Determining Standard Occupational Classification Codes from Job Descriptions in Immigration Petitions

TL;DR

This paper explores NLP-based methods to automate the assignment of Standard Occupational Classification codes from job descriptions in immigration petitions, aiming to streamline and improve accuracy in the process.

Contribution

It introduces and empirically evaluates various NLP models for automatically determining SOC codes from job descriptions, identifying the most effective approaches.

Findings

Certain NLP models outperform others in prediction accuracy.

The best models balance prediction quality with training efficiency.

Automated SOC code determination can reduce manual effort and errors.

Abstract

Accurate specification of standard occupational classification (SOC) code is critical to the success of many U.S. work visa applications. Determination of correct SOC code relies on careful study of job requirements and comparison to definitions given by the U.S. Bureau of Labor Statistics, which is often a tedious activity. In this paper, we apply methods from natural language processing (NLP) to computationally determine SOC code based on job description. We implement and empirically evaluate a broad variety of predictive models with respect to quality of prediction and training time, and identify models best suited for this task.