Enhancing Academic Excellence Using a Data-Driven Approach for NIRF Ranking Improvement of Newly Established IITs

In this paper, we discuss the urgent need for better evaluation techniques in educational institutions, concentrating about 10 recently founded Indian Institutes of Technology (IITs). We point out that conventional bibliometric measures fall short of adequately expressing the research influence and capacities of these universities. In order to improve the rankings of these IITs in the National Institutional Ranking Framework (NIRF), we suggest a novel method to evaluate their academic output and impact using data analytics and altmetrics. Here we compare Scopus publishing figures against NIRF rankings over many years. Furthermore, we advocate a thorough evaluation strategy including social media metrics and other kinds of scholarly influence outside conventional references. Here we introduce ResNet-PSO, a deep learning technique whereby Particle Swarm Optimisation (PSO) is coupled with Residual Neural Networks (ResNet) to improve the accuracy and efficiency of our research. By means of ResNet-PSO for data analytics, we can obtain significant insights from extensive academic datasets, so augmenting a more complete knowledge of research trends and impact variables. Our work intends to provide academic institutions and legislators important insights to promote research quality and competitiveness by bridging the gap between current metrics and developing altmetrics.