Prediction of Final Academic Performance of Secondary School Students Based on Alcohol Consumptions and Diverse Backgrounds

Abstract

The power of machine learning is prompting more educators to consider applying the technology to education. Also, alcoholism among students has become an important problem in society. Based on data from two US secondary schools, this paper investigates the impact of attributes including alcohol consumption, on students grades, and aims to predict students' final grades in Portuguese. The normal distribution index was used as a reference to analyze and clean the data. The visualization of the data to explore which attributes were most correlated with final grade has been achieved. In this paper, ridge regressor, decision tree regressor, decision tree classifier, and KNN classifier were used as training models, with MSE, MAE, r2, and accuracy as testing indexes and cross validation to verify results. The final results show that alcohol consumption has a significant negative impact on students' academic performance.