Islamic Religious Education (PAI) learning is directed at shaping students’ perspectives through a deeper approach, encouraging reflective thinking skills, and promoting the application of Islamic values in daily life. In this context, the Deep Learning method emerges as a learning approach that emphasizes active student participation, the development of critical thinking skills, and a deeper understanding of the material being studied. Therefore, this study aims to analyze the effect of the implementation of the Deep Learning method on the level of students’ understanding in Islamic Religious Education for tenth-grade students at SMK Negeri 1 Bulukerto.

This research employs a quantitative approach with a correlational design to examine the relationship between the variables studied. The research subjects include all tenth-grade students at SMK Negeri 1 Bulukerto, totaling 140 students. The sampling technique used is Proportionate Stratified Random Sampling, involving two majors: Accounting and Institutional Finance (AKL) and Software and Game Development (PPLG). Data collection was carried out through the distribution of Likert-scale questionnaires that had previously undergone validity and reliability testing. Furthermore, the collected data were analyzed using several statistical techniques, including the Kolmogorov–Smirnov normality test, Pearson Product Moment correlation test, and simple linear regression analysis with the assistance of SPSS software.

The results of the study indicate that the data are normally distributed and that there is a significant relationship between the implementation of the Deep Learning method and students’ depth of understanding. The results of the simple linear regression test also show a significance value of less than 0.05, indicating that the null hypothesis (H₀) is rejected and the alternative hypothesis (Hₐ) is accepted. The regression equation obtained is Y = 23.603 + 1.509X, which indicates that every increase in the implementation of the Deep Learning method is followed by an increase in students’ understanding. In addition, the positive regression coefficient indicates that the effect is unidirectional or direct.

Based on the results of the study, it can be concluded that the use of the Deep Learning method has a significant positive impact on improving students’ understanding in Islamic Religious Education learning. These findings indicate that the Deep Learning method is effective in helping students comprehend the material more deeply, and therefore can be considered as an alternative learning strategy for Islamic Religious Education to be implemented in schools.

Keywords: Deep Learning, Students’ Understanding, Islamic Religious Education