Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

NCAA Bracket Prediction Using Machine Learning and Combinatorial Fusion Analysis

Yuanhong Wu, Isaiah Smith, Tushar Marwah, Michael Schroeter, Mohamed Rahouti, D. Frank Hsu

TL;DR

This paper leverages 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).

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.

NCAA Bracket Prediction Using Machine Learning and Combinatorial Fusion Analysis

TL;DR

This paper leverages 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).

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 , which is higher than the best of the ten popular public ranking systems (). This exhibits the efficacy of CFA in enhancing the precision of sports prediction through different lens.
Paper Structure (21 sections, 12 equations, 4 figures, 1 table)

This paper contains 21 sections, 12 equations, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Previous work
  3. Combinatorial Fusion Analysis
  4. Multiple scoring systems
  5. Cognitive diversity
  6. Model combination
  7. Data sets and base models
  8. Data collection
  9. Feature selection
  10. Base models
  11. Model A: Logistic regression
  12. Model B: Support vector machines
  13. Model C: Random forest
  14. Model D: XGBoost
  15. Model E: Convolutional neural network
  16. ...and 6 more sections

Figures (4)

  • Figure 1: (a) Relationship between score, rank, and RSC function, where $D$ is a set of data items, N and R refer to natural numbers and real numbers, respectively hsu2006combinatorialhsu2024combinatorial. (b) RSC functions for two scoring systems A and B.
  • Figure 2: The CFA combination framework for both score and rank combinations, where SC and RC are score combination and rank combination, respectively; AC, WCP, and WCDS refer to average combination, weighted combination by performance, and weighted combination by diversity strength, respectively
  • Figure 3: (a) Five RSC functions and (b) model combination performance for the year 2022 test data, where A: logistic regression, B: SVM, C: Random Forest, D: XGBoost, and E: CNN.
  • Figure 4: (a) Five RSC functions and (b) model combination performance for year 2021 test data, where A: logistic regression, B: SVM, C: Random Forest, D: XGBoost, and E: CNN.