Large-Scale Skills Data Integration for Construction

At a Glance

• Client: YFor
• Sector: Construction workforce technology
• Scope: Data extraction, structuring, and analysis across multiple industry data sources, with AI-assisted reconciliation
• Key capabilities: Automated data extraction, AI-based analysis, data reconciliation and matching
• Delivery: End-to-end data extraction, analysis, and reconciliation project, delivered through a government-backed digital transformation programme

About the Client

YFor is a workforce intelligence platform built for the construction industry. It helps employers manage skills, qualifications, and compliance across their workforce.

Background

Construction employers face increasing pressure to evidence workforce competence to regulators and clients. YFor’s platform supports this through structured skills data. To further strengthen their data, YFor wanted to benchmark and enrich their existing framework against the wider landscape of publicly available industry data from training organisations, regulatory bodies, qualification providers, and government sources.

The Objective

Extract, structure, and analyse data from relevant external sources across the construction skills landscape, then systematically compare it against YFor’s existing framework to identify opportunities for enrichment and validate coverage.

What I Delivered

I built automated software to extract and structure data at scale from a large number of external industry sources. The data came in many different formats, so the extraction required a combination of AI and automation techniques tailored to each source.

Once extracted and formalised, I compared the external data systematically against YFor’s existing framework using AI-assisted matching and reconciliation, identifying where the two aligned, where there were opportunities for enrichment, and where external data could add further depth.

The project also delivered practical outputs beyond the analysis that fed directly into improving the platform and supporting future development.

Outcome

• Data from across the construction skills landscape was extracted, structured, and delivered alongside reusable code so the process can be rerun as sources are updated
• The analysis validated the strength of YFor’s existing data and identified opportunities for further enrichment
• Practical deliverables fed directly into platform improvements and future feature development

“Liam delivered a complex data integration project for us with real skill and professionalism. He took the time to understand our domain, worked independently, and produced practical outputs that fed directly into our platform development. He’s sharp, reliable, and I’d happily work with him again.”

— Geraldine Gordon, Board Director