Project Details

Data-Driven Scouting: A Statistical Model for Ranking & Evaluating High School Quarterbacks

Data-Driven Scouting

This document presents an insightful approach to high school quarterback scouting by leveraging the 2024 recruiting class. Utilizing econometric and machine learning models, we developed an intuitive ranking system capable of evaluating thousands of players simultaneously. This methodology is aimed at:

  • Minimize bias in the scouting and recruiting process.
  • Optimize resources allocation, saving time and costs.
  • Identify top prospects aligned with program requirements.
  • Provide a competitive edge over rival programs.

By integrating data-driven decision-making, this system enhances both the efficiency and effectiveness of talent scouting and recruitment.

We begin by establishing a conceptual framework to identify common scouting biases, then analyze the key characteristics and statistics that predict collegiate success. This foundation allows us to develop a robust statistical model that evaluates each player's potential, classifies their playstyle, and generates comprehensive rankings for the entire 2024 recruiting class.

The resulting data-driven approach minimizes subjective bias while providing programs with actionable insights. By quantifying player potential and fit, our model helps teams optimize their recruiting strategy, saving time and resources while gaining a competitive advantage in identifying the most promising prospects.

The models developed for this algorithm prioritize comprehensiveness and user-friendliness, ensuring coaching staff and recruiters can easily understand and implement them. While maintaining statistical rigor throughout, we explicitly document all technical assumptions - including their potential impact on results - and provide clear guidance for addressing various analytical challenges.

This research proposes an innovative ranking system to help college programs gain a competitive recruiting advantage through data-driven insights. DLB Metrics seeks to establish long-term partnerships, providing end-to-end support including model implementation, detailed analytical scouting profiles, and customized follow-up studies tailored to each program's specific needs— ensuring continuous improvement and strategic value in player evaluation.

This document introduces a data-driven approach to streamline player scouting, helping colleges evaluate talent more efficiently and equitably—giving every athlete a fair shot at collegiate play.