Dynamic hotspot prediction method and system

A system for dynamically predicting hotspots of an event in a geographic location and generating corresponding alerts, the system comprising:

• a communication interface configured to collect raw occurrence data from a remote database using ETL steps;
• and
• a server including at least one processor and a memory storing instructions for execution by the processor for performing steps including,
• performing spatial aggregation to map the collected raw occurrence data to multiple grids within the pre-selected geographical area;
• deriving aggregated data over a time period for the grids based on the mapped raw occurrence data, the aggregated data including an aggregated event count;
• implementing a data driven volume predictive model, where volume data is grouped into a number of pre-defined buckets, such that each pre-defined bucket represents a range of volumes with a lowest pre-defined bucket representing lowest volumes to a highest pre-defined bucket representing highest volumes, and for each grid, determining a corresponding probability of each bucket based on the aggregated event count and selecting a predictive volume as a highest probability bucket;
• calculating a hotspot probability measure for each grid by summing the probability of the highest probability bucket with probabilities of all higher pre-defined buckets;
• calculating a hotspot score for each grid based on the corresponding hotspot probability measure and a predicted bucket weight;
• selecting a predetermined N number of grids having the highest hotspot score as predicted hotspot;
• and
• generating an alert indicating the predicted hotspot and a display interface displaying the alert on a predictive GUI showing the multiple grids.

A non-transitory computer readable medium storing instructions for execution by a processor, wherein the instructions upon execution cause the processor to perform steps including:

• collecting raw occurrence data representing event occurrences within a preselected geographical area;
• performing spatial aggregation to map the collected raw occurrence data to multiple grids within the pre-selected geographical area;
• deriving aggregated data over a time period for the grids based on the mapped raw occurrence data, the aggregated data including an aggregated event count;
• building a data driven volume predictive model, where volume data is grouped into a number of pre-defined buckets, such that each pre-defined bucket represents a range of volumes with a lowest pre-defined bucket representing lowest volumes to a highest pre-defined bucket representing highest volumes, and for each grid, determining a corresponding probability of each bucket based on the aggregated event count and selecting the predictive volume as a highest probability bucket;
• calculating a hotspot probability measure for each grid by summing the probability of the highest probability bucket with probabilities of all higher pre-defined buckets;
• calculating a hotspot score for each grid based on the corresponding hotspot probability measure and a predicted bucket weight;
• selecting a predetermined N number of grids having the highest hotspot score as predicted hotspots;
• and
• generating an alert indicating the predicted hotspots and displaying the alert on a predictive GUI showing the multiple grids.