Clustering method and system

A method to create non-overlapping clusters in an area to facilitate customer segmentation and distribution within the area to optimize logistic operations, the method comprises:

• receiving, by a processor, a set of location data points associated with a plurality of user devices in an area and a defined block area, wherein each location data point comprises a latitude value and a longitude value indicating geographic coordinates of each user device;
• identifying, by the processor, at least two reference points from the set of location data points, wherein a first reference point of the at least two reference points has one of following combinations:
• minimum latitude value and minimum longitude value,
• maximum latitude value and minimum longitude value,
• minimum latitude value and maximum longitude value,
• maximum latitude value and maximum longitude value, and
• wherein a second reference point of the at least two reference points has opposite combination of latitude and longitude values from the first reference point, ensuring that the first and second reference points are diagonally opposite corners of a rectangular geographic boundary;
• using the identified first and second reference points to define four corners of the rectangular geographic boundary;
• determining, by the processor, remaining two corners of the rectangular geographic boundary by:
• combining the latitude value of the first reference point with the longitude value of the second reference point to determine a third corner of the rectangular geographic boundary;
• combining the latitude value of the second reference point with the longitude value of the first reference point to determine a fourth corner of the rectangular geographic boundary;
• dividing, by the processor, the rectangular geographic boundary into a set of blocks based on the defined block area;
• determining, by the processor, a number of location data points present in each block;
• sorting, by the processor, the set of blocks in a descending order based on the number of location data points present in each block;
• determining, by the processor, a centroid of a plurality of location data points present in a block of the set of blocks, wherein the centroid is a point at center of the block;
• reconfiguring, by the processor, the block to adjust boundaries of the block to remove an empty space from the block to form a reconfigured block, wherein the reconfigured block is based on the centroid and distribution of the location data points associated with each block from the set of blocks;
• marking, by the processor, the reconfigured block from the set of blocks as a fixed block or a floating block using an 80-20 hypothesis technique in order to generate a set of fixed blocks and a set of floating blocks;
• and
• creating, by the processor, a plurality of non-overlapping clusters in the area by iteratively adjusting the floating block of the set of floating blocks by one of:
• merging the floating block from the set of floating blocks with one of the fixed block based on the latitude value and the longitude value of the location data points present in the floating block;
• and
• re-marking the floating block as the fixed block when the merging of the floating block with the fixed block exceeds the defined block area, wherein the plurality of non-overlapping clusters facilitates customer segmentation and distribution within the area to optimize logistic operations within the area.