Academic achievement is influenced by a complex interplay of factors, including students’ prior educational backgrounds and socio-cultural environments. Understanding and quantifying these drivers necessitates large-scale data collection and robust analytical methodologies. Principal Component Analysis (PCA), a multivariate statistical technique, offers a powerful tool for processing and simplifying high-dimensional datasets. By transforming correlated variables into a reduced set of uncorrelated principal components, PCA enables researchers to capture the underlying variance in the data with improved efficiency. Although widely applied in disciplines such as environmental science and medicine, its application in educational research remains relatively underexplored, suggesting promising avenues for methodological advancement. This study aims to evaluate the relationship between student attendance and academic performance using the multivariate statistical tool called Principal Component Analysis (PCA). Data were collected from students enrolled in a Bachelor's degree in Food Engineering at the Technical University of Madrid during the 2024/25 academic year. Variables such as class attendance, exam participation, and academic outcomes were included in the analysis. A matrix of 20 variables x 139 observations (students) was built up. PCA was performed with STATGRAPHICS software, standardizing data to zero mean and unit variance. Eigenvalues and the amount of variance explained by each principal component (PC) were calculated. The number of components retained in the analysis was assessed by Cattel’s scree plot. The value of the eigenvectors and loadings of variables with PCs were computed. The coordinates of each observation with the first four Principal Components were obtained, and these data were analyzed by Cluster Analysis. PCA revealed significant differences between students. Four principal components explained 79.8% of the variance, highlighting the impact of absenteeism, participation in evaluation activities, and academic performance. Cluster analysis identified distinct student groups based on attendance and performance patterns. The findings suggest that regular class attendance is strongly correlated with higher academic success. PCA proved to be an effective tool for identifying key factors affecting academic performance, and future research should integrate machine learning techniques to enhance these insights.

Keywords: Academic performance, attendance, principal components analysis, multivariate analysis, academic indicators.