The Influence of Deep Learning -Based Problem Solving Models on Ability Solution Problem Mathematical Students on Questions Statistics Material Story in Class X

Abstract

This study aims to determine the effect of the deep learning-based problem solving model on students' mathematical problem-solving ability in statistics story problems in class X of SMA Negeri 12 Medan. The research used a Quasi-Experimental method with a population of all grade X students consisting of 10 classes. The sample was determined through cluster random sampling, resulting in class X-E2 as the experimental class and class X-E4 as the control class. Data were collected using a mathematical problem-solving ability test. Data analysis using the Liliefors normality test, F homogeneity test, and t-test showed a significant difference between the pre-test and post-test scores of problem-solving ability in both classes, with a sig. (P(T<=t) two-tail) value of 0.0076 < 0.05. The average post-test score of the experimental class reached 67.3000, while the control class was 46.0333, indicating that students' mathematical problem-solving ability was in the high category. Based on the calculation of Effect Size (Cohen’s D), a value of 3.539734 was obtained, which means that using the problem-solving model based on deep learning on students' mathematical problem-solving abilities has a high influence on improving students' ability to solve mathematical problems