Cross-geographical predictive data analysis

Abstract

There is a need for more effective and efficient predictive data analysis. This need can be addressed by, for example, solutions for performing/executing cross-geographical predictive data analysis that enhance network transmission efficiency. In one example, a method includes determining forecasted superior domain event data for a hierarchically superior geographic domain at a forecasting period; determining forecasted inferior domain event data for each hierarchically inferior geographic domain associated with the hierarchically superior geographic domain at the forecasting period; determining confirmed inferior domain event data based at least in part on each hierarchically inferior geographic domain; and performing prediction-based actions based at least in part on each confirmed inferior domain event data.

1 .- 20 . (canceled) 
     
     
         21 . A computer-implemented method comprising:
 generating, by one or more processors, forecasted superior domain event data for a hierarchically superior geographic domain at a forecasting period based at least in part on superior observed data for the hierarchically superior geographic domain at an observation period;   generating, by the one or more processors, an inferior domain event prediction model for a hierarchically inferior geographic domain of the hierarchically superior geographic domain based at least in part on inferior observed data for the hierarchically inferior geographic domain at the observation period;   generating, by the one or more processors, simulated inferior domain input data for the hierarchically inferior geographic domain at the forecasting period;   generating, by the one or more processors, forecasted inferior domain event data for the hierarchically inferior geographic domain at the forecasting period by processing the simulated inferior domain input data in accordance with the inferior domain event prediction model; and   initiating, by the one or more processors, one or more prediction-based actions based at least in part on the forecasted inferior domain event data.   
     
     
         22 . The computer-implemented method of  claim 21 , wherein the inferior domain event prediction model is configured to generate one or more predicted events based at least in part on prediction input data for an inferior domain event of the hierarchically inferior geographic domain. 
     
     
         23 . The computer-implemented method of  claim 21 , wherein the superior observed data for the hierarchically superior geographic domain comprises observed superior domain input data for the hierarchically superior geographic domain at the observation period and observed superior domain event data for the hierarchically superior geographic domain at the observation period. 
     
     
         24 . The computer-implemented method of  claim 23 , wherein generating the forecasted superior domain event data comprises:
 generating, by the one or more processors, preliminary superior domain event data for the hierarchically superior geographic domain at the forecasting period;   generating, by the one or more processors, simulated superior domain input data for the hierarchically superior geographic domain at the forecasting period based at least in part on the observed superior domain input data; and   generating, by the one or more processors, the forecasted superior domain event data based at least in part on the preliminary superior domain event data and the simulated superior domain input data.   
     
     
         25 . The computer-implemented method of  claim 24 , wherein generating the preliminary superior domain event data comprises:
 generating, by the one or more processors, a timeseries distribution based at least in part on the observed superior domain event data;   determining, by the one or more processors, one or more exogenous variables based at least in part on the observed superior domain input data; and   generating, by the one or more processors, the preliminary superior domain event data based at least in part on the timeseries distribution and the one or more exogenous variables.   
     
     
         26 . The computer-implemented method of  claim 25 , wherein generating the preliminary superior domain event data further comprises:
 generating, by the one or more processors, a group of decomposed timeseries distributions comprising one or more intrinsic mode function distributions and an error distribution based at least in part on an empirical mode decomposition of the timeseries distribution; and   generating, by the one or more processors, the preliminary superior domain event data based at least in part on the group of decomposed timeseries distributions.   
     
     
         27 . The computer-implemented method of  claim 26 , wherein generating the preliminary superior domain event data further comprises:
 generating, by the one or more processors and using one or more machine learning models, one or more per-model preliminary event data objects based at least in part on the observed superior domain input data and the group of decomposed timeseries distributions; and   generating, by the one or more processors, the preliminary superior domain event data based at least in part on the one or more per-model preliminary event data objects.   
     
     
         28 . The computer-implemented method of  claim 27 , wherein a machine learning model of the one or more machine learning models is configured to process the group of decomposed timeseries distributions and the one or more exogenous variables to generate a particular per-model preliminary event data object. 
     
     
         29 . The computer-implemented method of  claim 21 , wherein the simulated inferior domain input data is generated based at least in part on the inferior observed data. 
     
     
         30 . The computer-implemented method of  claim 21 , wherein the inferior observed data comprises observed inferior domain input data for the hierarchically inferior geographic domain at the observation period. 
     
     
         31 . The computer-implemented method of  claim 30 , wherein generating the inferior domain event prediction model comprises:
 generating, by the one or more processors, a zero-inflated Poisson model data object for the observed inferior domain input data; and   generating, by the one or more processors, the inferior domain event prediction model based at least in part on the zero-inflated Poisson model data object.   
     
     
         32 . The computer-implemented method of  claim 30 , wherein generating the simulated inferior domain input data comprises:
 determining, by the one or more processors and using a Gibbs-sampling-based Markov Chain Monte Carlo routine, an inferior-domain-related probability distribution of the observed inferior domain input data; and   generating, by the one or more processors, the simulated inferior domain input data based at least in part on the inferior-domain-related probability distribution.   
     
     
         33 . The computer-implemented method of  claim 21  further comprising:
 generating, by the one or more processors, confirmed inferior domain event data for the hierarchically inferior geographic domain at the forecasting period based at least in part on the forecasted inferior domain event data. 
 
     
     
         34 . The computer-implemented method of  claim 33 , wherein the hierarchically superior geographic domain comprises a plurality of hierarchically inferior geographic domains, and wherein generating confirmed inferior domain event data comprises:
 generating, by the one or more processors, inferred superior domain event data for the hierarchically superior geographic domain by aggregating respective forecasted inferior domain event data for each of the plurality of hierarchically inferior geographic domains;   determining, by the one or more processors, a measure of deviation between the forecasted superior domain event data and the inferred superior domain event data; and   generating, by the one or more processors, the confirmed inferior domain event data based at least in part on the measure of deviation.   
     
     
         35 . The computer-implemented method of  claim 34 , wherein the one or more prediction-based actions comprise:
 generating a cross-geographical event prediction user interface that displays the confirmed inferior domain event data in association with a geographic region placement indication for the hierarchically inferior geographic domain.   
     
     
         36 . The computer-implemented method of  claim 35 , wherein the confirmed inferior domain event data is indicative of a predicted likelihood of an event occurrence for the hierarchically inferior geographic domain. 
     
     
         37 . The computer-implemented method of  claim 33 , wherein the one or more prediction-based actions are based at least in part on the confirmed inferior domain event data. 
     
     
         38 . The computer-implemented method of  claim 35 , wherein the initiating the one or more prediction-based actions comprises:
 detecting, by the one or more processors, an emergency condition associated with an event type associated based at least in part on the confirmed inferior domain event data; and   in response to detecting the emergency condition, generating one or more emergency event outbreak notifications for the event type.   
     
     
         39 . An apparatus comprising one or more processors and at least one memory including program code, the at least one memory and the program code configured to, with the one or more processors, cause the apparatus to:
 generate forecasted superior domain event data for a hierarchically superior geographic domain at a forecasting period based at least in part on superior observed data for the hierarchically superior geographic domain at an observation period;   generate an inferior domain event prediction model for a hierarchically inferior geographic domain of the hierarchically superior geographic domain based at least in part on inferior observed data for the hierarchically inferior geographic domain at the observation period;   generate simulated inferior domain input data for the hierarchically inferior geographic domain at the forecasting period;   generate forecasted inferior domain event data for the hierarchically inferior geographic domain at the forecasting period by processing the simulated inferior domain input data in accordance with the inferior domain event prediction model; and   initiate one or more prediction-based actions based at least in part on the forecasted inferior domain event data.   
     
     
         40 . A computer program product comprising at least one non-transitory computer-readable storage medium having computer-readable program code configured to:
 generate forecasted superior domain event data for a hierarchically superior geographic domain at a forecasting period based at least in part on superior observed data for the hierarchically superior geographic domain at an observation period;   generate an inferior domain event prediction model for a hierarchically inferior geographic domain of the hierarchically superior geographic domain based at least in part on inferior observed data for the hierarchically inferior geographic domain at the observation period;   generate simulated inferior domain input data for the hierarchically inferior geographic domain at the forecasting period;   generate forecasted inferior domain event data for the hierarchically inferior geographic domain at the forecasting period by processing the simulated inferior domain input data in accordance with the inferior domain event prediction model; and   initiate one or more prediction-based actions based at least in part on the forecasted inferior domain event data.