This study aimed to determine the effect of the Problem-Based Learning model integrated with the deep learning approach on elementary school students’ mathematical problem-solving ability. The method used was a quasi-experimental design employing the Nonequivalent Control Group Design. The research subjects were grade V students of MI Babakan Ranji. Data were collected through pretests and posttests and analyzed using descriptive statistics, the paired samples t-test, and Analysis of Covariance (ANCOVA). The results showed that the mean score of the experimental class increased from 78.50 to 88.57 with a learning mastery rate of 97%, while the mean score of the control class increased from 76.73 to 79.73 with a learning mastery rate of 80%. The ANCOVA results indicated a significance value of p < 0.001, indicating that the Problem-Based Learning model integrated with the deep learning approach had a positive effect on students' mathematical problem-solving ability. Keywords: Deep Learning, Mathematical Problem Solving Ability, Problem-Based Learning.
Copyrights © 2026