Machine learning systems and methods for predictive engagement

Abstract

A machine learning (ML) process can include teaching, with a teaching set, a first ML algorithm to generate one or more machine-predicted results. One or more weights can be generated based on the one or more machine-predicted results and the teaching set. A second ML algorithm can be generated based on the one or more weights. Via the second ML algorithm, one or more machine-learned results can be generated. A description of one or more candidates can be received. Based on the one or more machine-learned results, a respective likelihood of interest in a CCG class of positions for each of the one or more candidates can be generated. A respective communication can be transmitted to each of a subset of the one or more candidates open to the respective likelihood of interest in the CCG class of positions for the subset above a threshold.

What is claimed is: 
     
         1 . A machine learning process comprising:
 generating a machine learning algorithm to predict a likelihood of a candidate as being a contract, contingent, or gig (CCG) based position holder;   generating a training set including known CCG-based position holders and known non-CCG-based position holders;   generating, via the machine learning algorithm, one or more machine-learned results;   improving accuracy of the machine learning algorithm with the training set by reconfiguring the machine learning algorithm to reduce an error metric based on a comparison between the one or more machine-learned results and known results;   receiving a description of one or more candidates;   generating, via the machine learning algorithm, a respective likelihood of interest in a CCG class of positions for each of the one or more candidates; and   generating a respective communication to each of a subset of the one or more candidates open to the respective likelihood of interest in the CCG class of positions for the subset above a threshold.   
     
     
         2 . The machine learning process of  claim 1 , further comprising:
 receiving a set of candidate parameters for a particular position, the particular position corresponding to the CCG class of positions; and   processing the set of candidate parameters to identify one or more candidates from a set of candidates that meet the set of candidate parameters.   
     
     
         3 . The machine learning process of  claim 1 , further comprising:
 generating a ranking of the subset of the one or more candidates based on the respective likelihood of interest in the CCG class of positions; and   generating a communication based on the ranking of the subset.   
     
     
         4 . The machine learning process of  claim 1 , further comprising:
 generating particular language designed to provoke a response from each of the subset of the one or more candidates; and   generating one or more strings of text via natural language processing for the respective communication for each of the subset of the one or more candidates, wherein the one or more strings of text comprise language are based on the particular language.   
     
     
         5 . 
     
     
         6 . The machine learning process of  claim 1 , further comprising:
 receiving an indication that a particular candidate of the one or more candidates does not prefer the CCG class of positions;   subsequent to receiving the indication, generating a change in a profile associated with the particular candidate;   generating that the change in the profile increases a likelihood of interest in the CCG class of positions more than or equal to a threshold amount; and   in response to the change increasing the likelihood of interest more than or equal to the threshold amount, adjusting the profile to facilitate communication with the particular candidate.   
     
     
         7 . The machine learning process of  claim 1 , wherein the description of the one or more candidates is extracted from at least one of media and investigative information. 
     
     
         8 . A machine learning system comprising:
 a device configured to:   generate a machine learning algorithm to predict a likelihood of a candidate as being a contract, contingent, or gig (CCG) based position holder;   generate a training set including known CCG-based position holders and known non-CCG-based position holders;   generate, via the machine learning algorithm, one or more machine-learned results;   improve accuracy of the machine learning algorithm with the training set by reconfiguring the machine learning algorithm to reduce an error metric based on a comparison between the one or more machine-learned results and known results; and   analyze, via the machine learning algorithm, a respective likelihood of interest in a CCG class of positions for each of the one or more candidates.   
     
     
         9 . The machine learning system of  claim 8 , wherein the at least one device is further configured to exclude any candidates from the one or more candidates that does not meet a predefined threshold. 
     
     
         10 . The machine learning system of  claim 8 , wherein the at least one device is further configured to generate a respective communication to each of a subset of the one or more candidates open to the respective likelihood of interest in the CCG class of positions for the subset above a threshold. 
     
     
         11 . The machine learning system of  claim 10 , wherein the at least one device is further configured to:
 analyze a respective result associated with the respective communication for each of the subset of the one or more candidates; and   transform another training set based on the respective result for each of the subset of the one or more candidates.   
     
     
         12 . A machine learning system comprising:
 memory; and   at least one device in communication with the memory, the at least one device being configured to:   generate a machine learning algorithm to predict a likelihood of a candidate as being a contract, contingent, or gig (CCG)-based position holder;   generate a training set including known CCG-based position holders and known non-CCG-based position holders;   generate, via the machine learning algorithm, one or more machine-learned results;   improve accuracy of the machine learning algorithm with the training set by reconfiguring the machine learning algorithm to reduce an error metric based on a comparison between the one or more machine-learned results and known results;   analyze, via the machine learning algorithm, a respective likelihood of interest in a CCG class of positions for each of one or more candidates; and   generate a respective communication to each of a subset of the one or more candidates open to the respective likelihood of interest in the CCG class of positions for the subset above a threshold.   
     
     
         13 . The machine learning system of  claim 12 , wherein the at least one device is further configured to:
 analyze a respective result associated with the respective communication for each of the subset of the one or more candidates; and   transform another training set based on the respective result for each of the subset of the one or more candidates.   
     
     
         14 . The machine learning system of  claim 12 , wherein the at least one device is further configured to:
 receive a set of candidate parameters for a particular position, the particular position corresponding to the CCG class of positions; and   process the set of candidate parameters to identify a candidate subset of the one or more candidates that meets the set of candidate parameters, wherein the subset of the one or more candidates are selected from the candidate subset.   
     
     
         15 . The machine learning system of  claim 12 , wherein the at least one device is further configured to:
 receive the respective likelihood of interest in the CCG class of positions for the one or more candidates;   analyze, for each candidate, if the respective likelihood of interest for a subset of the one or more candidates meets a threshold for a particular position; and   generate and transmit, to a profile associated with the particular position, a description of the subset of the one or more candidates that meet the threshold.   
     
     
         16 . The machine learning system of  claim 12 , wherein the at least one device is further configured to exclude any candidates from the one or more candidates that does not meet a predefined threshold.