EnterpriseReporting

Diversity Reporting

Estimate gender distribution across communities, events, and applicant funnels, in aggregate only.

Start with 500 free creditsDocumentation

Email gender · 1 credit per lookup · no monthly fee

Applicant funnel

F 46%
M 51%
? 3%

Aggregate only · no individual labels stored

The problem

Reporting on the gender balance of an applicant pool or customer base sounds simple until you realise you never collected the data, and self-identification, while ideal, comes with low response rates that leave the picture too sparse to report on.

With Encrata

For aggregate, anonymised reporting, inferred gender fills the gap: estimate the distribution across a pool without labelling any individual, and use it to surface imbalances worth acting on. Always prefer self-identification where available, keep the output aggregate-only, and never use an inferred label to make a decision about a specific person.

How it works

1

Send the address

Call the gender endpoint with just an email address; the name in the local part is enough to work from.

2

We infer the verdict

Encrata reads the name embedded in the address and returns a likely gender and country with a confidence score.

3

Use it with care

Segment, personalise or enrich on the verdict, always keeping neutral fallbacks and letting people override. One credit per lookup.

One call, structured answer

Diversity Reporting runs on the email gender lookup at 1 credit per lookup. Same API key, same JSON shape as every other Encrata lookup.

  • A single male / female / unknown verdict with a 0-100 confidence score
  • Country signal included, so ambiguous names resolve by region
  • 1 credit per lookup, with free repeats for six months
  • unknown is returned honestly when a name is ambiguous, never a guess
Terminal
curl -X POST "https://app.encrata.com/api/email/gender" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"email": "jane.doe@example.com"}'
response.json
{
  "email": "jane.doe@example.com",
  "gender": "female",
  "country": "US",
  "probability": 98,
  "credits": 1
}

Aggregate only, always

Where self-identification exists, always use it first, the inferred value is only there to fill the gaps that leave a pool too sparse to report on. Run the inference in a batch, aggregate the results, and report the distribution at the group level only: no individual carries a stored label, and no decision about any specific person is ever made from an inferred value.

Imbalances you can finally see

The output is a distribution you can act on, surfacing imbalances in an applicant pool or customer base that were previously invisible for lack of data. Keep the guardrails explicit in the report itself, aggregate-only, inference-supplemented, self-identification-preferred, so readers understand exactly what the numbers are and, just as importantly, what they are not.

More email gender use cases

View all
jane.doe@acme.com
+ Gender fieldFemale · 98%

Gender Enrichment

Add a probabilistic gender field to lead and customer profiles when users have not provided one

CRMEnrichment

Newsletter reach

58%
42%
Female 58%Male 42%

Audience Analytics

Understand campaign reach by inferred gender in aggregate across lists, subscribers, and event signups

MarketingAnalytics
Women's collection12,480
Men's collection9,020
2 segments built

Marketing Segmentation

Tailor content, product recommendations, or creative tests where gender relevance is legitimate

EcommerceMarketing
Start with 500 free credits
$curl https://encrata.com/api/agent/lookup -H "Authorization: Bearer YOUR_API_KEY" -d '{"e": "satya@microsoft.com"}'