PostgreSQL-based strategic analysis of 25 years of Broadway performance data
Designed and analyzed a normalized relational database in PostgreSQL to identify the financial and operational drivers of commercial success across 145 Broadway productions and 47,500+ weekly performance records (1995–2020). The analysis quantified Tony Award marketing ROI, identified longevity predictors, evaluated launch timing effects, and built a production type risk-return framework. This project is framed as strategic intelligence for The Broadway League.
Broadway producers and theater owners invest millions in productions with limited data-driven guidance on what predicts commercial success. The Broadway League needed actionable intelligence to help stakeholders make informed decisions about production development, marketing investment, and long-term sustainability planning.
Built a 3-table normalized schema (shows, financials, tony_awards) in PostgreSQL and developed 18 analytical queries using CTEs, window functions (LAG, ROW_NUMBER), multi-table JOINs, CASE statements, and date arithmetic. Show metadata for all 145 productions was manually researched and classified using IBDB.com and Wikipedia. Statistical validation was performed using paired t-tests and Wilcoxon signed-rank tests in Python.
Statistical validation (paired t-test, p < 0.001; Wilcoxon signed-rank, p < 0.001) confirms the Tony Award revenue lift is not attributable to chance. The 95% confidence interval for the mean weekly increase is $162,946 to $323,638.
For a full technical breakdown including code, queries, and methodology, view this project on GitHub.
← All Projects