onet-match

onet-match

**Occupation classification and job-title normalization against the O\*NET-SOC taxonomy.** onet-match turns messy, unstructured text about work (job titles, resume bullets, job postings, project descriptions, interest statements, skill lists) into standardized SOC codes with a fine-tuned retrieve-and-rerank transformer pipeline. On held-out O\*NET text it ranks the right occupation first 51% of the time, against 21% for a TF-IDF baseline, and 65% vs 17% on messy, human-style inputs. Each result is enriched with O\*NET tasks, skills, knowledge and RIASEC interests, and comes with a calibrated confidence. Use it from Python, the command line, a REST API or any MCP-compatible agent, with no API keys.

• [Try it in your browser](https://huggingface.co/spaces/BenjaminChan12/onet-match): no install, and the model runs on your device.
• Open source (MIT) and runs locally. No API key or account needed to match.
• Fine-tuned bge-base bi-encoder + cross-encoder reranker over all 923 O\*NET 31.0 occupations. About 47 ms per query on a laptop.
• Python API, CLI, REST API (FastAPI), MCP server for AI assistants, and Docker.
• Also includes the O\*NET data pipeline it's built on: bulk database download, a Web Services client and analysis tools.

Real outputs of the served model, saved in outputs/examples/readme_examples.json.

Quickstart

pip install "onet-match[matching]"

from onet_match import match

result = match("Must know survival analysis, R, SAS and clinical trial data", top_k=5) for m in result.matches: print(m.soc, m.title, m.confidence) print(result.profile["riasec_code"]) # aggregate interest code, e.g. "ICS"

The package imports as onet_match and provides the onet-match command. The first call downloads the pretrained model bundle (about 0.5 GB) from the Hugging Face Hub (BenjaminChan12/onet-match) and caches it.

onet-match match "Excel, QuickBooks, payroll, AP/AR"          # CLI (add --json for JSON)

pip install "onet-match[matching,serve]" onet-match serve --port 8000 # REST API curl -s localhost:8000/match -H 'content-type: application/json' \ -d '{"text": "I love weather, maps and tracking storms", "top_k": 3}'

REST routes: POST /match, POST /match/batch, GET /occupation/{soc} and GET /health. The full request and response contract and the Docker setup are in docs/API.md.

For coding agents: llms.txt is a one-page summary, and AGENTS.md covers usage from another project and work inside this repo.

Use from AI assistants (MCP)

onet-match mcp runs a Model Context Protocol server with two read-only tools: match_occupations(text, top_k) and get_occupation(soc). Add it to any MCP client (Claude Desktop, Cursor, VS Code and others):

{

"mcpServers": { "onet-match": { "command": "uvx", "args": ["--from", "onet-match[mcp]", "onet-match", "mcp"] } } }

Without uv, run pip install "onet-match[mcp]" and use "command": "onet-match", "args": ["mcp"]. For a remote server, use onet-match mcp --transport streamable-http --port 8001 (served at /mcp). Tool arguments and return fields are in docs/API.md. Listed in the MCP Registry as io.github.Benjamin-V-Chan/onet-match, on Glama and on mcpservers.org.

What each match contains

soc, title, confidence (calibrated, 0–1), score, major_group and its title, job_zone, riasec_code, description, top_tasks, top_skills and top_knowledge (with O\*NET importance and level). Each result also carries a profile that aggregates skills, knowledge and all six RIASEC interests across the matches, weighted by confidence.

Use cases

• Career exploration (EdTech). Map what students say they did or enjoy to occupations and skills.
• Resume and profile parsing. Code experience bullets and skill lists to SOC codes.
• Skills-based hiring and workforce planning. Turn a list of required skills into the roles that use them, to scope a job or find adjacent talent.
• Job-posting normalization. Turn informal titles and descriptions into standard occupations.
• Workforce and labor-market analytics. Batch-code large text collections.
• Career counseling tools. Show the tasks and skills behind a suggestion.
• LLM agents. Ground occupation questions in O\*NET instead of free generation (see llms.txt).

Worked example: onet-match-job-postings codes 3,000 LinkedIn job postings and compares pay by occupation group.

Details and integration patterns: docs/APPLICATIONS.md.

Accuracy

All models are evaluated on the same held-out splits. Every number traces to a saved run in outputs/runs/.

• **O\*NET test:** 6,792 held-out titles, task statements, work activities and descriptions.
• Messy-text test: 4,703 informal snippets written by a different LLM than the one that wrote the training text.
• Confidence: temperature-calibrated, ECE 0.037.
• Full results: per-input-type tables, calibration, ablations, learning curves and error analysis are in docs/RESULTS.md.

How it works

flowchart LR

B["O*NET 31.0 database (bulk download)"] --> C["Occupation catalog 923 occupations"] C --> P["Labeled pairs titles · tasks · activities"] C --> S["LLM-written messy text train: model A · test: model B"] P --> T["Fine-tune bi-encoder

• cross-encoder reranker"] S --> T T --> BU["Model bundle

(Hugging Face Hub)"] BU --> API["match() · onet-match CLI · REST API"]

1. A fine-tuned bi-encoder (bge-base) embeds the input and retrieves the 20 nearest occupations.
2. A fine-tuned cross-encoder rescores those 20.
3. The two scores are blended with a weight chosen on validation data.
4. A temperature-scaled softmax turns the blended scores into calibrated confidence.

The validation and test tasks are removed from the occupation documents the models search, so no test text leaks into retrieval. Synthetic training and test text come from different LLMs.

In-browser demo

The demo Space runs the same pipeline client-side with transformers.js: both models are exported to ONNX and quantized to int8 (about 130 MB, cached after the first visit). demo/build.py builds it from a bundle. Quantization and the browser runtime shift results slightly: on 800 test queries the browser picks the same top match as the Python package 95% of the time, with top-1 accuracy 61.5% vs 62.6% (outputs/demo/browser_parity.json). Use the Python package for anything that matters.

O\*NET data pipeline

The onet_data_collector package (onet-collect) downloads and verifies O\*NET database releases, which needs no credentials. It also wraps O\*NET Web Services: keyword search, occupation details and flattened profiles. See docs/COLLECTOR.md.

onet-collect bulk download                         # download + verify the latest O*NET database

onet-match collect "healthcare" "technology" # Web Services search (free O*NET account, see .env.example) onet-match eda | keywords | cluster # classic analysis: coverage, keyword attribution, TF-IDF clusters

Train your own

git clone https://github.com/Benjamin-V-Chan/onet-match && cd onet-match

pip install -e ".[dev]" onet-match matching build-data # O*NET catalog, labeled pairs, splits scripts/matching/reproduce.sh # every model, ablation and the results report onet-match matching bundle " " --run # package a model for serving

• Synthetic text: WITH_SYNTH=1 TRAIN_LLM= EVAL_PROVIDER= EVAL_LLM= scripts/matching/reproduce.sh also generates the messy training and test text, using a different LLM for each. It needs LLM API keys in environment variables.
• Training time: bge-base took 58 minutes for one epoch on a laptop GPU (Apple Silicon, MPS). The exact scripts behind every saved run are in scripts/matching/.
• Tests: pytest runs fully offline, using tiny local models and a mocked LLM.

Set ONET_MATCH_BUNDLE=/path/to/bundle to serve your own model, or ONET_MATCH_HF_REPO=owner/repo to load one from the Hub.

Background

This project was originally built in 2024 as an open-source edtech tool for analyzing O*NET occupational data at scale, and as part of my capstone project for an engineering course. Its analytics pipeline (EDA, occupation clustering, and keyword attribution) was later integrated into production products at Project Leo, and has inspired related work at other companies and projects.

In 2026 it was rebuilt around semantic occupation