The Lightcast Occupations Taxonomy (LOT) Classifier predicts LOT Specialized Occupations using a curated machine learning model approach.
The classifier uses a job posting's title, description and origin country and language in order to classify the content and assign it to one of Lightcast's Specialized Occupations.
Our taxonomists curate the model to target specific keywords and skills, while the remainder of the model learns from a vast corpus of raw job postings. This dual approach ensures the classifier identifies relevant skills, roles, responsibilities, and industry-specific terminology. To maintain accuracy, common words, company boilerplates, and benefits information are removed prior to classification.
Once assigned to a specialized occupation within the LOT Taxonomy, a posting can be mapped to various national taxonomy codes, such as O*NET, UKSOC, or NOC. The LOT Classifier produces derived names and codes across a four-tier structure: Career Area, Occupation Group, Occupation, and Specialized Occupation. This data enables the further derivation of relevant national taxonomy codes.