Prospective Analysis of Students' Academic Performance based on Personality Dimensions with Automatic Machine Learning (Auto ML)

Predicting students’ performance is important for their parents and their teachers. In recent years, learning analytics has been used to evaluate educational data and factors affecting academic performance. Numerous factors, including individual, family, social and environmental characteristics affect this issue. One of the most important individual factors is personality, which we will examine the impact of this factor on academic performance. For this purpose, we analyze the data of a school students in District One of Tehran. Researches in this field has focused on the correlation of different dimensions, but the main purpose of this study is predicting student performance in order to identify students at risk of academic failure, which with the knowledge of the family to improve They take action. The methodology used is CRISP-DM. The Auto ML data mining technique was used for analysis. According to the Accuracy criterion, the classification is more accurate than the artificial neural network method. According to the findings of this study, the conscientious dimension had the greatest effect and the neurotic dimension had the least effect on predicting students' performance.