Nomacore — Name-Based Demographic Estimation API

See It in Action

Predictions below are computed by the live model when this server starts. They are statistical estimates over public reference data, not statements about any individual.

Choose a name:

Pick a name above to see the predictions

Four Statistical Dimensions

Extract aggregated demographic signals to support analytical and segmentation workflows.

Country-Level Probability Estimates

Generate country-level probability estimates from forenames and surnames. Supports 100+ countries with probability scores for top matches.

✓ Works with forename, surname, or both
✓ Population-weighted priors for accuracy
✓ Fuzzy matching for spelling variations

Gender Prediction

Predict gender with country-aware accuracy. Names like "Andrea" are male in Italy but female in the US — we handle these nuances.

✓ Country-specific gender distributions
✓ Handles ambiguous names gracefully
✓ Probability scores, not binary guesses

Demographic Classification

Aggregated statistical categories derived from public census data. Six groups with full probability breakdown.

✓ Based on US Census 2010 statistical data
✓ Six demographic categories
✓ Full probability distribution

Age & Generation

Estimate age and generational cohort from forename popularity trends. "Jennifer" peaked in the 70s; "Emma" in the 2000s.

✓ Based on SSA baby name trends
✓ Expected age with confidence range
✓ Generation classification (Boomer, X, Millennial, Z)

Use Cases

Statistical name analysis for research and analytical workflows.

Market Research

Estimate demographic composition of audiences and markets from name-based signals.

Data Quality & Validation

Flag inconsistencies and enrich records with probabilistic demographic attributes.

CRM Enrichment

Support aggregate-level CRM analysis with statistical demographic distributions.

Statistical Analysis

Power research workflows with structured demographic probability distributions.

How It Works

Uses aggregated public datasets (US Census, SSA baby names, global name registries)

Applies probabilistic Bayesian models

Returns statistical distributions, not classifications

No storage of submitted names

The API returns statistical distributions, not individual classifications.

Integration is straightforward — one API call, JSON in, JSON out.

# Get all predictions in one call
curl -X POST https://nomacore.com/predict/all \
  -H "Content-Type: application/json" \
  -H "X-API-Key: nomacore_your_key_here" \
  -d '{"forename": "Giovanni", "surname": "Rossi"}'

# Response (abridged)
{
  "country": {
    "predictions": [
      {"country": "italy", "probability": 0.89},
      {"country": "switzerland", "probability": 0.04}
    ],
    "confidence": 0.95
  },
  "gender":    {"male": 0.991, "female": 0.009, "confidence": 0.98},
  "ethnicity": {"top_ethnicity": "white",
                "probabilities": {"white": 0.94, "hispanic": 0.03}},
  "age":       {"expected_age": 52, "generation": "Baby Boomer",
                "age_range":     {"min": 35, "max": 70}}
}

Request Pilot Access

Closed pilot. Email a brief description of your use case and we'll respond with an evaluation key.

contact@nomacore.com

Name-Based Demographic Estimation API