In light of the emergence of statistical analysis techniques based on data mining in education sciences, and the potential they offer to detect non-trivial information in large databases, this paper presents a procedure used to detect factors linked to academic achievement in large-scale assessments. The study is based on a non-experimental, cross-sectional design and a sample of 18,935 high school students from 99 educational institutions in Baja California state (Mexico). The information was collected from ENLACE tests and context surveys given to students in Baja California. Decision trees were used to apply classification techniques, and the results indicate that personal factors are most indicative of academic performance, followed by school-related and social factors. In conclusion, the paper discusses the similarities between the results obtained and those shown in literature, highlighting how simple decision trees allow a greater explanation and interpretation than other models and techniques.