(closer to) equal distance between all the neighbouring cells is really helpful when you're modelling a problem as a network - eg analysing and planning routes and capacity.
Hierarchical partitioning with exact containment is useful when aggregating but that's not always the most critical property.
Ah OK thank you that is making more sense -- that since Uber is primarily about navigation and route planning, hexagons minimize the number of cells or total land coverage you need to retrieve/analyze between two points? I think that was the missing piece of information I was looking for!
Hierarchical partitioning with exact containment is useful when aggregating but that's not always the most critical property.