What people do, not only what they say.
Sentiment gives you the mood. Movement gives you the behaviour. Read together they tell you whether a programme reached the districts it was written for.
- Unit
- Cell and cohort
- Grain
- 500m to district
- Cadence
- Daily and hourly
- Method
- Matched control areas
Behaviour as an independent measure
Survey instruments are slow, expensive, and vulnerable to what respondents think you want to hear. Movement data has the opposite properties. It is fast, continuous, and indifferent to how people describe themselves, which makes it a useful check on everything else you collect.
Used together the two are stronger than either alone. When sentiment about a transport programme is negative but corridor volume through the new route rose forty percent, you are looking at a communications failure rather than a delivery failure. Those two problems have different owners and different remedies, and most governments discover which one they had far too late.
Analyses that get used
Catchment and trade area. Draw any boundary and get the population that visits it, where they travelled from, how far, and how that changed against a chosen baseline.
Corridor and transit flow. Hourly and daily volume along road and rail corridors for capacity planning, evacuation modelling, and event control.
Cohort demographics. Age band, income band, and workforce composition attached to the catchment rather than to a person.
Programme evaluation. Behaviour inside a target area before and after an intervention, compared against a matched control area you did not touch, which is the only version of this analysis that supports a causal claim.
Working with imperfect coverage
Panel coverage varies by country, by region, and by device platform, sometimes by a factor of ten between a capital and a rural province.
We measure that variation, publish it alongside every result, and refuse analyses the panel cannot support in that geography. An unweighted figure from a thin panel is worse than no figure, because it carries the same authority in a briefing while being wrong. Where coverage is too sparse for a district-level claim, we say the district cannot be assessed.
Typical questions answered
The parts of this capability a technical evaluator will want to interrogate before a procurement decision.
Infrastructure
Which corridors are at capacity now, and which will be after the new development opens.
Service placement
Where a clinic, school, or registration office would serve the most people who currently travel furthest.
Event assessment
How many people were present at a gathering, arriving from where, over what window.
Programme reach
Whether a subsidy or campaign changed behaviour in the districts it targeted, against a control.
Asked in most evaluations
Answers we would give in the room, written down so you can circulate them without a meeting.
Where does the underlying data come from?
Commercially licensed mobility panels, telecom-derived aggregates where a national operator participates, and public transport and census sources. The exact mix depends on what is lawfully available in your jurisdiction, which we establish during the assessment phase before anything is promised.
How granular can the analysis go?
Cell sizes from roughly 500 metres upward, with hourly time resolution where panel density supports it. Granularity is bounded by coverage rather than by the tooling, and we report the bound rather than interpolating past it.
Can this measure the size of a gathering?
Yes, as a range with stated confidence derived from panel share in that area. Point estimates for crowd size are a well-known way to be publicly wrong, so we do not publish them.
Does it work outside major cities?
It depends on panel density. Capitals and secondary cities are usually well covered. Rural coverage varies widely and we will tell you before contracting whether your regions of interest can support the analysis you want.
Adjacent capability
Each capability runs on the same collection and classification core, so evidence gathered for one is available to the others.
Health system transformation
National health capability rebuilt with modern AI: triage and demand management, diagnostic support, clinical documentat...
Open-source intelligence
Collection across press, broadcast, social, forums, registries, imagery, maritime and aviation data, fused against a per...
Sentiment and buzz measurement
We separate what gets collected from what gets measured. A monitor names a query, a subject, and the ideas you want test...
Bring us the question your last briefing could not answer.
Tell us the jurisdiction and the mandate. We will tell you within a week whether we are the right people for it.