Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{191693,
        author = {Roselinevinnarasi.A and Hannah Inbarani H},
        title = {Feature Reduction And Svm-Based Ensemble Machine Learning Techniques For Breast Cancer Prediction},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {7418-7424},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191693},
        abstract = {Breast cancer is leading health problem for the global community, and it is vital to screen breast cancer in an early stage. Machine learning (ML) is a powerful method that should be utilized in the diagnosis process since it finds complex trends in medical data. The Principal Component Analysis (PCA), K-Nearest Neighbours (KNN) and Support Vector Machines (SVM) derived from soft voting have been postulated in the research paper. PCA method reduces the dimensions and redundancy. SVM assigns high decision boundaries compared to KNN which has a superior local classification. The team was tested using Wisconsin Breast Cancer Diagnostic (WBCD) data. It achieved 98% accuracy, 1.00 precision, 0.99 recall, and 0.99 F1-score, which is better than the scores of its individual classifiers. This method showed competitive performance with respect to Logistic Regression and reduced computation costs. This proves that it can be utilised to predict breast cancer and can be employed in medical diagnostics in general.},
        keywords = {KNN, Logistic Regression, Machine Learning, Multilayer Perceptron, PCA, Random Forest, SVM, WBCD.},
        month = {January},
        }