Job assignment optimization

A system, comprising:

• a memory having computer readable instructions;
• and
• a processor for executing the computer readable instructions, the computer readable instructions including:
• generating a job feature vector from features extracted from a new job request, each of the features associated with a constraint on minimum requirements with respect to a level of experience of a potential candidate for assignment to the new job request;
• for each employee in an employee database, generating an employee feature vector that includes skills attributed to the employee and a number of instances that each of the skills has been completed by the employee;
• searching employee feature vectors generated from the employee database for the minimum requirements indicated in the feature vector generated from the new job request;
• searching the employee feature vectors generated from the employee database for the minimum requirements indicated by constraints associated with the features in the new job request;
• modeling aggregate utility of past experience of employees as a weighted sum of applied utility functions, wherein the utility functions factor in features extracted from predicted future job requests, and
• wherein the features extracted from the new job request indicate a range of monetary values associated with the job;
• generating, based on the modeling, a score indicating a difference between a potential post assignment utility and a pre-assignment utility;
• outputting a list of qualified candidates that are ranked according to the score, the ranking, upon completion of the new job, furthering a balance in experience levels of the employees with respect to skills associated with the minimum requirements;
• accessing one or more past jobs from a past jobs database;
• generating, by a machine learning model, a demand feature vector comprising one or more features extracted from the one or more past jobs;
• determining an anticipated demand from the demand feature vector by plotting the demand feature vector in a feature space of the machine learning model;
• and
• updating the list of qualified candidate based at least in part on the anticipated demand;
• augmenting a job bidding tool based on the updating the list of qualified candidates.

A computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a computer processor to cause the computer processor to perform a method comprising:

• generating a job feature vector from features extracted from a new job request, each of the features associated with a constraint on minimum requirements with respect to a level of experience of a potential candidate for assignment to the new job request;
• for each employee in an employee database, generating an employee feature vector that includes skills attributed to the employee and a number of instances that each of the skills has been completed by the employee;
• searching the employee feature vectors generated from the employee database for the minimum requirements indicated in the feature vector generated from the new job request;
• searching the employee feature vectors generated from the employee database for the minimum requirements indicated by constraints associated with the features in the new job request;
• modeling aggregate utility of past experience of employees as a weighted sum of applied utility functions, wherein the utility functions factor in features extracted from predicted future job requests, and
• wherein the features extracted from the new job request indicate a range of monetary values associated with the job;
• generating, based on the modeling, a score indicating a difference between a potential post assignment utility and a pre-assignment utility;
• outputting a list of qualified candidates that are ranked according to the score, the ranking, upon completion of the new job, furthering a balance in experience levels of the employees with respect to skills associated with the minimum requirements;
• accessing one or more past jobs from a past jobs database;
• generating, by a machine learning model, a demand feature vector comprising one or more features extracted from the one or more past jobs;
• determining an anticipated demand from the demand feature vector by plotting the demand feature vector in a feature space of the machine learning model;
• and
• updating the list of qualified candidate based at least in part on the anticipated demand;
• augmenting a job bidding tool based on the updating the list of qualified candidates.