Keywords
Superconductors, Critical Temperature, Linear Model, Ridge Regression
Description
This study presents a data-driven framework for predicting the critical temperature of superconducting materials using interpretable linear and regularized linear models. Leveraging the Superconductivity dataset from the UCI Machine Learning Repository, the work evaluates Linear Regression, Ridge Regression, and Linear Regression with subset selection on a large set of physico-chemical material descriptors. The results demonstrate that well-regularized linear models achieve strong predictive performance while maintaining transparency and computational efficiency. Although feature subset selection improves interpretability, it incurs a modest reduction in accuracy, highlighting the trade-off between model simplicity and predictive power. Overall, the study emphasizes that simple, regularized linear approaches remain effective baselines for superconducting critical temperature prediction.
Abstract
This study adopts a data-driven approach to estimate the critical temperature of superconducting materials using linear machine learning models. A comprehensive dataset derived from material physico-chemical properties was analyzed after systematic preprocessing and standardization. Three linear modeling strategies—Linear Regression, Ridge Regression, and Linear Regression with Subset Selection—were developed and evaluated using standard regression performance metrics. The findings demonstrate that both basic and regularized linear models can effectively capture the relationship between material features and superconducting behavior, offering robust and interpretable predictions. While feature selection enhances model transparency, it comes with a modest reduction in predictive capability. Overall, this work emphasizes the value of simple, well-regularized linear models as efficient and interpretable tools for understanding and prediction of superconducting properties.
Course Name
STA 5703 Data Mining 1
Instructor Name
Dr. Emil Agbemade
Rights
This work is licensed under a Creative Commons Attribution 4.0 International License.
College
College of Sciences
STARS Citation
Deb, Dipok, "Data-Driven Prediction of Superconducting Critical Temperature: A Linear and Regularized Linear Modeling Approach" (2026). Data Science and Data Mining. 50.
https://stars.library.ucf.edu/data-science-mining/50