Automation Process for Learning Outcome Predictions

This paper presents a comprehensive study on the evaluation of algorithms for automating learning outcome predictions, with a focus on the application of machine learning techniques. We investigate various predictive models (logistic regression, random forest, gaussian naive bayes, k-nearest neighbors and support vector regression) to assess their efficacy in forecasting student performance in educational settings. Our experimental approach involves the application of these models to predict the outcomes of a specific course, analyzing their accuracy and reliability. We also highlight the significance of an automation process in facilitating the practical application of these predictive models. This study highlights the promise of machine learning in advancing educational assessment and paves the way for further investigations into enhancing the adaptability and inclusivity of algorithms in various educational settings.