Schedule decisions mixed public rankings, selection-committee incentives, opponent availability, staff preferences, and downside risk.
Back to proof
Sports Analytics / Decision Support
AI-Assisted Basketball Scheduling Decision Workflow
A staff-facing basketball scheduling workflow that turns messy NCAA data and selection-committee constraints into repeatable decision support.
Outcome: Staff adopted the scheduling recommendations. Public-safe outcome metrics: NCSOS 293 -> 59, NET 46 -> 9, WAB -0.76 -> +2.59, and Q1/Q2 record 0-2 -> 5-1.
The evidence
Problem, system, review loop, result.
A repeatable decision workflow for comparing schedule scenarios, quadrant impact, resume strength, and staff-ready recommendations.
Recommendations were checked through source consistency, quadrant classification, scenario comparison, and human review before staff use.
Staff adopted the recommendations as part of real scheduling decision work.
Public proof
Public-safe outcome signals after adopted recommendations include NCSOS 293 -> 59, NET 46 -> 9, WAB -0.76 -> +2.59, and Q1/Q2 record 0-2 -> 5-1.
The public version uses synthetic visuals and public outcome signals. It does not claim the workflow alone caused BYU's results.
non-conference strength-of-schedule lift
team ranking movement after adopted scheduling changes
resume-quality improvement
quality-game result shift
Ownership
Clear about the judgment. Clear about the assistance.
Problem definition, workflow design, evaluation criteria, source selection, validation, rollout, user feedback, adoption, and outcome framing.
Code, app structure, scripts, UI wiring, parsing, tests, and iteration support. I stayed accountable for whether the workflow was useful and honest.
Artifacts and proof
Look at the work.
Screenshots and artifacts are public-safe by design. Private strategy, records, credentials, and customer data stay out.
Fake opponent slate with quadrant impact, downside risk, and staff-ready recommendation language.
Public-safe example comparing neutral-site, road, and home-game tradeoffs without exposing internal targets.
Quadrant classification, source consistency, NET/RPI sanity checks, and human review before use.
No internal scheduling strategy, private staff notes, or claims of sole engineering ownership.
Why it matters