Multiple Linear Regression, Lasso Regression, Extreme Gradient Boosting (XGBoost)


Superconductors have substantial practical applications, among which Magnetic Imaging Resonance Imaging (MRI) is most widely used in the health industry. Two significant problems have prevented superconductors from being widely used: the first problem is that it is impractical to cool down the superconductors to extremely low temperatures of 77K, and the second problem is that the scientific model to predict the critical temperature (Tc). This project aims to find a scientific model to predict critical temperature more accurately.


This paper focuses on utilizing multiple linear regression, lasso regression, and extreme gradient boosting algorithms to predict the critical temperature of the superconductor. The model will be evaluated using the mean square error and adjusted R-squared values, and the best model will be recommended for future work related to this study.


Spring 2023

Course Name

STA 5703 Data Mining 1

Instructor Name

Xie, Rui


College of Sciences

Included in

Data Science Commons