This project evaluates whether individual driver performance meaningfully impacts revenue and operational outcomes, or whether performance is driven primarily by system-level factors. The objective is to inform where operational focus and analytical effort should be directed.
Operations teams often evaluate performance at the individual driver level under the assumption that driver behavior materially affects revenue and efficiency. This analysis tests that assumption by examining the relationship between driver-level KPIs and revenue outcomes.
- Driver-level performance metrics showed minimal variation across individuals
- Individual driver KPIs exhibited limited explanatory power with respect to revenue outcomes
- Results indicate that system-level operational factors, rather than individual driver performance, are more likely to drive revenue and efficiency
- Individual driver performance is unlikely to be a high-impact management lever
- Operational improvement efforts would likely yield greater returns by focusing on routing, load characteristics, demand patterns, or pricing
- The analysis helps prevent misallocation of management attention and analytics resources toward low-impact drivers
- Defined the analytical question based on common operational assumptions around driver performance
- Designed a relational data model and created SQL views to standardize KPI definitions, using CTEs for ad-hoc analysis and validation
- Visualized performance distributions, comparisons, and trends using Power BI
- SQL scripts for data modeling, KPI calculation, and validation
- Reusable SQL views supporting consistent performance definitions
- Interactive Power BI dashboards for fleet-level monitoring and trend analysis
Future iterations of this project will incorporate route-level, load-level, and time-based demand data to evaluate system-level drivers of operational performance identified by this analysis.
Anthony Desimone
🔗 www.linkedin.com/in/anthonyfdesimone
Data Analytics | SQL | Power BI | Data Modeling