TL;DR
Built and led an NLP pipeline analyzing 90% of Danish job ads using NER to extract in-demand skills and market trends. Delivered insights via an interactive web dashboard for university students. Automated daily updates for real-time relevance.
University students often lack clear, up-to-date visibility into which skills are most in demand across the job market. Meanwhile, valuable signals were locked inside millions of scattered Danish job ads posted online. There was no scalable way to extract or analyze this data in a structured, student-facing format.
I led a project to build a system that could extract, process, and analyze job market data at national scale—turning unstructured job ads into actionable insights. The goal was to cover the majority of available postings, identify trends in in-demand skills, and surface the results in a way that directly benefits students exploring career paths.
Using Named Entity Recognition (NER) and custom NLP pipelines, I processed millions of Danish job ads, covering roughly 90% of the country’s online listings. I automated data extraction to identify skills, roles, industries, and hiring trends in near real-time. To surface this insight, I built a user-friendly interactive web dashboard, making it easy for students to explore skill demand across fields and geographies. I also maintained daily pipeline and database updates to ensure the insights stayed fresh and reliable throughout the project.
The result was a scalable, continuously updating platform that helped university students make smarter career decisions based on real labor market data. The tool provided a data-backed foundation for understanding which skills matter most—right now—in Denmark’s evolving job landscape.