The Effectiveness of Interactive Quizwhizzer Games with a Deep Learning Approach to Improve the Understanding of Fractional Concepts for Fifth Grade Elementary School Students

evidenced by their test scores. The purpose of this study is to determine the effectiveness of using Quizwhizzer with a deep learning approach to improve the understanding of fractional concepts among fifth grade elementary school students. This study is an experimental research employing a one-group pretest posttest design. The sample consisted of fifth grade students at SDN Sendangmulyo. Data collection techniques included testing and documentation. The research instruments used were pretest and posttest questions regarding the conceptual understanding of mathematical fractions. Data analysis involved normality tests, homogeneity tests, paired sample t-tests, and N-Gain tests.The normality test results for the pretest scores yielded a significance value (sig) of 0.061, and the posttest scores yielded a sig of 0.078, indicating that both were normally distributed. Based on the homogeneity test, a sig value of 0.934 was obtained, meaning the pretest and posttest scores were homogeneous. Furthermore, the "Paired Samples t-Test" output showed a Sig (2-tailed) value of 0.000 < 0.05, resulting in the rejection of H0 and the acceptance of H1. Additionally, the N-Gain test result was 0.339, indicating an improvement in the "medium" category. Therefore, it can be concluded that the conceptual understanding of fractions among fifth-grade students can be improved through the use of Quizwhizzer with a deep learning approach in mathematics learning.