Soccer Stoppage Time Prediction Using Delay Regression and Neural Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Soccer matches do not have a standardized method for predicting stoppage time, leading to inaccuracies in downstream sports analytics and decision-making.
Innovation Solution
A dual-machine learning model approach is employed to predict stoppage time in soccer matches, utilizing real-time delay data and environmental data to generate accurate predictions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional manual stoppage time assignment is used, then referees have flexibility in decision-making, but prediction accuracy of stoppage time deteriorates
Solution Approach 1:
The stoppage time prediction is segmented into two distinct phases: (1) prediction of initial stoppage time before the half ends, and (2) prediction of additional stoppage time after the referee announces initial stoppage time. This segmentation allows each model to focus on specific aspects, improving overall accuracy while managing complexity through modular architecture.
Solution Approach 2:
The system performs preliminary prediction of stoppage time before the half actually ends, using delay data accumulated during play. This preliminary action enables downstream analytics and decision-making to be prepared in advance with accurate timing information, rather than waiting for manual referee determination.
2Measurement precision
If real-time delay data processing is implemented, then stoppage time prediction accuracy improves, but computational requirements increase
Solution Approach 1:
The system processes only the necessary delay data elements that are relevant to stoppage time prediction, rather than analyzing all possible match data. This partial action approach maintains high prediction accuracy while reducing unnecessary computational energy consumption by focusing only on critical delay events and their characteristics.
3Measurement precision
If comprehensive delay data categorization is used, then prediction model accuracy improves, but data processing complexity increases
Solution Approach 1:
Delay data is segmented into distinct categories based on the type of delay event (e.g., injuries, goals, VAR reviews, substitutions). This categorization allows the model to process different delay types with appropriate weighting and characteristics, improving prediction accuracy while managing data processing complexity through structured classification.
Data Source
AI summary
Techniques for method for using machine learning to predict stoppage time are disclosed. In an example, a method includes accessing, in real time, delay data from a sporting event. The delay data may be categorized by a type of delay. The method further includes generating, from the delay data, a linear regression. The method further includes providing, to a neural network, the linear regression and environmental data. The neural network is trained to predict an estimated stoppage time. The method further includes receiving, from the neural network, a predicted amount of stoppage time. The method further includes outputting the predicted amount of stoppage time.