Strategizing University Rank Improvement using Interpretable Machine Learning and Data Visualization
This work addresses the challenge for universities and HEIs in strategically planning rank improvements, though it is incremental as it applies existing methods like Decision Trees to a specific domain.
The paper tackles the problem of helping higher education institutions improve their annual global rankings by using interpretable machine learning and data visualization to analyze ranking data and derive actionable decision paths, with results including quantified certainty measures for these paths using Laplace correction.
Annual ranking of higher educational institutions (HEIs) is a global phenomenon and have significant impact on higher education landscape. Most of the HEIs pay close attention to ranking results and look forward to improving their ranks. However, maintaining a good rank and ascending in the rankings is a difficult task because it requires considerable resources, efforts and performance improvement plan. In this work, firstly, we show how exploratory data analysis (EDA) using correlation heatmaps and box plots can aid in understanding the broad trends in the ranking data. Subsequently, 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 Universities and HEIs to quantitatively assess the scope of improvement, adumbrate a fine-grained long-term action plan and prepare a suitable road-map.