<![CDATA[This study aimed to examine the effect of a deep learning-based mathematics educational game on students' understanding of geometric solid concepts at SMP Negeri 3 Kuala Batee. A quantitative approach was employed using a quasi-experimental design with a pretest–posttest control group. Thirty students participated in the study and were divided into an experimental group, which used the deep learning-based educational game, and a control group, which received conventional instruction. Data were collected through a conceptual understanding test administered before and after the learning intervention. The collected data were analysed using descriptive statistics, the Shapiro–Wilk normality test, the homogeneity test, and an independent samples t-test. The findings revealed that the experimental group achieved a higher mean posttest score than the control group. Furthermore, the hypothesis test indicated a significance value (Sig. 2-tailed) of 0.007 (< 0.05), confirming a statistically significant difference in learning outcomes between the two groups. These results demonstrate that the deep learning-based educational game is effective in improving students' understanding of geometric solid concepts. In addition, the use of the game enhanced students' enthusiasm, active participation, and engagement throughout the learning process. Therefore, integrating deep learning-based educational games into mathematics instruction can serve as an effective strategy for improving conceptual understanding and fostering a more interactive learning environment.]]>
