Intelligent Framework for Predicting Institute Rankings

The National Institutional Ranking Framework (NIRF), implemented by the Ministry of Education, Government of India, has brought about a paradigm shift in evaluating Higher Educational Institutions (HEIs) across India. This innovative framework establishes an equitable and standardized platform for assessing and ranking institutions based on specific parameters. NIRF rankings provide essential insights into an institute's national standing, revealing both strengths and weaknesses. Witnessing the earnest efforts of various institutions to comprehend and elevate their rankings, our research was sparked with the motivation to contribute to this process by refining and optimizing it. In the context of our technical journal contribution, we unveil pioneering strategies focused on the analysis of NIRF rankings, forecasting their implications, and guiding institutes, including our own, in formulating targeted improvement plans. The essence of our research lies in the extraction and analysis of diverse data from sources covering NIRF ranks, parameters, grading scales, weightages, and external references. Our primary goal is to develop a precise predictive model using Machine Learning, accurately forecasting NIRF ranks, and providing customized strategies based on input from individual institutions. The journey commences with a comprehensive understanding of the parameters influencing rankings, encompassing transparent “white box” elements and more elusive “black box” factors. Through meticulous data collation, we have curated an exhaustive dataset, empowering us to analyze trends and explore the effects of parameter variations. Subsequently, we have engineered a robust model using this extensive dataset, rigorously analyzing its performance, and refining it through testing, feedback analysis, and iterative rebuilding to align with the objective of predicting scores for different parameters judged in NIRF rankings.