Neural Network-Driven Resume Skill Inflation Detection Using NLP and Source Code Repositories

Inflation in resumes has been a major issue in recruitment, and in most cases, a candidate can exaggerate his technical expertise without any proof. The conventional screening process relies heavily on self-reported skills, which results in ineffective recruitment and skill constraints. In this paper, I suggest an AI-based model to identify skill inflation by matching resume assertions with publicly available developer actions, such as GitHub repositories and professional profile texts. The suggested system is based on the principles of Natural Language Processing (NLP) and its ability to identify purported skills in resumes and compare them to such objective measures as repository originality, commit frequency, and metrics of code quality. A machine learning algorithm is utilized to categorize the resumes as either genuine or inflated. The outcomes of experiments prove the suggested method to be effective in detecting the differences between alleged and proven skills, providing a scalable and automated method for recruitment screening.