Model card

astris-match-engine-v1

Eight-dimension match engine combining skills (0.27), experience (0.20), logistics (0.15), retention (0.15), language (0.10), education (0.05), culture (0.05) and interview (0.03), with an essential-skill coverage cap and a cross-function-family cap. The retention dimension reads the retention ensemble.

At a glance

Kindscoring heuristic
Version1.0.0
StatusActive — contributing to scores
Ensemble weight0
Trained atNot trained yet
Trained onn/a
ArtifactNo artifact (heuristic or pre-training)

Metrics

{
  "weights": {
    "skills": 0.27,
    "culture": 0.05,
    "language": 0.1,
    "education": 0.05,
    "interview": 0.03,
    "logistics": 0.15,
    "retention": 0.15,
    "experience": 0.2
  },
  "validation": "synthetic_seed",
  "real_cohort": "pending"
}

Notes

Composition / weighting layer over the model outputs, not itself a retention voter — weight 0. See api/ml/match_engine.py.