# Who Gets the Job and How are They Paid? Machine Learning Application on H-1B Case Data

## TL;DR

This study applies machine learning to analyze H-1B visa application data from 2008-2018, revealing factors influencing wages and certification likelihood among international workers in the US labor market.

## Contribution

It introduces a machine learning approach to identify key features affecting salary and approval chances in H-1B applications, providing stylized facts about international workers.

## Key findings

- Healthcare industry and California increase wages.
- Ph.D. degrees and retail/finance jobs improve certification chances.
- Education sector and lower degrees are linked to rejection.

## Abstract

In this paper, we use machine learning techniques to explore the H-1B application dataset disclosed by the Department of Labor (DOL), from 2008 to 2018, in order to provide more stylized facts of the international workers in US labor market. We train a LASSO Regression model to analyze the impact of different features on the applicant's wage, and a Logistic Regression with L1-Penalty as a classifier to study the feature's impact on the likelihood of the case being certified. Our analysis shows that working in the healthcare industry, working in California, higher job level contribute to higher salaries. In the meantime, lower job level, working in the education services industry and nationality of Philippines are negatively correlated with the salaries. In terms of application status, a Ph.D. degree, working in retail or finance, majoring in computer science will give the applicants a better chance of being certified. Applicants with no or an associate degree, working in the education services industry, or majoring in education are more likely to be rejected.