{"resourceId":"usc-viterbi-football-datamart-2026","versions":[{"version":"external-81b9e26520512027f8a298102de9500aa989c2f3031b5f8b3980fbd07620670b","resource":{"id":"usc-viterbi-football-datamart-2026","title":"USC Viterbi data mart nears operational use with football’s director of AI","organization":"University of Southern California / Daily Trojan","sector":"College athletics / football coaching analytics data engineering","geography":"United States (USC Athletics, Los Angeles)","publishedAt":"September 16, 2026","publicationDate":"2026-09-16","eventDate":null,"sourceName":"Daily Trojan","sourceLabel":"Independent campus reporting — athletics–engineering AI data platform","sourceUrl":"https://dailytrojan.com/2026/09/16/viterbi-project-compile-trojan-football-data/","evidenceClass":"independent-reporting","outcomeClass":"emerging","topics":["infrastructure","knowledge-work","operating-model","developers-agents"],"finding":"A 12-person Viterbi data-engineering team has spent about eight months building a football statistics data mart with USC football so analysts can work from analysis-ready play history rather than inconsistent raw feeds. The team coordinates with Conor McQuiston, director of artificial intelligence for USC football. Phase 1 (every play for every team over ~10 years) is described as about to go operational for the current season; phase 2 adds per-player role detail. Staff explicitly defer fourth-down predictive products until data quality is ready. No measured time-savings or competitive outcomes are reported.","sledRelevance":"Newly relevant Power conference implementation signal not in the archive and not in the 2026-09-20 edition: an on-staff AI director plus academic engineering partnership building the data foundation before flashy models—complements archived ASU/Intel on-device play-card automation with a different architecture (central data mart vs local agent).","evidence":"Daily Trojan feature (2026-09-16) quoting Wilcox and Prabhu on operational timing, McQuiston coordination, phase scope, and deferral of predictive decision tools; reference to 2025 Science and Medicine in Football decision-bottleneck study.","architectureImplications":"Interpretation: prioritize play/player event schemas, quality checks, and analyst-facing tables before coaching decision models; keep model experiments in the AI director’s sandbox consuming curated marts rather than raw vendor dumps.","governanceImplications":"Interpretation: name ownership between athletics analytics and academic engineering partners; define which coaches may query which grain of opponent/player data; document that predictive play-calling tools are out of scope until validated.","securityPrivacyImplications":"Interpretation: opponent and proprietary scheme data are competitive secrets—prefer controlled campus identity access; student-athlete biometric streams are not described here and should not be silently added to the same mart without consent review.","caveats":"Campus newspaper, not an audit; “about to go operational” is intent; no metrics; AI-director title is reported; privacy posture unspecified.","streamIds":["college-athletics"],"roles":{"sales":"Open with analyst time lost to messy play data, not generic “AI for football.” USC’s story is a data-mart build coordinated with an on-staff AI director so coaches can ask better questions later—not a finished fourth-down oracle. Discover whether the athletic department already funds an AI/analytics lead, what film/stats vendors feed today, and who owns schema changes. Value is bounded: faster analyst cycles and reusable play history. Do not sell win guarantees or claim the Viterbi project has published prep-time savings.","engineering":"Fit is campus data engineering for football analytics: ingest multi-year play feeds, normalize into a mart, then hand curated tables to the AI director’s team. Integrate with existing film/stats vendors via batch pipelines and role-based query layers; keep experimental models off production coach dashboards until data contracts stabilize. Prerequisites include sustained engineering staffing, clear athletics–academic IP/access agreements, and quality SLAs. Constraint: reporting says predictive products are explicitly deferred. Security: treat scheme and opponent data as confidential athletics IP.","delivery":"Delivery work is phased mart release (play-level, then player-role), analyst onboarding, and feedback loops from the AI director on which coach questions the data can answer. Dependencies: Viterbi/athletics coordination, source-data licenses, and identity access. Ownership: football AI/analytics lead owns product questions; engineering owns pipelines. Skills: SQL/data quality for analysts; coaches learn query limits. Governance checkpoints: go-live criteria for phase 1, written ban on unvalidated auto-play-calling, quarterly data-quality review. Risks: premature predictive demos, schema drift, and over-claiming competitive edge."},"roleDetails":{"sales":{"customerProblem":"Football analysts spend scarce week-of-game hours cleaning inconsistent multi-vendor play data instead of producing coaching insights.","stakeholders":["Director of football AI/analytics","Head coach / coordinators","Athletics CIO/IT","Academic engineering partner","Compliance (data use)"],"discoveryQuestions":["Who owns the football analytics stack and data contracts today?","Which play/film vendors feed the staff, and how messy are joins?","Is there an AI/analytics director role with authority over tools?","Which coach questions must wait until data quality is fixed?"],"valueHypothesis":"If a curated multi-year play mart reaches operational use, analyst time can shift from wrangling to insight generation—without claiming automatic win-rate lift.","potentialEngagement":"Four-to-six-week discovery of current football data sources, a mart MVP scope, and access matrix with the AI/analytics lead.","unsupportedClaims":["Guaranteed prep-time percentage savings","Ready fourth-down or play-calling automation","That USC’s model generalizes to every Power program’s vendor mix"]},"engineering":{"fit":"Athletics–engineering data platform for football play/player history feeding human analysts and later models.","architectureIntegration":"Batch ingest of historical play feeds into a governed mart; semantic layer for analysts; separate sandbox for AI experiments consuming curated tables only.","prerequisites":["Multi-year play-level source access","Named AI/analytics product owner","Identity and environment separation for athletics IP"],"constraints":["Predictive decision products explicitly deferred in source","Campus partnership staffing may be seasonal","No published performance SLOs yet"],"security":"Restrict opponent/scheme data; no uncontrolled export of proprietary tendencies; separate student-athlete biometric stores if ever added.","proofOfValue":["Analyst hours on wrangling vs insight before/after phase 1","Documented coach questions newly answerable","Data-quality defect rate on play keys"]},"delivery":{"work":"Phase-1 mart go-live, analyst training, feedback cadence with football AI director, phase-2 player-role enrichment backlog.","dependencies":["Vendor data licenses","Athletics–academic collaboration agreement","Identity/access provisioning"],"ownership":"Football AI/analytics director owns use cases; data engineering owns pipelines and quality.","skillsAdoption":"Analysts adopt mart schemas; coaches learn what is queryable vs still manual.","governanceCheckpoints":["Written phase-1 acceptance criteria","Ban on unvalidated auto-recommendation tools","Quarterly access review"],"acceptanceCriteria":["Phase-1 play history queryable by named analysts","Documented data dictionary","No unauthorized external data shares in pilot"],"risks":["Operational claim slips without quality gates","Model demos before data contracts mature","IP leakage via academic collaboration tooling"]}},"retrievedAt":"2026-09-22T03:10:45Z","enrichedAt":"2026-09-22T03:15:28Z","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Interpretation: graduate engineering collaborators and football analysts need shared documentation so knowledge does not leave with a single student lead.","procurementImplications":"Interpretation: fund data-platform staffing and source licenses before buying another black-box play-calling AI.","operatingModelImplications":"Interpretation: keep human AI/analytics ownership between mart and coaches; treat academic partners as pipeline contributors, not game-day decision makers.","sourceVerification":{"openedUrl":"https://dailytrojan.com/2026/09/16/viterbi-project-compile-trojan-football-data/","referenceExcerpt":"After eight months of preparation, they are “about to go operational” with the first phase","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}