This study presents the development of a novel automated systemRapid Analysis and Detection of At-risk students with Artificial intelligence-based Response (RADAR)that utilizes explainable artificial intelligence (XAI) to identify students who are at risk of falling behind or dropping out of school. The system integrates various featuresincluding learners' personalityprevious academic performancecurrent academic concepts progressand soft skills. Machine learning algorithms are utilized to analyze the combination of data and identify patterns that predict a student's likelihood of falling behind. The proposed RADAR system employs a multi-modal approachconsidering the learner's features. The system is trained on a dataset of students from a school districtwhere the data is collected and preprocessed accordingly. The feature selection algorithm is applied to identify the most relevant features that can accurately predict students at-risk of falling behind or dropping out. The pilot study establishes the framework of the system and examines the implementation implications. The results of this study indicate that the RADAR system achieves high accuracy in identifying at-risk students. Furthermorethe system effectively employs the identified features to predict students' performance in a continuous mannerenabling advisorsadministratorsand students to take proactive measures to maintain high academic progress levels. The system is designed to provide an automated and continuous monitoring of the students' performanceand to notify the relevant parties in case of any deviations. The proposed system represents an innovative approach to using XAI for the detection and support of at-risk studentsenabling educators to take timely actions. The results of this study demonstrate the potential of the RADAR system to improve the support and guidance provided to at-risk studentsand to ultimately improve their academic outcomes.
