernizationReal-time Analytics Databricks Genie · Databricks SQL · Databricks Serverless Compute DB Databricks National Australia Bank (NAB) Financial Services · Australia NAB had standardized on Databricks but its 300–400 data engineers were building 1,600+ Spark pipelines in inconsistent ways, with hand-written Spark and legacy SQL DMLs of 5,000–8,000 lines and some pipelines containing… 100% of Bronze pipelines on Spark Declarative Pipelines Data Lake / Data Warehouse ModernizationReal-time Analytics Databricks AutoCDC · Lakeflow · Lakeflow Spark Declarative Pipelines