Comparison and analysis of the accuracy of Lasso regression, Ridge regression and Elastic Net regression models in predicting students' teaching quality achievement

Abstract

In this paper, the "Student Performance Data Set" data set of Kaggle competition is used to conduct correlation analysis on multiple attributes such as students' personal information, school information and students' school performance, and a correlation heat map is drawn. The results show that there is a strong positive correlation among the attributes. We then divided the data set into training, validation, and test sets in a 6:2:2 ratio, and used the Lasso regression model, the Elastic Net model, and the Ridge regression model to make predictions. After training 50 epochs, we evaluated and compared the models. The results show that Lasso regression model has the lowest prediction error and the best error effect. Elastic Net was the next best predictor, while Ridge regression model had the largest prediction error and was the worst. To sum up, Lasso regression model has the best Performance in grade prediction based on the "Student Performance Data Set" dataset. This conclusion is of great significance for schools and educational institutions, as it can help them better understand students' learning and improve the quality and effectiveness of teaching. At the same time, this conclusion is also valuable for data scientists and machine learning researchers, because it can guide them to choose the most appropriate model and algorithm on similar data sets, improving the accuracy and effectiveness of predictions. In general, this paper analyzes and discusses the problem of Student achievement prediction, puts forward the Lasso regression model based on the "Student Performance Data Set" data set, which has the best performance prediction effect, and analyzes the principles of the three models. This conclusion has practical applications for schools and educational institutions, as well as providing a reference for data scientists and machine learning researchers.