Resource Matching Optimization Problem

This resource matching optimization demo combines machine learning and MIP technologies to address the fundamental problem of resource management-providing workforce resources with the right skills and capabilities, for the right job, at the right time, location, and cost.

 

Introduction to the Resource Matching Optimization Problem 

Large professional services companies employ thousands of professionals making labor the industry’s highest expense. Examples of industries where professional service firms are commonly used include: Information technology outsourcing, Business process outsourcing, Accounting, Legal, Advertising, Engineering, and other specialized services.

Companies are using Machine Learning to automatically compute the matching score between resources and jobs, but the actual assignment is done manually which leads to poor demand fulfillment and low labor resource utilization, high project delivery costs and low customer satisfaction

The integration of Machine Learning (ML) and Mixed Integer Programming (MIP) is essential to solve Resource Matching Optimization problem effectively:

    • Machine Learning addresses the scoring of resources and jobs, but alone cannot address the complex combinatorial nature of the assignment problem
    • MIP addresses the complex combinatorial nature of the assignment problem, but alone would require a human to provide a large number of matching scores, making the approach impractical

Problem Statement

The goal is to find an assignment of resources to jobs that maximizes the total matching score of resources and jobs, while satisfying the requirements of jobs and the availability of resources. There is a matching score for each resource and job combination

We now dive into the RMO demo itself, starting with a simple scenario. This scenario considers 62 confidential resumes from the Recruitology dataset, four non-confidential resumes, and a matching number of randomly generated jobs. The weights for the job attributes are: {Role: 45%, Technology: 35%, Domain: 20%}. For this scenario, we have disabled three resources and defined more data science job as high priority with a minimum matching score requirement of 100%. Also, we allow at most one new resource to be hired.

The “Assignment Quality” KPI (76.2%) measures the average matching score of all the assignments.

Typically, business conditions change frequently and an algorithm that was once efficient for solving the problem no longer works when new business conditions are considered. This illustrates one of the greatest advantages of using a Mixed Integer Programming approach to solve business problems as opposed to using heuristic or Hungarian method.

The new business conditions can be easily considered by adding new variables and constraints to the MIP model and then calling the Gurobi Solver to find a solution that recommends the best course of action. Our RMO MIP model requires us to quantify how well a resource profile (resume) meets a job’s requirements.

To access the resource matching optimization application and create your scenario using your own data from a blank template or to play with existing default scenarios just register at www.gurobi.com and go to https://demos.gurobi.com/rmo. Please access the video above and also this whitepaper to read full instructions on how to use the optimization application demo.

Access the two contents below and get full instructions to create your own resource matching problem scenario

Contact Us

We’re happy to assist you. Please contact us using this form, and a Gurobi representative will get back to you shortly.

  • Free Consultations
  • General Inquiries
  • Gurobi Optimizer Questions

Can’t view the form? Please email us at sales@gurobi.com.

Thank you! The information has been submitted successfully.