<![CDATA[The determination of high-achieving students in schools is often conducted manually and subjectively, which may lead to inaccuracies in the decision-making process. Therefore, a method capable of supporting objective and data-driven assessment is required. This study aims to apply data mining techniques using the multiple linear regression method to predict high-achieving students based on academic performance data. The dataset used in this study consists of students' academic scores from SD Negeri Tlogotirto 2 for the first semester of the 2025/2026 academic year, including scores in Islamic Religious Education, Pancasila and Civic Education (PPKn), Indonesian Language, Mathematics, and Visual Arts as the independent variables, while the average score serves as the dependent variable. This research employed a quantitative approach following the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework, which comprises six stages: business understanding, data understanding, data preparation, modeling, evaluation, and deployment. The data were analyzed using IBM SPSS Statistics to develop a multiple linear regression model. The results indicate that the proposed model demonstrates a strong ability to explain the relationship between the independent and dependent variables, as evidenced by a high coefficient of determination (R²). Furthermore, the analysis reveals that the subject-specific academic scores have a statistically significant influence on students' academic achievement. The multiple linear regression method can therefore be utilized as an objective and systematic decision-support tool for predicting high-achieving students. The resulting model is expected to assist schools in making more accurate decisions and improving the quality of students' academic evaluation.]]>
