NCAA Bracket Prediction Using Machine Learning and Combinatorial Fusion Analysis

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

cs.LGMar 11, 2026

NCAA Bracket Prediction Using Machine Learning and Combinatorial Fusion Analysis

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

Organizations: Department of Computer and Information Science, Fordham University, New York, NY, 10023, USA · Gabelli School of Busines, Fordham University, New York, NY, 10023, USA · Department of Computer and Information Science, Fordham Universiyt, New York, NY, 10023, USA

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.

Figures & tables

Panel of Figure 1 — Fig. 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 [ 5 , 4 ] . (b) RSC functions for two scoring systems A and B.

Fig. 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

Panel of Figure 3 — Fig. 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.

Panel of Figure 4 — Fig. 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.

INCC Stats	$71.43\%$	Jelly Juke	$66.67\%$
Joby Nitty Gritty	$69.84\%$	Logan	73.02%
Massey	$69.84\%$	Moore	$71.43\%$
NET Rankings	$73.02\%$	ESPN SOR	$69.84\%$
Sports Ratings	$68.25\%$	Donchess Inference	$69.84\%$

TABLE I : 10 popular NCAA men’s basketball public team ranking systems with their accuracies for 2024 year

Sports Outcome Prediction

Sports outcome prediction uses statistical and machine-learning models to forecast match results, scores, tournaments, and athlete performance.

See all 19 papers

WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting
Jul 20, 2026Zhaokai Wang, Tianlin Gui, Jiayuan Rao +3LLM Evaluation Forecasting Benchmarks
Shanghai Jiao Tong University · Shanghai, China · Nanjing University +4
Topological Data Analysis and Graph-Theoretic Approaches for Tennis Match Prediction
Jul 26, 2026Jake Schwaderer, Alexander Bastien, Omid Khormali +3Sports Analytics Sports Outcome Prediction
Department of Mathematics University of Evansville Evansville, Indiana 47722, USA.
AI World Cup 2026: Benchmarking Large Language Models for End-to-End Football Tournament Prediction
Aug 4, 2026Jonaid Shianifar, Iias FaiudLLM Evaluation Forecasting Benchmarks
AI World Cup Project

Jul 20, 2026J/K move · Enter open · S save

WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting

Zhaokai Wang, Tianlin Gui, Jiayuan Rao, Shangzhe Di+2

Shanghai Jiao Tong University · Shanghai, China · Nanjing University+4

LLM Evaluation Forecasting Benchmarks Probabilistic Forecasting Sports Outcome Prediction Agent Benchmarks

Open paper AskPDF arXiv

Predicting a football match before kickoff requires more than knowing past results: a model must use changing information and make a clear prediction before the answer is available. We present WorldCupArena, a dynamic benchmark for language models and deep-research agents. The 2026 FIFA World Cup is its first evaluation, and the same process can be reused for future leagues and cups. Before each match, a model either receives a common evidence package or searches for information itself. It predicts the result and score, likely players and events, match statistics, and the outcome of the competition. After the match, these predictions are compared with the recorded result. We report result accuracy, exact-score accuracy, and a scoreline score that gives some credit when a predicted score is close but not exact, together with scores for the other prediction tasks. Across systems, similar result accuracy can mask larger differences in detailed predictions. Four systems predicted champion Spain, and two of them also recovered the exact final pairing. Compared with betting-market and human-fan baselines, the best system shows only small gains in result and exact-score accuracy, but a clearer gain in Scoreline. New schedules can be added as they begin, allowing the benchmark to evaluate future models without using outcomes that are already known. Code, predictions and evaluation scripts will be publicly released.

Abstract

Sports Outcome Prediction

Explore similar work

WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting

Topological Data Analysis and Graph-Theoretic Approaches for Tennis Match Prediction

AI World Cup 2026: Benchmarking Large Language Models for End-to-End Football Tournament Prediction