Published Paper Details:

In contemporary education, pupils' academic performance must be predicted correctly. Logistic Regression and Random Forest are examples of machine learning algorithms that can effectively predict students who are more likely to fail. Logistic Regression is used for the assessment and prediction of such issues as timely interventions and customized care which address multiple factors in a student's life. Conversely, Random Forest may handle big data sets well because its precision is remarkable. With a population of 480 students sampled from Kalboard360, this study compares logistic regression and random forest about demographic, educational or behavioral features. The findings reveal the effectiveness of both approaches: Logistic regression has an 81% accuracy rate with some space for improvement while Random Forest has a classification accuracy rate of 89% which shows that it can categorize different student outcomes. Such insights from these algorithms have informed tailored interventions aimed at highlighting the significance of employing Machine Learning techniques within the academic arena and understanding their strengths as well as weaknesses for successful strategies.