System and method for determining and managing reputation of entities and industries through use of behavioral connections

Abstract

A system and method for determining and managing reputation of an entity or industry includes determining a sample size of the population that provides at least a pre-defined percent confidence interval, and which has the predefined level of familiarity (unique group); determining a measure of likelihood that the targeted population will perform a positive action on behalf of an entity (behavioral connection score), wherein determining the measure of the likelihood that the targeted population will perform a positive action on behalf of an entity comprises: receiving survey ratings from behavioral connection survey questions where each survey rating is provided by a party within the unique group; weighting the received survey ratings to accommodate for at least one of the group consisting of cultural bias and missed demographic quotas; and aggregating the ratings within each individual question to provide a single aggregated behavioral connection score for each behavioral connection survey question.

We claim: 
     
         1 . A method for determining reputation of an entity, comprising the steps of:
 determining a sample size of population that is demographically representative of a desired survey population and which provides at least a pre-defined percent confidence interval, where those within the sample size have a predefined level of familiarity with the entity, and wherein this sample size which provides at least a pre-defined percent confidence interval, and which has the predefined level of familiarity, is referred to herein as a unique group;   determining a measure of the likelihood that the targeted population will perform a positive action on behalf of an entity, referred to as a behavioral connection score, wherein determining the measure of the likelihood that the targeted population will perform a positive action on behalf of an entity comprises the steps of:
 receiving survey ratings from behavioral connection survey questions where each survey rating is provided by a party within the unique group; 
 weighting the received survey ratings to accommodate for at least one of the group consisting of cultural bias and missed demographic quotas; and 
 aggregating the converted and weighted received ratings within each individual question to provide a single aggregated behavioral connection score for each behavioral connection survey question. 
   
     
     
         2 . The method of  claim 1 , further comprising the step of converting the received rating from a raw scale to a different numerical scale. 
     
     
         3 . The method of  claim 1 , further comprising the step of removing from the sample size those not likely to provide true responses to survey questions. 
     
     
         4 . The method of  claim 1 , wherein the step of weighting the received survey ratings to accommodate for at least one of the group consisting of cultural bias and missed demographic quotas, further comprises applying a standardization formula in each market to ensure that behavioral connection scores are comparable across different markets, where different weights are applied to specific data based on the specific market. 
     
     
         5 . The method of  claim 1 , wherein the pre-defined percentage confidence interval is ninety-five percent confidence interval. 
     
     
         6 . The method of  claim 1 , further comprising providing the entity seeking its reputation with the single aggregated behavioral connection score for each behavioral connection survey question. 
     
     
         7 . The method of  claim 1 , further comprising the step of converting the received rating from a raw scale to a different normative scale. 
     
     
         8 . The method of  claim 4 , where market is a country or a region. 
     
     
         9 . The method of  claim 1 , where a set of reputation scores, driver scores, factor scores, and behavioral connection scores, is derived from a set of unique groups over pre-defined time intervals to create an overtime trend of scores per entity. 
     
     
         10 . A method for predicting a measure of likelihood that a targeted population will perform a positive action on behalf of an entity, referred to as a behavioral connection score, comprising the steps of:
 training a set of one or more supervised machine learning models using historical data of previously determined driver scores, factor scores, and reputation scores, used as input variables, wherein each behavioral connection business outcome score is a dependent variable, where a reputation score is a level of emotional connection of those within a unique group with the entity, a factor score is a level of how those within the unique group practically think about the entity, and a driver score is a score of an area that members of the unique group would tend to care about when assessing the reputation of the entity;   storing the trained set of supervised machine learning models; and   predicting at least one of the business outcomes from the reputation scores, driver scores, and factor scores, through use of at least one of the trained supervised learning models.   
     
     
         11 . The method of  claim 10 , wherein the step of training a set of supervised machine learning models further comprises the step of training a single machine learning model for a single behavioral connection question using the input variables of the reputation scores, factor scores, and driver scores, and the output dependent variable of a single behavioral connection score for a responding unique group. 
     
     
         12 . The method of  claim 10 , wherein a unique group is defined by determining a sample size of population that is demographically representative of a desired survey population and which provides at least a pre-defined percent confidence interval, where those within the sample size have a predefined level of familiarity with the entity, and wherein this sample size which provides at least a pre-defined percent confidence interval, and which has the predefined level of familiarity, is referred to as the unique group. 
     
     
         13 . The method of  claim 12 , further comprising the step of removing from the sample size those not likely to provide true responses to survey questions. 
     
     
         14 . The method of  claim 12 , wherein the pre-defined percentage confidence interval is ninety-five percent confidence interval. 
     
     
         15 . The method of  claim 10 , wherein the step of training a set of supervised machine learning models further comprises the step of training a single machine learning model for a single behavioral connection question using the input variables of the reputation scores, factor scores, and driver scores, and the output dependent variable of a single behavioral connection score for a set of responding unique groups. 
     
     
         16 . The method of  claim 10 , wherein the set of unique groups responded for the same entity over a period of time at set intervals. 
     
     
         17 . The method of  claim 10 , wherein the supervised machine learning model is trained with a pre-defined time lag. 
     
     
         18 . The method of  claim 10 , wherein the supervised machine learning model is selected from the group consisting of linear regression, multivariate linear regression, random forest, gradient boosting, and ensemble decision tree models. 
     
     
         19 . The method of  claim 10 , wherein the supervised machine learning model is selected from the group consisting of supervised machine learning regression models. 
     
     
         20 . The method of  claim 10 , wherein the supervised machine learning model is selected from the group consisting of supervised machine learning classification models. 
     
     
         21 . The method of  claim 10 , where additional sets of metrics may be used as inputs to the machine learning model, such as ESG (environmental, social, governance) scores, brand scores, and other reputation management related scores or metrics. 
     
     
         22 . The method of  claim 10 , where instead of predicting a behavioral connection, the supervised machine learning model is used to prioritize at least one of the group consisting of, the inputs of reputation score, driver scores, factor scores, ESG (environmental, social, governance) scores, brand scores, and other reputation management related scores or metrics, to the machine learning model by order of priority as contributing to the prediction of the behavioral connection business outcome score. 
     
     
         23 . The method of  claim 1 , further comprising the step of deriving correlations between a set of reputation scores over a pre-defined time period and a set of scores of at least one behavioral connection business outcome.