NCAA Bracket Prediction Using Machine Learning and Combinatorial Fusion Analysis

TL;DR

This paper presents a novel combinatorial fusion analysis method that improves NCAA basketball tournament predictions by integrating multiple ranking systems, achieving higher accuracy than existing public rankings.

Contribution

Introduces Combinatorial Fusion Analysis (CFA), a new approach for combining sports rankings to enhance prediction accuracy in NCAA tournament outcomes.

Findings

CFA achieves 74.60% accuracy in NCAA bracket prediction.

CFA outperforms the best existing public ranking systems.

The method demonstrates the effectiveness of combining diverse ranking sources.

Abstract

Machine learning models have demonstrated remarkable success in sports prediction in the past years, often treating sports prediction as a classification task within the field. This paper introduces new perspectives for analyzing sports data to predict outcomes more accurately. We leverage rankings to generate team rankings for the 2024 dataset using Combinatorial Fusion Analysis (CFA), a new paradigm for combining multiple scoring systems through the rank-score characteristic (RSC) function and cognitive diversity (CD). Our result based on rank combination with respect to team ranking has an accuracy rate of $74.60\%$, which is higher than the best of the ten popular public ranking systems ($73.02\%$). This exhibits the efficacy of CFA in enhancing the precision of sports prediction through different lens.