Prediction of the Factors Affecting PISA Mathematics Literacy of Students from Different Countries by Using Data Mining Methods

The purpose of this study is to predict the mathematical literacy levels students participating in research through data obtained from PISA 2015 exam organized by OECD using mining and determine variables that affect mathematics literacy. For purpose, students' their were analyzed separately for 6 different countries at proficiency levels. population 519334 72 countries, who have taken exam. sample was determined according consists a total 34,565 Singapore, Japan, Norway, USA, Turkey, Dominican Republic, which been observed be In first stage study, analyzes performed prediction methods. At stage, WEKA program employed M5P algorithm, one most common methods, used. second research, output variable predicted input Artificial Neural Networks methods extent decision trees method produce valid results. carried out MATLAB program, relationship between actual math scores examined. As result found socio-economic status index United States, Dominic. On other hand, influencing Japan learning time father's education level. consistency results as follows: 86.10% 40.26% 30.10% 39.15% America, 26.43% 29.24 % differentiation among