Hello!
I’m working on a CV parsing project and a Candidate Ranking model for jobs. It’s a tool that helps companies to parse CVs and rank candidates based on their needs easily. What form of data should I use for CV parsing? Candidate Ranking is an AI model that recommends best-fit candidates for this job based on their CVs. What form of input data should I use for this kind of task? I’d appreciate it if you recommend a dataset I can begin with.
Given that CV data is highly personal, i doubt any public datasets are available.
In the recruitment website, resumes are recommended according to the positions posted by the company, and most recruitment websites make recommendations based on NLP and resume activity. You can go through the company’s recruitment department, and they will receive a lot of resumes under a certain position. If you’re working for a large business, you might get thousands of resumes for a sought-after position. This amount should be enough for you to do AI training.