This study attempts to determine the factors affecting the mathematics achievement of students in Turkey based on data from the Programme for International Student Assessment 2012 and the correct classification ratio of the established model. The study used mathematics achievement as a dependent variable while sex, having a study room, preparation for mathematics exams, completing homework on time, interest in mathematics, enjoying mathematics and enjoying reading about mathematics were used as independent variables. The study sample consisted of 4478 students participating in PISA 2012. Probit regression analysis was used to analyse the data. According to the findings, it was determined that there was a positive interaction between the dependent variable and all the independent variables except regularly completing homework and that the correct classification ratio of the model was 58 (44%).