Resume Screening and Ranking using Convolutional Neural Network

Manual filtering becomes a tedious task for the recruiter as there are thousands of candidates applying for a single job posting. In this paper, a Long Short-term Memory (LSTM)-based and Convolutional Neural Network (CNN)-based approach are introduced for categorizing resumes submitted by candidates. Along with proposed CNN and LSTM model, also implemented other baseline models such as Random Forest, K-nearest neighbor, and Support Vector Machine. The resumes of the candidates and the job description are compared using Cosine Similarity. The list of job applicants is ranked based on the percentage obtained by Cosine Similarity.