Archive Partners
Verified 2026 iXBRL Data

Ghost Tech Detection. High-Revenue, Low-Headcount UK Anomalies.

Most credit bureaus throw the headcount field away. We treat it as a primary anomaly axis, and the resulting Ghost Tech feed is one of the cleanest UK alt-data factors a quant desk can wire in.

SignalGhost Tech: Revenue / HeadcountNamed, typed event
RefreshDaily, ~04:00 GMT (point-in-time clean for backtesting)Every business day
CoverageAll UK private companies, FRS 102 + FRS 105UK companies

The signal

Ghost Tech: Revenue / Headcount

When revenue per employee crosses the SIC peer 99th percentile, you're looking at one of three things, a shell company, a transfer-pricing artefact, or a genuinely AI-driven outperformer. Each is tradable; we just flag the anomaly.

Trigger formula(turnover / average_headcount) ≥ percentile_99(SIC_peer_set) AND average_headcount ≤ 10
What we measureRevenue-per-employee benchmarked against the live SIC peer-set distribution. Companies appearing in the 99th percentile *and* operating with 10 or fewer staff are tagged as Ghost Tech candidates and pushed to the alt-data feed.
Underlying iXBRL tagsuk-bus:Turnoveruk-bus:AverageNumberEmployeesuk-bus:WagesAndSalariesuk-bus:DirectorsRemuneration

What a match looks like

The kind of record this signal returns.

#Turnover (FY25)Trigger detail
1£880,000Rev/headcount £880k · 1 director, 0 staff
2£1,420,000Rev/headcount £710k · SIC 99.6 percentile
3£4,910,000Rev/headcount £2.4M · 2 staff · holdco-shaped
4£3,180,000Rev/headcount £530k · 6 staff · AI signature
5£1,290,000Rev/headcount £1.29M · sole director

Illustrative examples of the figures each match carries. The live feed names every company, with the filing behind each figure.

Get on the Pulse

Want the Ghost Tech feed point-in-time clean for backtesting?

The Data Market exposes five years of Ghost Tech signal events with no look-ahead bias, JSON, Parquet or CSV delivery. Each row is auditable to the originating Companies House filing reference.