Validation · how we check Humanity
Two tests every number has to pass
A synthetic population is only worth asking if it gives back what the real one would. We check Humanity in two ways. The statistics have to add up, every part to its whole, every time. And the attitudes have to match a survey the model has never seen.
- 0people lost or counted twice, in any build
- 100%of regional totals equal to the published figure
- 47budget lines per household, always summing to the budget
- 0Eurobarometer answers used to build the population
Every part adds up to the whole
Official statistics are published as totals: how many people live in a region, how old they are, how many households there are, what households spend. Humanity has to give every one of those totals back, exactly, from the bottom up. Not as an average that comes out roughly right, but as a sum of individual records that lands on the published number.
That is a hard constraint, and it is a useful one. If a single household were missing, or a budget line were invented, some total somewhere would stop adding up. So every release is checked from the smallest unit to the largest, and a build that misses does not ship.
- People add up to places People sum to households, households to square kilometres, and those to municipalities, regions and the country. At every level the total is the number the statistical office published.
- Spending adds up to the budget Every household has 47 spending lines, and they sum to its budget exactly. The budget follows from the income. Where a line is split further, like the grocery basket, the parts sum to the line.
- Households agree with people A market sized in households and the same market sized in people give the same answer. Nobody is lost between the two, and nobody is counted twice.
- Everyone is in a home Every person, children included, belongs to a household, and every household to one square kilometre. Nobody floats outside a place, so every local count is complete.
- Regions earn what they earn Household income follows the published figures for the region it is in, so the money adds up region by region as well as nationally, in local currency.
- It holds however you slice it Cut the population by age, then by income, then by place, add the pieces back up, and you get the official figure again. No rounding drift between a dashboard and the annual report.
Checked against a survey it never saw
Values and attitudes are the hardest part of a population to get right, and the easiest to fake. Every person in Humanity carries around sixty of them, from trust and life satisfaction to how much the environment matters, and they come from the European Social Survey.
Which is exactly why we do not test them against the European Social Survey. A model that gives back its own source has only proved it can copy. So we test against Eurobarometer, the European Commission's own public opinion survey, which is not used anywhere in the build. Different people, different interviewers, different years, different wording, overlapping themes.
If the synthetic population answers like Eurobarometer's respondents, country by country, then the attitudes are real structure that carries over to a survey it never saw, and not an echo of the one it was built from.
- Trust
- in parliament, the legal system, politicians and other people
- Satisfaction
- with life, and with how democracy works
- Environment
- how much climate and nature matter
- Outlook
- on the economy, on Europe, on the future
- How
- the share of people in each answer, per country, set side by side
Other things it was never told
The same principle runs through every release: a check only counts if the model could not have learned the answer. A few of the comparisons, and what came out.
- Second homes in France Humanity derives a 10.3% share of secondary dwellings from the housing stock and the resident population. INSEE publishes 10%.
- Education in Dutch neighbourhoods Neighbourhoods ranked by education level correlate at 0.59 with CBS neighbourhood data, which was not an input.
- Gradients averages erase French heat pump use ranges from 2.6% to 35% across regions, matching the official gradient. Households run larger in Paris than in Burgundy, as the census says.
Where a number needs care
Regions and countries are precise. One square kilometre with five filters stacked is an estimate, and every answer says how confident it is. Anything under 100 people is not shown at all. Money stays in local currency, so compare across countries by rank or income quartile. The reference year is 2024. The long version is on Accuracy, with the publishers behind each layer on Sources.
How the population is constructed is shared under agreement for procurement, due diligence and audits. Write to hello@hiasynth.co and say what the review needs to cover.
See it answer
The quickest test is your own question, about a place you know.