You wouldn’t. But just because a prediction can’t be 100% accurate because of missing data doesn’t mean that the prediction isn’t useful.
Really, what they are likely comparing is the relative changes in parking lot occupancy over time. So it’s not necessary to have complete coverage of all parking lots. You just need enough coverage to make the prediction with a certain level of confidence.
Really, what they are likely comparing is the relative changes in parking lot occupancy over time. So it’s not necessary to have complete coverage of all parking lots. You just need enough coverage to make the prediction with a certain level of confidence.