Forecasting Student Achievement: Exploring Data Mining Techniques in Education
Author : Dr. Nedendla Satyavathi and Dr. Eppakayala Balakrishna
Abstract :
The capability to forecast the performance trends of the students holds great significance in the field of education. Predictive analytics, using various data-driven methods, can help educators and institutions identify struggling students early on, tailor teaching methods to individual learning styles, and implement targeted interventions to improve overall academic outcomes. The suggested Data Mining (DM) methods for predicting the final grades of students using their past data are a valuable and realistic approach in the field of education. DM is a powerful method that involves the discovery of patterns and relationships within large datasets, and it can be particularly beneficial in predicting student performance and understanding the factors that influence academic outcomes. The use of three eminent DM methods (Naive Bayes, Random Forest, and Decision Tree) in experimental studies on two educational data-sets can yield precious approaching into student performance and academic outcomes. This result indicates that data mining methods can be valuable tools for educators and educational institutions to gain deeper insights into student outcomes and make informed decisions to improve teaching and learning practices.
Keywords :
DM, student performance forecast, and classification
