AI soccer analyst improves collaboration with stage-aware verifiable insights
AI Soccer Analyst: Stage-Aware and Verifiable Human-AI Collaboration for Soccer Data Analysis
Human-Computer InteractionArtificial Intelligence
Summary
Analyzing sports data is hard because it needs both computer calculations and expert sports knowledge. The authors created AI Soccer Analyst, a system that helps experts work step-by-step with an AI, making the analysis easier to check and change. This approach keeps experts involved and makes the AI-generated reports more trustworthy. People testing the system liked the quality and reliability of the final results.
What this means in practice
- •For sports data analytics teams: Collaborate with AI to create reliable, checkable analyses by following structured stages tailored to sports data interpretation.
- •For business intelligence teams: Use stage-aware AI collaboration methods to improve transparency and revisability in complex data reporting workflows beyond sports.
Authors
Calvin Yeung, Keisuke Fujii
Abstract
Sports data analysts translate domain questions into insights by combining computation with sport-specific domain expertise. Large language models ease programming, but prompt-to-report workflows may obscure decisions and evidence. We present AI Soccer Analyst, a mixed-initiative system with revisable stages: Data Understanding, Problem Definition, Structured Planning, Execution, Evidence-Grounded Reporting, and Interaction and Refinement. A formative study with five analysts first informed design goals for automation, verifiability, human control, and accessibility. Subsequently, a task-based evaluation with 16 participants combined system logs, retained artifacts, ratings, and open responses; 33 of 48 tasks met the operational completion criteria. Exploratory tests supported favorable participant perceptions of completed-task output quality, task achievement, reliability, and verifiability after Holm correction. Interaction records showed domain knowledge emerging through clarification, planning, and refinement. These findings position stage-aware human-AI collaboration as a practical approach for producing inspectable, revisable, and verifiable analyses while retaining domain-expert involvement in consequential decisions.