Systems and methods for determining reach using truncation and aggregation

Abstract

Methods and systems are presented for creating and retrieving a matrix wherein a first dimension represents viewers, a second dimension represents media assets, and each data point represents a probability that a viewer accessed a media asset. The methods further include reducing the number of rows and columns of the matrix based on a desired size of the matrix and calculating a reach value for a media asset based on a the data points in the modified matrix.

1 . A method for reducing a number of data points used for calculating unique reach, the method comprising:
 retrieving a matrix comprising a plurality of data points, wherein:
 a first dimension of the matrix represents viewers, 
 a second dimension of the matrix represents media assets, and 
 each data point of the plurality of data points represents a probability a viewer associated with a value of the first dimension of the data point accessed a media asset associated with a value of the second dimension of the data point; 
   determining a required size of the matrix;   reducing, based on the determination, a number of values of the first dimension by combining a subset of data points associated with a subset of values of the first dimension;   reducing, based on the determination, a number of values of the second dimension by reducing a range of values of the plurality of data points; and   calculating a reach value for a media asset based on a first value of the first dimension and a second value of the second dimension associated with a data point corresponding to the media asset.   
     
     
         2 . The method of  claim 1 , wherein reducing the number of values of the second dimension further comprises:
 rounding up a data point in response to determining the data point is above a first threshold value; and   rounding down the data point in response to determining the data point is below a second threshold value.   
     
     
         3 . The method of  claim 1 , wherein reducing the number of values of the first dimension further comprises:
 determining that a plurality of viewers associated with the subset of values of the first dimension share an attribute.   
     
     
         4 . The method of  claim 3 , wherein the attribute is a demographic value or a behavior value. 
     
     
         5 . The method of  claim 1 , further comprising iteratively reducing the number of values of the first dimension and the number of values of the second dimension until the required size is reached. 
     
     
         6 . The method of  claim 1 , wherein the determining the required size is based on a user preference, a computing capability, or data availability. 
     
     
         7 . The method of  claim 1 , wherein the subset of data points is a first subset of data points, the subset of values of the first dimension is a first subset of values of the first dimension, and further comprising:
 reducing, based on the determination, the number of values of the first dimension by averaging a second subset of data points associated with a second subset of values of the first dimension; and   adding the first subset of data points weighted by a first weight value to the second subset of data points weighted by a second weight value.   
     
     
         8 . The method of  claim 7 , wherein the first weight value and the second weight value are based on demographic or behavior values associated with each of the first subset of data points and the second subset of data points. 
     
     
         9 . The method of  claim 1 , wherein the calculating the reach value further comprises:
 determining a probability value that a first viewer watched the media asset based on the data point; and   multiplying the probability value by a number of values in the subset values of the first dimension.   
     
     
         10 . The method of  claim 1 , wherein the plurality of data points are associated with a plurality of viewership data sources or future predictions. 
     
     
         11 . A system for reducing a number of data points used for calculating unique reach, the system comprising:
 storage circuitry configured to store a matrix comprising a plurality of data points, wherein:
 a first dimension of the matrix represents viewers, 
 a second dimension of the matrix represents media assets, and 
 each data point of the plurality of data points represents a probability a viewer associated with a value of the first dimension of the data point accessed a media asset associated with a value of the second dimension of the data point; and 
   control circuitry configured to:
 retrieve the matrix; 
 determine a required size of the matrix; 
 reduce, based on the determination, a number of values of the first dimension by combining a subset of data points associated with a subset of values of the first dimension; 
 reduce, based on the determination, a number of values of the second dimension by reducing a range of values of the plurality of data points; and 
 calculate a reach value for a media asset based on a first value of the first dimension and a second value of the second dimension associated with a data point corresponding to the media asset. 
   
     
     
         12 . The system of  claim 11 , wherein the control circuitry is further configured, when reducing the number of values of the second dimension, to:
 round up a data point in response to determining the data point is above a first threshold value; and   round down the data point in response to determining the data point is below a second threshold value.   
     
     
         13 . The system of  claim 11 , wherein the control circuitry is further configured, when reducing the number of values of the first dimension, to:
 determine that a plurality of viewers associated with the subset of values of the first dimension share an attribute.   
     
     
         14 . The system of  claim 13 , wherein the attribute is a demographic value or a behavior value. 
     
     
         15 . The system of  claim 11 , wherein the control circuitry is further configured to iteratively reduce the number of values of the first dimension and the number of values of the second dimension until the required size is reached. 
     
     
         16 . The system of  claim 11 , wherein the control circuitry is further configured to determine the required size based on a user preference, a computing capability, or data availability. 
     
     
         17 . The system of  claim 11 , wherein the subset of data points is a first subset of data points, the subset of values of the first dimension is a first subset of values of the first dimension, and wherein the control circuitry is further configured to:
 reduce, based on the determination, the number of values of the first dimension by averaging a second subset of data points associated with a second subset of values of the first dimension; and   add the first subset of data points weighted by a first weight value to the second subset of data points weighted by a second weight value.   
     
     
         18 . The system of  claim 17 , wherein the first weight value and the second weight value are based on demographic or behavior values associated with each of the first subset of data points and the second subset of data points. 
     
     
         19 . The system of  claim 11 , wherein the control circuitry is further configured, when calculating the reach value, to:
 determine a probability value that a first viewer watched the media asset based on the data point; and   multiply the probability value by a number of values in the subset values of the first dimension.   
     
     
         20 . The system of  claim 11 , wherein the plurality of data points are associated with a plurality of viewership data sources or future predictions. 
     
     
         21 - 50 . (canceled)