Authors:
This repository contains the source code related to the paper:
When Decisions Hesitate: Fusion of SVM and Random Forest Classifiers
to be presented at the ICAISC 2026 (International Conference on Artificial Intelligence and Soft Computing).
The proposed framework combines Random Forest and Support Vector Machine in a hybrid classification pipeline. Random Forest classifies samples with high confidence; samples falling below a configurable probability threshold are deferred to SVM, which better captures non-linear decision boundaries in uncertain regions. The framework is evaluated on standard benchmarks (Wine, Breast Cancer) as well as synthetic non-linear datasets (moons, circles) and compared against Decision Tree, standalone SVM, KNN, and Naive Bayes baselines.
This work is licensed under the Creative Commons License.
Feel free to use, modify, and distribute the code under the terms of the license.
To appear in ICAISC 2026: When Decisions Hesitate: Fusion of SVM and Random Forest Classifiers
Please find the citation information in CITATION.cff file.
This research was supported by the Polish Ministry of Science and Higher Education under project no. MNiSW/2025/DPI/650 "Intelligent mechanisms of selective information processing in deep neural networks" as part of "Supporting students to improve their competencies and skills" program.
