This study explored science-related variables that have an impact on the prediction of science achievement groups by applying the educational data mining (EDM) method of the random forest analysis to extract factors associated with students categorized in three different achievement groups (high, moderate, and low) in the Korean data from the 2015 Programme for International Student Assessment (PISA). The 57 variables of science activities and learning in school collected from PISA questionnaires for students and parents were analyzed. Variables related to students’ past science activities, science teaching and learning methods, and environmental awareness were found to played important roles in predicting science achievement. When checking partial dependence plots for major variables, science activities and instructional strategies had a high probability of changing the prediction of an achievement group. This study focused on science-related contextual variables that can be improved through government policies and science teachers’ efforts in the classroom.

This study analyzed the responses of Korean students to interest, confidence, value, and instructional clarity in science and mathematics. To achieve this, the raw data of the recent student survey of TIMSS were analyzed. A one-way ANOVA was performed, and a post hoc test was performed. Additionally, a cohort analysis was performed to determine the changes when the fourth-grade students reached the eighth grade. The study results are as follows. First, interest and confidence were higher in the fourth grade than in the eighth grade. Second, in most cases, the average response of Singaporean students was the most positive, but in terms of interest and confidence in science in the fourth grade, the Japanese response average was generally the highest. Third, the average scores of Korean students on wanting to have a job related to their subject and knowing what teachers expect from them were low in both science and mathematics.