Determinants of Scoring in the Irish Open

This analysis is based on scores and stats from individual rounds in the last ten Irish Opens: 4,461 rounds in total.

Section 1: Absolute Correlation Coefficients with Score

Key Points

• SGTee demonstrated a consistent correlation with "Score", highlighting the importance of tee shots throughout the years.
• SGApp correlation fluctuated, especially in recent years, showing the varying influence of approach shots.
• During the Irish Open, SGATG had a higher correlation with "Score", suggesting that short game skills were critical at this event.

Key Points

• GreensInRegulation consistently correlated highly with "Score", reinforcing the importance of accurate approach play.
• DrivingDistance's correlation varied year by year, reflecting its inconsistent influence on scores.
• Scrambling was particularly important during the Irish Open, where it correlated strongly with "Score".

Key Points

• Par4 performance showed the highest correlation with "Score", suggesting it was the most significant par type.
• Par5 correlation fluctuated, indicating varying importance depending on the course setup.
• At the Irish Open, Par3 performance played a crucial role, showing a higher correlation than other par types.

Section 2: Importance of Each Metric in Determining Score

Random Forest Regressor and Feature Importance

Random Forest Regressor is an ensemble learning method that constructs multiple decision trees during training and outputs the average prediction. It combines the predictions of several models to improve accuracy and robustness.

Feature importance is a technique used to interpret a machine learning model. It refers to the score that quantifies the contribution of each feature to the prediction made by the model.

In a Random Forest, the importance of a feature is computed by looking at how much the feature decreases the impurity (e.g., variance for regression tasks) across all the trees in the forest. The more a feature decreases the impurity, the more important it is considered.

The calculated importance scores for all features are then normalized to give relative importance as a percentage. This shows the relative contribution of each feature to the prediction task.

Interpreting Feature Importance

Features with high relative importance percentages have a strong impact on the model's predictions. They are crucial for accurate predictions and indicate key areas where performance matters most.

Features with low relative importance have a minimal impact on the model's predictions. While they can still contribute, they are less critical.

Key Points

• SGApp (Approach Shots) had the highest relative importance (40.31%), much higher than the DP World Tour average of 28.85%.
• SGTee's relative importance was lower (17.85%), indicating that tee shots had less influence on scoring in this event compared to the tour average of 25.36%.
• SGP (Putting) showed higher importance (30.07%), highlighting the increased role of putting, especially at the Irish Open.

Key Points

• DrivingDistance (7.51%) and DrivingAccuracy (5.27%) had lower importance, suggesting that distance and accuracy off the tee were secondary factors in scoring.
• GreensInRegulation (28.13%) aligned closely with the DP World Tour average, demonstrating its continued importance in determining scores.
• Scrambling (30.39%) and PPGIR (28.71%) were crucial, exceeding the DP World Tour averages, which highlights the emphasis on recovery and putting during the Irish Open.

Key Points

• Par4 performance (67.05%) was significantly higher than the DP World Tour average, confirming the importance of performing well on Par4 holes.
• Par3 (17.42%) had a slightly higher importance than the tour average, highlighting the role of precision on shorter holes during the event.
• Par5 performance (15.52%) was lower than the average, indicating that longer holes played a slightly lesser role in determining overall scores.

Top 5 Ranked Players - 2024 Irish Open

The table below shows the top-5 ranked players across the three different Random Forest models above.

Rankings and estimated scores for all players can be found here.