00000cam 2200000zi 4500 9.966443 CaOODSP 20261001141336 m o d f cr cn||||||||| 261001e20250908oncd obs f000 0 eng d CaOODSP eng rda CaOODSP n-cn--- CS11-522/2024-1-10E-PDF Evans, Justin, author. Life in the FastText lane : harnessing linear programming constrained machine learning for classifications revision / by Justin Evans and Laura Wile. At head of title: Proceedings of Statistics Canada Symposium 2024 : the future of official statistics [Ottawa] : Statistics Canada = Statistique Canada, September 8, 2025. 1 online resource (8 unnumbered pages) : graphs. text txt rdacontent computer c rdamedia online resource cr rdacarrier [Statistics Canada international symposium series : proceedings], 1709-8211 Title from cover. Issued also in French under title: Filer sur la voie du fastText : exploiter l'apprentissage automatique restreint par programmation linéaire pour réviser les classifications. Includes bibliographical references. "Statistics Canada's Labour Force Survey (LFS) plays an essential role in the estimation of labour market conditions in Canada. Periodically, LFS revises its data to the most recent industry and occupational classification versions. Differences in versions can be extensive, including high-level and unit-group structural changes, creations, deletions, split-offs and combination of classification units (classes). Historically, to reconcile split-off classes - where one class splits into multiple classes - a sample of LFS split-off records would be manually recoded to the new classification version. Based on the split-off proportion observed in the recoded sample, a random allocation method would be applied on all data to reflect the changing Canadian labour market over time. This article proposes using machine learning (fastText), constrained to split-off proportions using linear programming, to revise industry and occupation classifications in LFS. The hybrid framework benefits from a text-based revision mechanism while adhering to traditional proportions driven estimates, thus ensuring a minimal impact on the comparability of published labour market indicators"--Abstract, page [2]. Machine learning. Labor supply Canada Statistics. Occupations Canada Classification. Statistics lcgft Statistics Canada, issuing body. Filer sur la voie du fastText : (CaOODSP)9.966445 Statistics Canada international symposium series - proceedings, 1709-8211 (CaOODSP)9.505681 PDF 521 KB https://publications.gc.ca/collections/collection_2026/statcan/11-522-x/CS11-522-2024-1-10-eng.pdf 11-522-X