The models are optimized for the 99% of the cases without any special circumstance. Airlines overbook by x% because they know that a lot of people won't show up, they increase the price over time etc.
I can see that an event like this can throw the whole system out of whack. It's not obvious how the parameters should be altered. Without any data about how many people will buy more than one ticket in a situation like this, predictions are impossible.
I can see that an event like this can throw the whole system out of whack. It's not obvious how the parameters should be altered. Without any data about how many people will buy more than one ticket in a situation like this, predictions are impossible.