<![CDATA[This study aims to examine the effectiveness of instructional design based on the ADDIE model with a deep learning approach on students’ learning outcomes at SDIT Permata Bunda Bandar Lampung. The research employed a quantitative approach using a quasi-experimental method with a Nonequivalent Control Group Design. The research subjects consisted of two classes, namely an experimental class and a control class, each comprising 30 students. The experimental class was taught using an instructional design based on the ADDIE model integrated with a deep learning approach, while the control class received conventional instruction. Data were collected using a learning achievement test administered as pretest and posttest. The data were analyzed using descriptive statistics, Kolmogorov–Smirnov normality test, Levene’s homogeneity test, independent samples t-test, and N-Gain analysis. The results indicated that the average posttest score of the experimental class (86.00) was higher than that of the control class (68.83). The independent samples t-test showed a significance value of 0.000 (p < 0.05), indicating a statistically significant difference in learning outcomes between the two groups. Furthermore, the N-Gain analysis revealed that the experimental class achieved a moderate level of improvement (0.61), while the control class showed a low level of improvement (0.10). Therefore, it can be concluded that instructional design based on the ADDIE model with a deep learning approach is effective in improving elementary school students’ learning outcomes.]]>
