Unveiling Patterns Using Enhanced Educational Data Mining for forecasting Student Academic Performance

The capacity of EDM models to forecast students' performance in the future based on their historical data is essential to their effectiveness. This concept has led to the development of classification models by several academics that are able to forecast the currently unknown labels of future cases. The machine learning-based EDM method consists of multiple steps. The three primary techniques of EDM are features selection, classification, and data categorization. Predictive analytics can be performed via machine learning techniques as well as human methods. Future predictions are invariably based on historical evidence. As its name suggests, it seeks to forecast the expected course of events. It begins to produce data-driven, actionable insights that the business may use to guide its next steps. This article presents a student performance forecasting model using the educational data mining. In this model, features are selected using the Correlation-based Feature Selection. Then classification is performed by Support Vector Machine and Linear Regression techniques. The dataset is collected from educational data from the Learning Management System (LMS) Kalboard 360. Experimental results have shown that the accuracy of CFS-SVM is 99.10 Percent.