A Deep Learning-Based Approach for Predicting the Outcome of H-1B Visa Application
暂无分享,去创建一个
The H-1B is a visa that allows US employers to employ foreign workers in specialty occupations. The number of H-1B visa applicants is growing drastically. Due to a heavy increment in the number of applications, the lottery system has been introduced, since only a certain number of visas can be issued every year. But, before a Labor Condition Application (LCA) enters the lottery pool, it has to be approved by the US Department of Labor (DOL). The approval or denial of this visa application depends on a number of factors such as salary, work location, full-time employment, etc. The purpose of this research is to predict the outcome of an applicant’s H-1B visa application using artificial neural networks and to compare the results with other machine learning approaches.
[1] M. Boyd. Recruiting High Skill Labour in North America: Policies, Outcomes and Futures , 2014 .
[2] Jimmy Ba,et al. Adam: A Method for Stochastic Optimization , 2014, ICLR.
[3] Yoshua Bengio,et al. Deep Sparse Rectifier Neural Networks , 2011, AISTATS.
[4] Axel Dreher,et al. Student Flows and Migration: An Empirical Analysis , 2005, SSRN Electronic Journal.
[5] S. Seo. A Review and Comparison of Methods for Detecting Outliers in Univariate Data Sets , 2006 .