EquiGrade: An AI-Driven Cross-Board Mark Normalization System
Gemini said EquiGrade is an AI-powered normalization platform that equates marks across different educational boards by analyzing question paper difficulty and percentile distributions. It ensures a fair merit list for counseling by mathematically balancing a student's performance against the specific toughness of their respective board's syllabus.
EquiGrade: An AI-Driven Cross-Board Mark Normalization System aims to create a fair meritocratic framework is for student counseling by addressing the "scoring disparity" between different educational boards (e.g., CBSE, State Board, ICSE). Currently, admission systems often treat raw marks as equal, ignoring that a 95% in a rigorous, application-based board may represent a higher level of competency than a 98% in a rote-learning-heavy board.
The system moves beyond simple linear scaling. It utilizes Machine Learning to calculate a Question Paper Difficulty Index (QPDI) by scanning and analyzing board exam papers using Natural Language Processing (NLP). It categorizes questions based on Bloom’s Taxonomy (Knowledge vs. Application vs. Synthesis). Simultaneously, it applies Statistical Percentile Equating to compare how a student performed relative to their specific peer group. The final output is a Normalized Competency Score (NCS) that provides a common ground for universities to rank students from diverse backgrounds without bias.
Imagine two students, Arjun and Sneha, both aiming for a Computer Science seat at a top government-aided college.
Arjun (State Board): He scores 198/200. His question paper was relatively straightforward, following a predictable pattern. Many students in his board scored above 195.
Sneha (CBSE): She scores 192/200. However, her physics and math papers were exceptionally tough this year, focusing on deep application-based problems. In her board, 192 is considered an elite score (Top 1%).
The TNEA Reality: Currently, TNEA considers the Raw Cut-off. Arjun (198) gets the seat. Sneha (192) misses out on all top-tier colleges because the cut-off for her dream college closed at 196.
The Consequence (Management Quota): Even though Sneha might be technically more proficient or better prepared for an engineering curriculum, she is forced to either take a seat in a low-ranking college or pay ₹10-15 Lakhs in Management Fees to get a seat in a good private college. This creates financial stress and an unfair advantage for those who have money over those who have merit.