The growing complexity of the modern job market has created a significant disconnect between the skills that candidates possess and the competencies that employers demand. Addressing this challenge, this paper presents TalentMap — an intelligent, end-to-end platform that leverages Natural Language Processing (NLP) and supervised Machine Learning to automate resume analysis, identify skill deficiencies, and predict the most suitable career paths for job seekers. When a user uploads a resume in PDF or DOCX format, the system parses its content, extracts structured information such as technical skills, academic qualifications, and work experience, and maps this information against a curated repository of job-role requirements. A multi-algorithm prediction pipeline — incorporating Naive Bayes, Logistic Regression, and Support Vector Machine classifiers — assigns the candidate to a matching role and computes a quantitative job-fit score. The platform then generates a personalized skill gap report, recommends targeted learning resources and industry certifications, and highlights top-hiring organizations along with estimated selection probabilities. An interest-driven module further allows users to explore alternative career domains by dynamically retrieving up-to-date skill requirements through live web queries. The system is deployed as a lightweight web application built with Flask, making it accessible to students, fresh graduates, and academic counselors without requiring any technical expertise. Experimental validation on a curated dataset demonstrates that the SVM classifier achieves the highest prediction accuracy of 88.2%. TalentMap provides a transparent, inclusive, and data-driven solution to bridge the widening skills gap in today's competitive employment landscape.

Keywords — Skill Gap Analysis; Career Prediction; Resume Parsing; Natural Language Processing; Machine Learning; Recruitment Analytics; Flask Web Application