Student absenteeism is not only an administrative issue, but also reflects discipline and motivation to learn, which affect academic achievement. Unfortunately, in many schools, absenteeism data is still only recorded without further analysis. Researchers are interested in examining how data mining techniques can be used to reveal patterns of absenteeism and its relationship to learning achievement. This study was conducted at SMA Negeri 7 Palembang using data from 318 eleventh-grade students in the 2024/2025 academic year. The analysis was carried out through data pre-processing, classification label formation, and the application of the K-Nearest Neighbor (KNN) and Logistic Regression algorithms. The results show that both algorithms are capable of predicting achievement categories with high accuracy, namely 95.83%. KNN with a K value of 3 is more balanced in recognizing high-achieving students (F1-score 0.75), while Logistic Regression excels in precision (1.00) but has lower recall (0.56). Regression interpretation shows that each additional absence reduces the probability of a student achieving high performance by 0.74 times. These findings confirm that absenteeism is not just a number, but an important factor that can affect academic achievement. Therefore, schools are advised to utilize attendance and absenteeism data not only for administration, but also as an academic monitoring system so that learning strategies can be more targeted.
Keywords: Data Mining, Absence, Academic Achievement, KNN, Logistic Regression