Class

Article

College

Jon M. Huntsman School of Business

Department

Management Information Systems Department

Faculty Mentor

Zsolt Ugray

Presentation Type

Poster Presentation

Abstract

This study conducts a comparative analysis of feature selection techniques and machine learning models to improve breast cancer risk prediction using the Wisconsin Breast Cancer Dataset. Through evaluating univariate feature selection, recursive feature elimination, and principal component analysis, alongside ten machine learning models, the research aims to identify the most effective combination for accurate diagnosis.

Performance metrics such as accuracy, precision, recall, and F1 score guide the analysis.

The findings suggest that integrating specific feature selection methods with particular machine learning algorithms significantly enhances predictive accuracy, offering insights for developing more effective breast cancer detection tools and improving patient outcomes.

Location

Logan, UT

Start Date

4-9-2024 10:30 AM

End Date

4-9-2024 11:20 AM

Included in

Business Commons

Share

COinS
 
Apr 9th, 10:30 AM Apr 9th, 11:20 AM

A Comprehensive Study: Comparing Machine Learning Techniques for Breast Cancer Prediction

Logan, UT

This study conducts a comparative analysis of feature selection techniques and machine learning models to improve breast cancer risk prediction using the Wisconsin Breast Cancer Dataset. Through evaluating univariate feature selection, recursive feature elimination, and principal component analysis, alongside ten machine learning models, the research aims to identify the most effective combination for accurate diagnosis.

Performance metrics such as accuracy, precision, recall, and F1 score guide the analysis.

The findings suggest that integrating specific feature selection methods with particular machine learning algorithms significantly enhances predictive accuracy, offering insights for developing more effective breast cancer detection tools and improving patient outcomes.