High spatial resolution prediction

Abstract

A method, system, and computer program product for managing resources by obtaining a high spatial resolution estimate of behavior adoption are described. The method includes obtaining a low-resolution estimate with a fixed geographic scale, selecting a sample of customers based on the low-resolution estimate, implementing a statistical model to obtain relative probability of adoption of the behavior by each of the sample of customers, and generating a weighted random realization from the sample of customers, the weighted random realization being weighted based on the relative probability of adoption. The method includes iteratively implementing the selecting the sample of customers, the implementing the statistical model, and the generating the weighted random realization to obtain a set of the weighted random realizations, and obtaining the high spatial resolution estimate, providing greater resolution than the low-resolution estimate at a location of interest, based on the set of the weighted random realizations.

1 - 8 . (canceled) 
     
     
         9 . A system to manage resources by obtaining a high spatial resolution estimate of behavior adoption, the system comprising:
 an input interface configured to obtain a low-resolution estimate with a fixed geographic scale, the low-resolution estimate indicating a number of adoptees of a behavior in a specified time period; and   a processor configured to select a sample of customers based on the low-resolution estimate, implement a statistical model to obtain a relative probability of adoption of the behavior by each of the sample of customers, generate a weighted random realization from the sample of customers, the weighted random realization being weighted based on the relative probability of adoption, iteratively repeat generating the weighted random realization for different ones of the sample of customers, and obtain the high spatial resolution estimate, providing greater resolution than the low-resolution estimate at a location of interest, based on the set of the weighted random realizations.   
     
     
         10 . The system according to  claim 9 , wherein a sample size of the sample of customers at each iteration is equal to the number. 
     
     
         11 . The system according to  claim 9 , wherein the processor implements the statistical model by obtaining inputs associated with the sample of customers. 
     
     
         12 . The system according to  claim 11 , wherein the inputs include one or more of demographic information and behavioral attributes. 
     
     
         13 . The system according to  claim 11 , wherein the processor determines changes in consumption patterns for the sample of customers based on the inputs. 
     
     
         14 . The system according to  claim 9 , wherein the statistical model is implemented as one or more of a support vector machine, a logistic regression, neural networks, and random forests. 
     
     
         15 . The system according to  claim 9 , wherein the processor obtains the high spatial resolution estimate based on obtaining a count of adopting customers among the sample of customers for each iteration at a given location and obtains a range of the count of adopting customers over all the iterations as an uncertainty in the high spatial resolution estimate. 
     
     
         16 . A computer program product for managing resources by obtaining a high spatial resolution estimate of behavior adoption, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to perform a method comprising:
 obtaining a low-resolution estimate with a fixed geographic scale, the low-resolution estimate indicating a number of adoptees of a behavior in a specified time period;   selecting a sample of customers based on the low-resolution estimate;   implementing a statistical model to obtain a relative probability of adoption of the behavior by each of the sample of customers;   generating a weighted random realization from the sample of customers, the weighted random realization being weighted based on the relative probability of adoption;   iteratively implementing the selecting the sample of customers, the implementing the statistical model, and the generating the weighted random realization to obtain a set of the weighted random realizations; and   obtaining the high spatial resolution estimate, providing greater resolution than the low-resolution estimate at a location of interest, based on the set of the weighted random realizations.   
     
     
         17 . The computer program product according to  claim 16 , wherein the selecting the sample of customers includes selecting a sample size equal to the number. 
     
     
         18 . The computer program product according to  claim 16 , wherein the implementing the statistical model includes one or more of obtaining inputs associated with the sample of customers, and the obtaining the inputs includes obtaining demographic information and behavioral attributes. 
     
     
         19 . The computer program product according to  claim 17 , wherein the obtaining the inputs includes determining changes in consumption patterns for the sample of customers. 
     
     
         20 . The computer program product according to  claim 16 , wherein the obtaining the high spatial resolution estimate includes obtaining a count of adopting customers among the sample of customers for each iteration at a given location and obtaining a range of the count of adopting customers over all the iterations as an uncertainty in the high spatial resolution estimate.