CAMPUSLINK: Placement Season Without the Spreadsheet Tandav

• The system should use AI, machine learning, NLP, recommendation systems or generative AI to analyse student profiles, recruiter requirements and historical placement data. It should not merely digitise records — it should provide student readiness and employability scoring, skill-gap analysis against target roles, recruiter-student matching and ranking, conflict-free drive scheduling, offer and documentation tracking, and predictive analytics on placement outcomes
• Student readiness profiling built from resumes, academic records, certifications, projects, aptitude and mock-interview scores, communication and soft-skill assessments, branch, CGPA and backlog history — surfacing skill gaps and low readiness before a student reaches a recruiter
• Recruiter requirement matching by parsing job descriptions and eligibility criteria, then scoring candidates on skill and stack fit, branch and CGPA eligibility, certification and project relevance, and past interview performance, with a fit score and stated reasons for inclusion or exclusion
• Drive scheduling and conflict management covering overlapping drives, venue and resource double-booking, students shortlisted for simultaneous drives, and panel and infrastructure availability
• Offer and documentation tracking across offer letters and CTC, bonds, verification status, PPOs and internship conversions, and offer acceptance, deferral or withdrawal
• Analytics and predictive insight on branch-wise and skill-wise conversion, salary and package trends, students at risk of remaining unplaced, and recruiter engagement and repeat hiring
• Communication automation replacing manual email and WhatsApp coordination for shortlists, schedules, document deadlines, offer updates and drive announcements
• Readiness scoring and explainability: assign each student-recruiter pairing a level such as Not Ready → Developing → Ready → Highly Employable, and explain the major factors. Instead of "Not Shortlisted", the system should say something like: below threshold, because CGPA meets eligibility but the required skill set shows a gap in cloud technologies and the mock-interview score sits under the recruiter's benchmark. Recruiter-side rankings should be explained the same way
• Workflow automation may include: auto-scheduling around detected conflicts, auto-shortlisting on eligibility and fit score, personalised preparation recommendations, automated documentation reminders, escalation of at-risk students to mentors, and recruiter follow-up prompts on pending offers
• Innovation opportunities: generative-AI-assisted resume and profile building, AI mock interviews and communication analysis, a chatbot eligibility assistant, predictive at-risk identification, embedding or vector-search based matching, explainable shortlisting, real-time conflict detection, blockchain-based offer verification, job-portal API integration, gamified preparation, mobile alerts and multi-campus analytics aggregation
• Minimum expected prototype: demonstrate at least three core capabilities — preferably one covering readiness profiling and skill-gap analysis, one covering recruiter-student matching and drive scheduling, and one covering analytics, predictive insight and offer tracking — running the chain of profiling, matching, scheduling, notification, offer tracking and analytics

For the Grand Finale, your build should include:

• A working prototype with a student readiness and employability scoring mechanism, including skill-gap analysis
• Recruiter-student matching demonstrated across at least three simulated drives, with explainable shortlisting output and fit scores
• A conflict-aware drive scheduling mechanism plus automated notification workflow
• A placement monitoring dashboard with offer and documentation tracking, conversion rates, package trends and at-risk student identification
• Technical documentation: system architecture, models and algorithms used, accuracy and performance evaluation of matching and scoring on simulated or public datasets, and the multi-campus scalability and deployment approach

The Grand Finale is judged on:

• Quality of readiness profiling, skill-gap analysis and employability scoring — 25%
• Accuracy and explainability of recruiter-student matching and ranking — 25%
• Conflict-aware scheduling, notification and offer/documentation workflow — 20%
• Analytics and predictive insight, including at-risk student identification — 20%
• Architecture, scalability across campuses and demo quality — 10%