Predictive Analytics for Early Identification and Intervention of At-Risk Students

Multiple Linear Regression Analysis (MLRA) is an analytical approach employed to foretell the value of a dependent variable versus multiple independent variables. It models the linear regression between these variables, tolerating forecasters to understand the impact of each independent variable on the single one while regulating others. This paper leverages predictive analytics to identify at-risk students as early as possible, using a model to predict the dependent variable for new points of analysis. The trend and strength of the linear relationship between the dependent variable and each independent variable are identified. The synthetic data is employed and modeled by a machine learning algorithm to point out some educational indicators. Accuracy of models and effectiveness of interventions are cross-checked and then compared with what had been done manually by human decision. At some points, some predicted results may or may not align with the previous human decision, but an integrated plan so as to achieve timely support for any at-risk students and improve the retention rate is developed from the data-merged decisions.