Media
Ask your subscribers anything.
Get answers in seconds
A synthetic version of your subscribers, built from your customer data.
Test price, content and format decisions before they go live
What Electric Twin is
Electric Twin builds a synthetic version of your subscribers from your customer data.
Ask them anything and get real answers in about a minute,
just like your customers would.
No panels, no fieldwork, no six-week wait.
Accurate, independently validated, with up to a 96% match (1-MAE) against real-world surveys.
Electric Twin platform
Your subscribers, on demand
This is what it looks like. Ask a question in plain English, get research-grade answers in about a minute.
Understand the why behind every number. We give you evidence that stands up when the room asks how you know.
merlin.electrictwin.com
We’re moving the digital subscription from £26 to £29 a month. Ask @Subscribers who cancels, who downgrades, and what would keep them.
M
Merlin
Stay at the new price
71%
Downgrade to the weekend-only tier
18%
Would cancel - mostly year-one discount joiners
11%
The risk isn’t the base, it’s the discount cohort - aim the retention offer at year-one subscribers. Ask them what they think and why.
Ask your subscribers anything…
How the audience is built
Built from data you already have
A synthetic audience is not a audience. It’s a live audience of your customers that you can ask anything, then ask again. We validate against a holdout of real respondents, so it holds up when you take it to the board.
Your data: subscriber, consumption and churn data
Validated against a holdout of real respondents before go-live
Onboarding takes days, not months. Your data stays yours.
@Subscribers
Synthetic audience
Respondents
2,900 synthetic subscribers
Built from
Subscriber base, consumption history, UK media dataset
Validation
up to 96% match (1-MAE) against a real-respondent holdout
Ready to ask
Ask this audience
What media teams test
From subscription pricing to the greenlight meeting
Built for the teams the business turns to before it commits - audience insight, pricing, and commissioning.
Ask @Subscribers who cancels if the price moves £3 a month
Subscription pricing and propositions
Test price moves, tier changes and new propositions on your own subscriber base before the renewal cycle hits. See who stays, who downgrades, who walks - and why.
Ask @Subscribers which of these three commissions they’d actually watch
Content strategy and commissioning
Put concepts in front of the audience you’re commissioning for and see forecast appetite by segment before the budget is committed - not after the ratings land.
Ask @Lapsed_Subscribers which format would bring them back
Concept and format testing pre-launch
Test titles, formats and treatments before launch - which lands with which segment, what confuses, what they’d make time for. Evidence for the greenlight meeting, not gut feel.
Research at the speed of your commissioning cycle
60s
to responses, instead of 6 weeks
Unlimited
questions and iterations, at no extra cost
50k evals
across 155 countries, continuously benchmarked
Up to 96%
match rate (1-MAE) against real-world data
Why not the usual routes
The honest comparison
A panel survey
Accurate, but slow
Six to eight weeks of fieldwork per question set, and a budget to match. Electric Twin matches panel accuracy and answers in about a minute. Keep the panel for the studies that truly need real respondents.
6-8 weeks, or 60 seconds
A generic LLM
Fast, but it has never met your customers
An LLM alone answers from the internet, not from your data - useful for drafting, blind on your subscribers. Modelled from your own data, Electric Twin reaches up to 96% (1-MAE) against real-world answers.
Gut feel
Free, until it isn’t
Experience is a fine compass and a poor pricing model. The price rise announcement goes out either way. The difference is whether you tested it on your subscribers first.
£0 today. Expensive when the cancellations land
Our accuracy
Proof from a national newsroom
“From rationing research to running it on demand.”
10x
research volume
92%
accuracy (NDAM) vs a real panel, in The Times validation
How it works
Your subscribers. Your audience
Step 1
Build your audience
Synthetic subscribers built from your customer and consumption data. No panels, no recruitment.
Step 2
Ask the questions
Type them like you would to a colleague. No survey scripting, no fieldwork window.
Step 3
Get your answers
Research-grade results in seconds, benchmarked against real-world data.
Step 4
Dig deeper
Follow up on any answer and drill into segments until you have the why.
