Enhancing Student Performance through Adaptive Knowledge Assessment: A Bayesian Optimization Approach

-The contributions of educational data mining are essential to the growth of the educational setting as a whole because they apply state-of-the-art methods, techniques, and applications. This recent development in data mining and machine learning gives helpful tools for investigating the educational environment. Modern academic institutions are very competitive and convoluted. Analysis of performance, methods of assessing students' work, providing outstanding instruction, and future planning are some of the most serious issues facing educational institutions today. These institutions should develop student intervention programs to aid students having difficulties in the classroom. Data preparation, feature selection, and model training are the three methods on which the proposed approach stands. The purpose of data preprocessing is to enhance the data's quality and tailor it to the data mining task at hand. Feature selection involves picking the features that matter most for training the model. Next, let utilize KNN-RF to train the models. When compared to the two most popular alternatives, KNN and RF, the proposed technique is clearly superior. The success rate of the proposed approach was 95.26 percent.