Retrieval Augmented Generation for Relational Mapping of Resume Data for Improved Analysis

Analysis of resume data is often a critical and time-intensive process that requires extensive metadata. However, a lack of consistency and scalability often leads to inefficiencies and errors in the recruitment process. Tools like Applicant Tracking Systems (ATS) often struggle with the contextual understanding of resume data, as they evaluate each resume in isolation without considering its relations to other similar resumes. We proposes the implementation of a Retrieval-Augmented Generation (RAG) architecture to create a vector relational mapping of resume data based on several curated parameters, such as skills, experiences, and education. This approach enables the system to understand the contextual relations between different resumes, helping the system evaluate them more effectively within a broader context, and improve recruitment outcomes by reducing biases and increasing efficiency.