# Capturing Intransitive Dominance in Tennis Forecasting: A Graph Neural Network Approach

DevFeed: [Capturing Intransitive Dominance in Tennis Forecasting: A Graph Neural Network Approach](<https://devfeed.tech/articles/capturing-intransitive-dominance-in-tennis-forecasting-a-graph-neural-network-approach-132734.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2510.20454>)

Author: Lawrence Clegg, John Cartlidge

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Predictive AI](<https://devfeed.tech/topics/predictive-ai.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [Graphs](<https://devfeed.tech/topics/graphs.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [forecasting](<https://devfeed.tech/tags/forecasting.md>), [graph](<https://devfeed.tech/tags/graph.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [neural-network](<https://devfeed.tech/tags/neural-network.md>), [tennis](<https://devfeed.tech/tags/tennis.md>)

## AI overview

The graph neural network models tennis match history as temporal directed graphs, with players as nodes and past outcomes as edges, to capture intransitive dominance (A beats B, B beats C, C beats A). It achieves 65.7% accuracy and a 0.214 Brier score, performing competitively with Weighted Elo but not improving unconditional accuracy on its own. A forecast-encompassing test finds complementary information: combining the model with Weighted Elo significantly improves on that baseline, with some indication of greater gains on intransitive matchups. The abstract suggests the graph representation can capture signals missed by transitive rating systems, including between players without common opponents.

## Source excerpt

arXiv:2510.20454v3 Announce Type: replace Abstract: Intransitive player dominance, where player A beats B, B beats C, but C beats A, is common in competitive tennis. Yet, there are few known attempts to incorporate it within forecasting methods. We address this problem with a graph neural network approach that explicitly models these intransitive relationships through temporal directed graphs, with players as nodes and their historical match outcomes as directed edges. Our model (65.7% accuracy, 0.214 Brier score) forecasts competitively with established rating systems such as Weighted Elo. Although it does not improve on the baseline in unconditional accuracy, a forecast-encompassing test shows that it carries complementary information. A combined forecast significantly outperforms Weighted Elo, and there is some indication that the gain is larger on the intransitive matchups our model targets. A graph-based representation of player interactions thus captures a forecasting signal that transitive rating systems discard, even between players who share no common opponents.