Kicking for Goal or Touch? An Expected Points Framework for Penalty Decisions in Rugby Union

TL;DR

This study develops a data-driven Expected Points (EP) framework to guide penalty decisions in rugby union, specifically choosing between a goal kick or kicking to touch. It constructs two context-aware EP surfaces: EP_lineout from phase-level data (lineout entry) and EP_kick from an angle–distance kick-success model with a continuation value after misses, enabling decision maps that compare EP_lineout(x_{LO}) and EP_kick(x, y) across field locations and game contexts. Key contributions include a first comprehensive EP-based penalty analysis, explicit translation from penalty location to lineout position, scenario analyses of manpower and team strength, and a case study (NZ vs SA) with a regret metric to quantify decision quality; all code is made reproducible for further extension toward win-probability analyses. The framework is modular and adaptable to team-specific kickers and lineout units, and it lays groundwork for richer data integration and broader decision branches in rugby analytics. Overall, the approach provides actionable, location-specific guidance for penalty decisions and advances the state of sport analytics in rugby by marrying phase-level data with field-position–dependent kicking outcomes.

Abstract

Following a penalty in rugby union, teams typically choose between attempting a shot at goal or kicking to touch to pursue a try. We develop an Expected Points (EP) framework that quantifies the value of each option as a function of both field location and game context. Using phase-level data from the 2018/19 Premiership Rugby season (35,199 phases across 132 matches) and an angle-distance model of penalty kick success estimated from international records, we construct two surfaces: (i) the expected points of a possession beginning with a lineout, and (ii) the expected points of a kick at goal, taking into account the in-game consequences of made and missed kicks. We then compare these surfaces to produce decision maps that indicate where kicking for goal or kicking to touch maximizes expected return, and we analyze how the boundary shifts with game context and the expected meters gained to touch. Our results provide a unified, data-driven method for evaluating penalty decisions and can be tailored to team-specific kickers and lineout units. This study offers, to our knowledge, the first comprehensive EP-based assessment of penalty strategy in rugby union and outlines extensions to win-probability analysis and richer tracking data.

Figures (9)

• Figure 1: Field zones used in the phase-level dataset
• Figure 2: Average expected points of the next score given lineout position
• Figure 3: Estimated probability of kick success by position on the pitch. Note that the goal posts are located at lateral position 0. Kick probabilities begin at 5 m from the goal line
• Figure 4: Estimated expected points of a penalty kick by position on the pitch
• Figure 5: Decision maps comparing the expected points of a lineout versus a kick at goal for different assumed meters gained to touch $d_{\text{touch}}$.