A
Astris HR
Pathway
Astris HR Model

The model under the hood.

Astris HR Model is our proprietary workforce intelligence model. Today it composes deterministic scoring, embedding similarity, a knowledge graph, and large language model reasoning. Tomorrow it adds logistic regression, gradient-boosted trees, and a neural network trained on observed placement outcomes — all behind one inference interface.

Architecture

Three layers. One interface.

Astris HR Model is composed of a recall layer, a scoring layer, and a reasoning layer. The same interface serves a quick deterministic score and a fully reasoned recommendation — the latency-quality tradeoff is a configuration, not a code change.

Recall

Embedding similarity

Candidates and jobs are embedded into 1536-dim space. HNSW ANN narrows the field to the top 200 candidates per job in under 50 ms over a million-row table. The skills graph contributes when an exact embedding match doesn't exist.

Score

7-component deterministic + ensemble

Skills (40%), experience (20%), language (10%), distance (10%), schedule (10%), certifications (5%), transportation (5%). Composite is a weighted average with a transferable-skill credit and a company quality adjustment. Ensemble adds trained sub-models as data accumulates.

Reason

Plain-language rationale

A large language model produces 2-4 sentence rationales on demand. Cached on the match row. PII gates prevent disclosure of work auth, DOB, or exact address. Generated only when an employer expands a match card — not for every score.

Scoring methodology

Every component, weighted explicitly.

Astris HR's scoring is deliberate. No mystery weights. No hidden features. Every component runs deterministically and ships its sub-score with the composite.

Skills
40%
Experience
20%
Language
10%
Distance
10%
Schedule
10%
Certifications
5%
Transportation
5%
Skills

Fraction of required skills the candidate has, with a 0.6 transferable-credit for skills bridged through the knowledge graph.

Experience

Years of experience scaled against the required minimum. Zero experience scores 20; meeting the requirement scores 100.

Language

Fraction of the job's required languages the candidate speaks at conversational+ proficiency.

Distance

Haversine miles against the candidate's stated max commute. Remote roles auto-score 100. State match without coordinates scores 70.

Schedule

Overlap between candidate availability + shift preferences and the job's schedule.

Certifications

Fraction of required certifications the candidate has documented. Zero required → auto 100.

Transportation

Heuristic on candidate transport vs. job's transportation requirements + transit accessibility.

Ensemble framework

One inference interface. Many models behind it.

Astris HR Model is designed as an ensemble from day one. The heuristic scorer ships now. Additional models register themselves into the catalog as their offline training pipelines produce artifacts — and start contributing to the composite score on the same day, with no code changes at the call site.

Heuristic
Live

Deterministic 7-component scorer with skill-graph boost. Reference implementation. Always available.

Embedding similarity
Stub

Cosine similarity over candidate/job embeddings. Wired to the pgvector HNSW index; activates when embedding population completes.

Logistic regression
Planned

Trained on placement outcomes. Calibrated probabilities. Strong baseline before tree models converge.

Gradient-boosted trees
Planned

XGBoost over the full feature vector. Captures non-linear interactions and handles missing features cleanly.

Neural network (MLP)
Planned

Multi-layer perceptron for non-linear feature interactions that trees underfit. Smallest model that earns its weight in the ensemble.

K-means / DBSCAN
Planned

Skill / occupation clustering. Surfaces candidate cohorts and powers workforce-planning analytics.

Company quality boost

Independent of the candidate, every employer carries a quality score (0-100) derived from Glassdoor and Indeed ratings, our own observed retention, and caseworker feedback. The ensemble adds(qualityScore − 50) ÷ 10to the composite, capped at ±5 points. Higher-quality employers get a small but real advantage in the ranking, all else equal.

Feedback loops

The model improves from real use.

Document parse ratings

Caseworkers, candidates, and employers rate every Astris parse 1-5. ≤2 stars + a correction hint triggers automatic re-parse with the hint folded into the prompt.

Translation feedback

Thumbs up/down on translated UI strings. Average below 3 over 3+ votes triggers Claude-generated overrides that win over the static dictionary.

Match feedback

Employers rate match quality on a 5-star scale. Each rating becomes a labeled training row for the next supervised model retraining cycle.

Placement outcomes

30/90/180/365-day retention milestones, termination reasons, and follow-up survey responses are the supervised label for retention model retraining.

Supported languages

Document processing in 35+ languages.

Astris HR Model parses resumes and job descriptions in any of these languages. Source language is detected and stored on every document. Foreign credentials and former occupations are preserved in their source language and mapped to English equivalents without being erased.

Afghanistan
PashtoDari
Central Asia
UzbekTurkmen
Iran
Persian (Farsi)
Kurdistan
Sorani KurdishKurmanji Kurdish
Iran/Azerbaijan
Azerbaijani
Iran/Pakistan
Baluchi
Middle East / North Africa
Arabic (MSA)
Egypt
Arabic (Egyptian)
Syria/Lebanon/Jordan/Palestine
Arabic (Levantine)
Iraq
Arabic (Iraqi)
Gulf states
Arabic (Gulf)
Eritrea / Northern Ethiopia
Tigrinya
Ethiopia
Amharic
Somalia / Horn of Africa
Somali
East Africa
Swahili
India
Hindi
Pakistan / India
Urdu
Punjab
Punjabi
Bangladesh / India
Bengali
Gujarat
Gujarati
South India / Sri Lanka
Tamil
Andhra Pradesh
Telugu
Nepal
Nepali
Sri Lanka
Sinhala
Vietnam
Vietnamese
Myanmar
Burmese
Myanmar / Thailand
Karen
Myanmar / Bangladesh
Rohingya
Ukraine
Ukrainian
CIS
Russian
Spain / Latin America
Spanish
Italy
Italian
France / West Africa
French
Portugal / Brazil / Lusophone Africa
Portuguese
Global
English
38+ languages and counting. Don't see yours? Tell us.

Model roadmap.

What we're working on next.

Q3
  • Embedding pipeline live
  • Logistic regression v1 trained on first 500+ placements
  • Translation override generator in production
Q4
  • XGBoost retention model
  • Internal mobility matching for employer-owned workforces
  • Skills assessment v1
Q1+
  • Neural network (MLP) for non-linear interactions
  • Public API + ATS connectors
  • Cross-tenant labor market intelligence