Predicting Final Grades in Differential Calculus using Pre-College Profile and ALeKS Grades via Artificial Neural Network

The goal of this study was to develop a predictive model to estimate students' final grades in Differential Calculus using performance in an AI-based personalized learning platform (ALEKS – Assessment and Learning in Knowledge Space) and Senior High School (SHS) status. With the critical need to address low academic performance in mathematics within the Philippine education system, this research leverages Artificial Neural Networks (ANN) with ReLU and Softmax activation functions to create an accurate predictive tool. The ALEKS platform, covering seven key mathematical areas, serves as the data source for this model. The study involved rigorous data preprocessing, feature engineering, and iterative training to optimize the model's accuracy. Integrating technology and data analysis, this research sought to provide educators and administrators with effective tools to identify students at risk of lower grades and implement targeted interventions. Evaluation metrics such as accuracy, precision, and recall are employed to ensure the model's robustness and generalizability. This predictive model not only enhanced educational outcomes in Differential Calculus but also addressed the broader challenges in mathematics education exacerbated by the COVID-19 pandemic. The findings underscore the potential of data-driven strategies in improving student performance and supporting educational reforms to foster better academic achievements in critical subjects like mathematics.