Data Driven and Visualization based Strategization for University Rank Improvement using Decision Trees

Annual ranking of higher educational institutes (HEIs) is a global phenomena and past research shows that they have significant impact on higher education landscape. In spite of criticisms regarding the goals, methodologies and outcomes of such ranking systems, previous studies reveal that most of the universities pay close attention to ranking results and look forward to improving their ranks. Generally, each ranking framework uses its own set of parameters and the data for individual metrics are condensed into a single final score for determining the rank thereby making it a complex multivariate problem. Maintaining a good rank and ascending in the rankings is a difficult task because it requires considerable resources, efforts and accurate planning. In this work, we show how exploratory data analysis (EDA) using correlation heatmaps and box plots can aid in understanding the broad trends in the ranking data, however it is challenging to make institutional decisions for rank improvements completely based on EDA. We present a novel idea of classifying the rankings data using Decision Tree (DT) based algorithms and retrieve decision paths for rank improvement using data visualization techniques. Using Laplace correction to the probability estimate, we quantify the amount of certainty attached with different decision paths obtained from interpretable DT models . The proposed methodology can aid HEIs to quantitatively asses the scope of improvement, adumbrate a fine-grained long-term action plan and prepare a suitable road-map.