Cross-Era Player Matchup Simulation Using Historical Tracking Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is currently no mechanism to quantify or visualize a matchup between players from different generations, such as Lebron James and Michael Jordan, to determine how they would perform against each other in a historical game.
Innovation Solution
A system and method that utilizes historical tracking data to simulate a play by substituting a player with a target player, using (x,y) coordinates and body-pose information, and applies model adaptation techniques to normalize differences between eras, allowing the simulation of games or plays between players who have never played against each other.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If historical tracking data is used to simulate player matchups across different generations, then the ability to quantify and visualize player comparisons is improved, but the complexity of the system increases due to the need to learn and adapt player attributes across different eras
Solution Approach 1:
The system performs preliminary learning of player attributes from historical tracking data before conducting simulations. The computing system learns player attributes, movement patterns, and game context data in advance, storing this information for future simulation requests. This preliminary action enables accurate cross-era player comparisons without requiring complex real-time calculations during the actual matchup simulation.
2Measurement precision
If model adaptation techniques are applied to normalize differences between eras, then the accuracy of simulating players from different generations is improved, but the computational processing time increases
Solution Approach 1:
The system applies model adaptation techniques that transform and normalize player attributes across different eras by adjusting parameters such as speed, strength, and skill levels to account for changes in game rules, equipment, and playing styles. This parameter transformation enables accurate comparisons between players from different generations while managing computational complexity through efficient normalization algorithms.
3Adaptability or versatility
If the system learns comprehensive player attributes from historical data, then the ability to simulate alternative outcomes is improved, but the quantity of data processing and storage requirements increase
Solution Approach 1:
The system extracts and stores only the essential player attributes and game context data needed for simulation from the comprehensive historical tracking data. Rather than processing all available data, the system identifies and extracts key parameters such as player positions, movements, and game outcomes, storing this condensed information for efficient retrieval during simulation requests.
Data Source
AI summary
A computing system retrieves historical event data for a plurality of games in a league. The historical event data includes (x,y) coordinates of players within each game and game context data. The computing system learns one or more attributes of each team in each game and each player on each team in each game. The computing system receives a request to simulate a play in a historical game. The request includes substituting a player that was in the play with a target player that was not in the play. The computing system simulates the play with the target player in place of the player based on the one or more attributes learned by the computing system. The computing system generates a graphical representation of the simulation.