Utilising a Gaussian process classifier integrating with meta-heuristic optimisers to predict and classify performance systems

This study pioneers academic achievement prediction with a powerful Gaussian process classifier (GPC) model. Advanced optimisation methods like PVSA and smell agent optimisation improve the model's prediction power. These algorithms use machine learning (ML) and bioinspired methods to improve forecasting and decision-making. The main goal is to accurately predict students' comprehensive performance, which improves educational outcomes, especially in higher education, where it helps strategic decision-making and reduce dropout rates. To fully examine the input variables and determine how each component affected student academic performance, machine learning (ML) approaches were used. The research carefully evaluates varied educational datasets using machine learning (ML) to reduce dimensionality. Proactive educators can make data-driven decisions to boost academic performance. By categorising people by their intrinsic strengths and reducing failure rates, the study hopes to improve education. Predictive modelling, especially machine learning (ML), helps the academic community proactively address issues, improving learning environments and student results. The SAO-optimised GPC model outperformed the PVSA-optimised model with 88 correct predictions, as seen by its bigger Area under the receiver operating characteristic (ROC) curve. This shows its high discrimination and performance level classification skills.