Rounding is a privacy control, designed to prevent accidental or deliberate identification of individuals through the results of insight queries.
Rounding controls the precision of the statistics returned by a query. Because the statistics returned are always "round numbers", an attacker cannot gain information by looking at precise counts.
Each dataset has a configurable rounding threshold, and results are rounded down to be a multiple of this threshold. When a query involves more than one dataset, results are rounded down to be a multiple of the highest of the rounding thresholds. When you create a dataset, by default the rounding threshold will be set to 100 individuals.
For example, suppose dataset A has a rounding threshold of 50 and dataset B has a rounding threshold of 25. The highest of these is 50, so the statistics returned will always be a multiple of 50.
If, say, there are 1,070 people in the query result who live in London, this will be rounded down to 1,050. If there are 49 people who live in Scotland, this will be rounded down to 0.