Chapter 21: Further Reading

Books

• Anderson, C., & Sally, D. (2013). The Numbers Game: Why Everything You Know About Soccer Is Wrong. Penguin Books. A foundational text on soccer analytics that covers many of the statistical concepts underlying modern recruitment, including expected goals, age curves, and the value of different playing positions.

• Kuper, S., & Szymanski, S. (2018). Soccernomics: Why England Loses; Why Germany, Spain, and France Win; and Why One Day Japan, Iraq, and the United States Will Become Kings of the World's Most Popular Sport (5th ed.). Nation Books. Explores the economics of player transfers, including market inefficiencies and the sociology of recruitment networks.

• Biermann, C. (2019). Football Hackers: The Science and Art of a Data Revolution. Blink Publishing. An accessible account of how data analytics has transformed football, with extensive coverage of recruitment departments at clubs including Brentford, Midtjylland, and Liverpool.

• Tango, T., Lichtman, M., & Dolphin, A. (2007). The Book: Playing the Percentages in Baseball. Potomac Books. While focused on baseball, this text introduced the MARCEL projection system and many of the statistical concepts (regression to the mean, aging curves, reliability coefficients) that have been adapted for soccer analytics.

• Connelly, G. (2022). Expected Goals: The Story of How Data Conquered Football and Changed the Game Forever. HarperCollins. Chronicles the rise of expected goals as the dominant metric in football analytics, with extensive discussion of its application in recruitment.

• Smith, R. (2022). Expected Goals: How Data Changed Football Forever. Mudlark. A complementary perspective on the data revolution in football, with particular attention to recruitment case studies.

Academic Papers

• Decroos, T., Bransen, L., Van Haaren, J., & Davis, J. (2019). "Actions Speak Louder than Goals: Valuing Player Actions in Soccer." Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 1851-1861. Introduces the VAEP framework for valuing on-ball actions, which has significant applications in recruitment scoring models.

• Fernandez, J., Bornn, L., & Cervone, D. (2021). "Decomposing the Immeasurable Sport: A Deep Learning Expected Possession Value Framework for Soccer." MIT Sloan Sports Analytics Conference. Presents a framework for valuing possession sequences, relevant to evaluating a player's contribution beyond simple event-level metrics.

• Trainor, C., & Dwyer, B. (2021). "Adjusting Player Statistics Across Leagues." Journal of Sports Analytics, 7(3), 189-205. Directly addresses the cross-league comparison problem discussed in Section 21.5, proposing methodologies for league adjustment factors.

• Pappalardo, L., et al. (2019). "A Public Data Set of Spatio-Temporal Match Events in Soccer Competitions." Scientific Data, 6, 236. Describes a publicly available dataset that can be used to practice the recruitment analysis techniques discussed in this chapter.

• Brooks, J., Kerr, M., & Guttag, J. (2016). "Developing a Data-Driven Player Ranking in Soccer Using Predictive Model Weights." Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 49-55. Proposes a method for weighting player metrics based on their predictive value for team success.

• Muller, O., Simons, A., & Weinmann, M. (2017). "Beyond Crowd Judgments: Data-Driven Estimation of Market Value in Association Football." European Journal of Operational Research, 263(2), 611-624. Explores quantitative models for estimating player market value, relevant to the financial risk assessment discussed in Section 21.6.

• Power, P., Ruiz, H., Wei, X., & Lucey, P. (2017). "Not All Passes Are Created Equal: Objectively Measuring the Risk and Reward of Passes in Soccer from Tracking Data." Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1605-1613. Demonstrates how tracking data can enrich the evaluation of passing ability beyond simple completion rates.

Industry Reports and Data Providers

• StatsBomb. Data methodology documentation and open data. StatsBomb provides detailed event data and has published extensively on metrics relevant to recruitment, including expected goals, expected assists, and pressure events. Website: https://statsbomb.com

• Wyscout. A professional scouting and performance analysis platform used by many clubs for video analysis and statistical data. Their data coverage spans 200+ competitions worldwide. Website: https://wyscout.com

• Opta (Stats Perform). One of the longest-established providers of football data, offering event data, advanced metrics, and analytical tools. Website: https://www.statsperform.com

• FBref. A free resource providing detailed player and team statistics sourced from StatsBomb and other providers. An excellent starting point for practicing recruitment analysis. Website: https://fbref.com

• Transfermarkt. The standard reference for player market values, transfer fees, contract information, and injury histories. Website: https://www.transfermarkt.com

• CIES Football Observatory. An academic research group that publishes regular reports on player valuation, league comparisons, and demographic trends in football. Website: https://football-observatory.com

Blog Posts and Online Resources

• StatsBomb Blog. Regularly publishes articles on recruitment-relevant analytics topics, including player evaluation methodologies, league comparisons, and metric development. https://statsbomb.com/articles/

• The Athletic. Produces high-quality long-form journalism on football analytics and recruitment, including detailed accounts of how specific clubs approach data-driven scouting.

• Between the Posts. A blog focused on football analytics with particular attention to goalkeeper analysis and defensive metrics relevant to recruitment.

• Soccerment. Provides analytical tools and research on player evaluation, with regular content on recruitment analytics methodologies.

• McKay Johns (YouTube and Blog). Produces accessible content on football analytics and data visualization techniques applicable to scouting presentations.

Tools and Software

• Python Libraries: pandas, numpy, scikit-learn, matplotlib, seaborn -- the core stack for building recruitment analysis pipelines as demonstrated in the code examples for this chapter.

• mplsoccer. A Python library for creating soccer visualizations including pitch plots, radar charts, and heat maps. Particularly useful for scouting report generation. https://mplsoccer.readthedocs.io

• socceraction. A Python library implementing the VAEP and xT frameworks for valuing player actions. https://github.com/ML-KULeuven/socceraction

• R and the worldfootballR package. An alternative to Python for football data analysis, with the worldfootballR package providing convenient access to data from FBref, Transfermarkt, and other sources.

Related Chapters

• Chapter 7: Expected Goals (xG) Models -- foundational understanding of the xG metric used extensively in recruitment evaluation.
• Chapter 9: Bayesian Methods in Soccer Analytics -- details on the Bayesian shrinkage techniques used for small-sample adjustment in player evaluation.
• Chapter 14: Player Valuation and Market Analysis -- complements this chapter's coverage of recruitment with detailed treatment of financial valuation.
• Chapter 17: Tracking Data and Spatial Analysis -- covers the tracking data methods that provide off-ball insights referenced in Sections 21.1 and 21.7.
• Chapter 22: Youth Development Analytics -- extends the projection and development concepts from Section 21.4 to the youth academy context.