Multi-Variable Assessment Systems and Methods that Evaluate and Predict Entrepreneurial Behavior

Abstract

Multi-variable assessment systems and methods that evaluate and predict entrepreneurial behavior are provided herein. Methods include predicting a likelihood of an individual successfully conducting one or more business transactions by scoring features of the individual from entrepreneur data collected from a plurality of network modalities, as well as a social-network structure for the individual and business event information and performing a business transaction with the individual when scored features meet or exceed thresholds for conducting the business transaction.

What is claimed is: 
     
         1 . A method, comprising:
 generating extracted features of an individual from entrepreneur data collected from a plurality of network modalities;   assessing entrepreneurial behavior of the individual by calculating multivariate scores for each of the extracted features;   comparing the multivariate scores to one or more business opportunity thresholds;   funding a business opportunity with the individual when the multivariate scores meet or exceed the one or more business opportunity thresholds;   iteratively collecting additional performance data during the business opportunity;   extracting features from the additional performance data into the features; and   reevaluating continuance of the business opportunity based on updated multivariate scores calculated using the additional performance data, wherein the business opportunity is terminated if the updated multivariate scores fall below the one or more business opportunity thresholds.   
     
     
         2 . The method according to  claim 1 , further comprising obtaining the entrepreneur data related to personal skills data and social network data, the plurality of network modalities comprising social networks, phone records, and message records. 
     
     
         3 . The method according to  claim 2 , further comprising
 obtaining business event information relating to events between the entrepreneur and contacts of the entrepreneur found in the entrepreneur data;   storing the entrepreneur data from the plurality of network modalities as unstructured data; and   performing a dynamic measurement of engagement between the entrepreneur and the contacts by looking for contacts between the entrepreneur and the contacts that cross the plurality of network modalities including social media, phone records, SMS messages, and email messages, the dynamic measurement comprising an entrepreneur score for the entrepreneur.   
     
     
         4 . The method according to  claim 3 , wherein the business event information comprises any of phone records, SMS messages, and email messages for the entrepreneur having a time, a duration, and a contact. 
     
     
         5 . The method according to  claim 4 , further comprising determining at least one of currentness, originating party, sequences of SMS messages, frequency of SMS messages with the contacts, time of day of the SMS messages, sequences of calls, frequency of calls with the contacts, time of day of the calls, or combinations thereof. 
     
     
         6 . The method according to  claim 5 , further comprising:
 categorizing social media communications for the entrepreneur found through the social networks;   determining a distribution of the social media communications between business and friends; and   inferring diversification, breadth, and seriousness of the entrepreneur from the distribution.   
     
     
         7 . The method according to  claim 6 , further comprising:
 determining contact clusters of email addresses for the contacts using the entrepreneur data and the business event information; and   determining category distributions and linkages between the entrepreneur and the contacts.   
     
     
         8 . The method according to  claim 1 , further comprising performing the method for a plurality of individuals. 
     
     
         9 . The method according to  claim 8 , wherein calculating multivariate scores for each of the extracted features comprises, for each of the plurality of individuals:
 placing the multivariate scores for each of the extracted features into a matrix;   weighting each of the multivariate scores to determine principle components of the matrix;   generating an information-weighted principle components space using the principle components of the matrix and an information index;   generating clusters of the information-weighted principle components space for the plurality of individuals together; and   comparing the multivariate scores for the individual to the clusters.   
     
     
         10 . A method, comprising:
 obtaining principal components of an entrepreneur data space for a plurality of entrepreneurs;   obtaining information weightings for each principal component dimension of the entrepreneur data space;   rotating the entrepreneur data space using information-weighted principal component values;   clustering groups of entrepreneurs in the entrepreneur data space using the rotated entrepreneur data space;   obtaining entrepreneur data for an individual;   obtaining information weightings for each principal component dimension of the entrepreneur data for the individual;   rotating the entrepreneur data using information-weighted principal component values; and   comparing a distance between the rotated entrepreneur data and the groups of entrepreneurs in the entrepreneur data space to determine if the individual is close to the groups.   
     
     
         11 . The method according to  claim 10 , wherein the extracted features comprising entrepreneur data of the individual from collected from a plurality of network modalities using entrepreneur data collected across a plurality of network modalities. 
     
     
         12 . The method according to  claim 11 , further comprising assessing entrepreneurial behavior of the individual by calculating multivariate scores for each of the extracted features. 
     
     
         13 . The method according to  claim 12 , further comprising obtaining the entrepreneur data related to personal skills data and social network data, the plurality of network modalities comprising social networks, phone records, and message records. 
     
     
         14 . The method according to  claim 13 , further comprising:
 obtaining business event information relating to events between the entrepreneur and contacts of the entrepreneur found in the entrepreneur data;   storing the entrepreneur data from the plurality of network modalities as unstructured data; and   performing a dynamic measurement of engagement between the entrepreneur and the contacts by looking for contacts between the entrepreneur and the contacts that cross the plurality of network modalities including social media, phone records, SMS messages, and email messages, the dynamic measurement comprising an entrepreneur score for the entrepreneur.   
     
     
         15 . The method according to  claim 13 , further comprising determining a best performing group of the groups based on the distance. 
     
     
         16 . A method, comprising:
 predicting a likelihood of an individual successfully conducting one or more business transactions by scoring features of the individual from entrepreneur data collected from a plurality of network modalities, as well as a social-network structure for the individual and business event information; and   performing a business transaction with the individual when scored features meet or exceed thresholds for conducting the business transaction.   
     
     
         17 . The method according to  claim 16 , wherein the scored features are compared against scored features of other successful individuals in similar business transactions.