Understanding the academic performance of students in colleges is an essential topic in Education research field. Educators, program coordinators and professors are interested in understanding how students are learning specific topics, how specific topics may influence the learning of other topics, how students’ grades/attendances in each course may represent important indicators to measure their performance, among other tasks. The use of data visualization and analytics is expanding in education institutions to perform a variety of tasks related to data processing and gaining into data-informed insights. In this paper, we present a visual analytic tool that combines data visualization and machine learning techniques to perform some visual analysis of students’ data from program courses. Two educational data collections were used to guide the creation of i) predictive models employing a variety of well known machine learning strategies, attempting to predict students’ future grade based on grade and attendance previous semesters and ii) a set interactive layouts that highlight the relationship between grades and attendance, also including additional variables such as gender, parents education level, among others. We performed several experiments, also using these data collections, to evaluate the layouts ability of highlighting interesting patterns, and we obtained promising results, demonstrating that such analysis may help the education experts to understand deficiencies on course structures.