Changelog
Product updates and improvements
A running log of what changed in the dataset, schema, and enrichment models. Entries are tagged so you can scan for what matters to your work:
- new — additions to the dataset, new fields, new products, or new endpoints.
- improved — accuracy gains, coverage expansion, or model retraining.
- fixed — corrections to historical data, schema bugs, or enrichment edge cases.
Subscribers receive the same notes via email when changes ship. For accuracy benchmarks behind each model release, see data quality; for the field-level schema, see schema.
New Website Launch
Launched the new Canaria website with dataset catalog, methodology documentation, data schema explorer, provider comparison, and solutions pages. Built on Next.js with a modern dark theme.
Automated Sample Generation Pipeline
Launched AI-powered sample generation. When you request a sample, our AI assistant builds an optimized query based on your use case, executes it, reviews quality, and delivers a CSV with signed download link via email. Up to 3 quality review iterations per sample.
Skills Taxonomy Expanded to 37,000+
Expanded the skills taxonomy to 37,000+ technical skills, 3,000+ certifications, and 400+ soft skills. Added NLP relevance filtering to reduce false positives (e.g., "Java" correctly excluded from Barista postings).
Salary Prediction Model v2
Retrained the salary prediction model on 50M+ Glassdoor/Indeed observations. MAPE improved to under 15%. Coverage for 2023+ data now reaches 85-95%.
Canaria Job Intelligence Platform
Official launch of the Canaria Job Intelligence Platform with 900M+ unique deduplicated job postings, 82 enriched fields, and our NLP enrichment pipeline. Coverage from 2022 to present with daily incremental updates.
Ready to Explore the Data?
Get a free sample of our research-grade job market data. No credit card required.
Request a Free Sample