Forecasting future students´ academic level and analyzing students´ feature using schooling logs

Most educational institutions nowadays digitally manage their students´ data, which are maintained on servers on campus. We intend to use these data in order to provide academic guidance. Thus, in this study, we forecast students´ future academic records using smart card based time recording data and grade data. We use a Bayesian network as our forecasting method. In the past study, we forecast future student´s academic records for the end of the second year using data from the first year through the first period of the second year. This time, we forecast them from the first year in order to forecast students´ future academic level as soon as possible and prevent a poor results person from falling. We also revised the variables data and increased new variables by time recording data.