Similar Companies API filters

A lookalike search takes the same filter object as any other company search. The seed domains decide what the results look like, and filters decide which companies are allowed in. The same filter works in count, preview, and export requests. This page covers what is specific to lookalike search. For the matching rules, accepted values, and CLI flag of each filter, see the full Company Search API filters reference.

Filters and lookalike options

Two kinds of setting shape a lookalike search. Use the one that matches what you want to change.

You want to	Use
Keep only lookalikes in a market, size, or stage	`filter`
Leave out companies you already know	`filter.domain` with `notIn`
Drop lookalikes that are only weakly similar	`lookalike.minScore`
Change how much similarity counts in the ranking	`lookalike.weight`

A lookalike search cannot be combined with a semantic search, so describe your market with filters, not with a description.

Limit lookalikes to your market

Seeds find similar companies anywhere. Add filters to keep the ones you can sell to.

{
  "lookalike": { "domains": ["stripe.com", "adyen.com"] },
  "filter": {
    "country": ["US", "CA"],
    "employees": ["51-200", "201-500"],
    "type": "private"
  }
}

Exclude seeds and existing customers

Put the domains you do not want back in filter.domain with notIn. Add your seeds and current customers there if you want to be sure they are left out.

{
  "lookalike": { "domains": ["stripe.com", "adyen.com"] },
  "filter": {
    "domain": { "notIn": ["stripe.com", "adyen.com", "checkout.com", "mollie.com"] }
  }
}

Require companies you can act on

The require filter keeps only companies that have the fields you need, such as a LinkedIn page or a revenue range.

{
  "lookalike": { "domains": ["notion.so"] },
  "filter": { "require": ["linkedin", "revenue"] }
}

Minimum score or filter

lookalike.minScore and filter remove different companies:

minScore, from 0 to 1, drops companies that are not similar enough to the seeds.
filter drops companies that do not meet an exact criterion, however similar they are.

Use both to get close matches inside your market.

{
  "lookalike": { "domains": ["notion.so"], "minScore": 0.7 },
  "filter": { "country": "US", "employees": ["11-50", "51-200"] }
}

Filtered results still come back in ranked order. Keep that order, and do not sort by score.

Filters you can add

Every company search filter works with a lookalike search.

Purpose	Filters
Market	`country`, `region`, `state`, `city`
Size	`employees`, `reportedEmployees`, `revenue`, `workforceSize`
Kind of company	`type`, `categories`, `naicsCodes`, `keywords`, `technologies`
Age and stage	`foundedYear`, `fundingRounds`, `fundingAmount`, `fundingYear`, `workforceGrowth`
Specific companies	`domain`, `id`, `query`
Data you need	`require`

See Company Search API filters for what each one accepts.

People at lookalike companies

On a people search, the same two fields go inside company: company.lookalike for the seeds and company.filter for the company filters.

{
  "filter": { "seniority": ["c-suite", "vp"] },
  "company": {
    "lookalike": { "domains": ["stripe.com", "adyen.com"] },
    "filter": { "country": "US" }
  }
}

In the CLI

Add filter flags to company similar. Use --exclude-domain to leave companies out and --min-score to drop weak matches:

companyenrich company similar stripe.com adyen.com --country US,CA --employees 51-200,201-500
companyenrich company similar notion.so --min-score 0.7 --exclude-domain notion.so,coda.io

Company Search API filters

The full reference: every filter, matching rule, and accepted value.