### 4.1 Analytics Readiness The boxing dataset demonstrates strong foundational quality with 97% completeness and 14 explicit dimension hierarchies spanning fighter attributes, match outcomes, and temporal dimensions. However, the data is structured as five parallel dimension tables (cleandata through cleandata_v5) with no validated joins, limiting immediate cross-table analytics. For commerce applications—such as predicting fighter marketability, optimizing event scheduling, or forecasting pay-per-view demand—the current structure requires consolidation into a unified analytical layer before advanced modeling can deliver reliable business value. ### 4.2 Strategic ML Opportunities | Model Type | Prediction Target | Viability | Applicable Tables | |------------|-------------------|-----------|-------------------| | Time-Series Forecasting | Future values of a measure over time (e.g. s_boxer_ranking, f_boxer_ranking, f_boxer_age) | Low | cleandata | | Anomaly Detection | Outlier or unusual records (e.g. s_boxer_ranking, f_boxer_ranking, f_boxer_age) | Low | cleandata | | Regression | Continuous target (e.g. s_boxer_ranking, f_boxer_ranking, f_boxer_age) | Low | cleandata | All three model types currently rate **low viability** due to the absence of outcome variables tied to commercial performance—ticket sales, viewership, or sponsorship revenue are not present. Time-series forecasting of fighter rankings (s_boxer_ranking, f_boxer_ranking) offers the most immediate path to ROI if enriched with revenue or engagement metrics, enabling predictions of which matchups will drive the highest commercial returns. This requires linking the 127-row cleandata table to transactional systems capturing event-level financial performance. ### 4.3 Investment Recommendations - **Consolidate parallel tables (30 days):** Merge cleandata through cleandata_v5 into a single master fighter-match table, resolving the 12-row discrepancy in cleandata_v4 and establishing a unified schema for all downstream analytics. - **Enrich with commercial KPIs (60 days):** Integrate pay-per-view buys, gate receipts, and social media engagement metrics at the match level to transform ranking and KO pattern data into predictive features for revenue forecasting models. - **Pilot fighter marketability scoring (90 days):** Build a regression model using s_boxer_ranking, f_boxer_ranking, win/loss/KO patterns, and the proposed engineered feature to score fighters' commercial appeal, prioritizing high-value matchups for promotional investment. - **Establish temporal aggregation pipelines:** Leverage the 14 dimension hierarchies to create rolling career trajectory metrics (win streaks, knockout rates by weight class) that feed anomaly detection for identifying breakout talent or declining performance trends.