Analysis of commuting patterns for discovery of regions
Conventionally, people talk about a region based on official division, tradition, or their own perception. However, this may be quite vague and the concept of a region may be fairly dynamic over time. With the availability of large data, such as commuting data or various intra-city (town) economic activities data, it may be possible to come up with a data-driven approach to discover regions, i.e., what combination of cities and towns would form a region.
-- Given commuting records of many cities and towns in Massachusetts and Rhode Island, find a new partition of regions from the commuting data.
-- A multi-objective clustering analysis was carried out.
-- Data source: not available