Determinants of Scoring at East Lake Golf Club
This analysis is based on scores and stats from individual rounds in the ten Tour Championships at East Lake Golf Club: 1,179 rounds in total.
Section 1: Absolute Correlation Coefficients with Score
SGTee: The correlation between Score and SGTee exhibits noticeable variation across the years, with peaks in 2018 and 2023, but much lower values inbetween.
SGApp: The correlation for SGApp (Strokes Gained on Approach) generally shows a consistent pattern, indicating that approach shots remain a critical factor in scoring on this course.
SGATG: SGATG (Strokes Gained Around the Green) appears to have a more variable relationship with Score, but is more consistently has the lowest correlation with Score.
SGP: The correlation for SGP (Strokes Gained Putting) shows that putting is consistently influential on scoring, although the degree of influence varies.
DrivingDistance: The correlation between Score and DrivingDistance tends to vary, indicating that while distance off the tee can be advantageous, it is not always the most critical factor in scoring well at East Lake.
DrivingAccuracy: The relationship between Score and DrivingAccuracy is more stable, reflecting the importance of staying in play on this course, where penal rough and hazards can significantly impact scoring.
GreensInRegulation: GreensInRegulation shows a strong and relatively stable correlation with Score, underlining that hitting greens consistently is crucial for low scores at East Lake.
Scrambling: The Scrambling metric shows variable correlation, but has a consistently higher correlation with scoring than the driving metrics
PPGIR: The correlation with PPGIR (Putts Per GIR) reinforces the significance of putting well, with similar correlations to Score with the GreensInRegulation and Scrambling metrics.
Par3: The correlation between Score and Par3 performance varies considerably, most notably in recent year.
Par4: The Par4 correlation is generally strong and consistent, making them a key determinant of scoring at East Lake Golf Club.
Par5: The correlation with Par5 performance is typically lower and more variable, indicating that while scoring on par-5s can help, it is not as critical as par-4 performance.
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.
Relative Importance (as a percentage):
- SGTee: 27.68%
- SGApp: 30.12%
- SGATG: 20.56%
- SGP: 21.64%
SGTee: The relative importance of SGTee at 27.68% underscores the significance of a strong performance off the tee at East Lake Golf Club. This is slightly higher than the PGA Tour average of 24.82%, indicating that distance and accuracy from the tee may be more crucial on this course compared to others.
SGApp: With the highest relative importance at 30.12%, SGApp (Strokes Gained on Approach) is critical for scoring at East Lake. This aligns with the course's demand for precise approach shots to navigate well-guarded greens, and it is slightly above the tour average of 26.77%.
SGATG: The importance of SGATG (Strokes Gained Around the Green) is 20.56%, which is lower than the PGA Tour average of 24.44%. This may suggest that while short-game skills are important, they are less impactful at East Lake compared to approach shots and tee performance.
SGP: SGP (Strokes Gained Putting) accounts for 21.64% of the scoring impact, closely aligning with the tour average of 23.98%. This highlights the ongoing importance of putting, especially on East Lake's challenging greens.
Summary: The analysis reveals that approach play (SGApp) and tee shots (SGTee) are particularly critical at East Lake, possibly more so than on other courses. The slightly higher importance of these metrics compared to the PGA Tour averages suggests that East Lake demands precision in these areas. In contrast, the slightly lower importance of SGATG suggests that recovery shots around the green, while important, may play a lesser role in determining the outcome here.
Relative Importance (as a percentage):
- DrivingDistance: 8.74%
- DrivingAccuracy: 4.89%
- GreensInRegulation: 32.41%
- Scrambling: 29.57%
- PPGIR: 24.39%
DrivingDistance: The relative importance of DrivingDistance is 8.74%, which is close to the PGA Tour average of 9.31%. This suggests that while driving distance contributes to scoring, it is not the most critical factor at East Lake, where precision and strategy might outweigh pure distance.
DrivingAccuracy: DrivingAccuracy accounts for 4.89%, slightly higher than the tour average of 3.77%. This indicates that hitting fairways is somewhat more critical at East Lake, likely due to the course's penal rough and strategic challenges.
GreensInRegulation: With the highest relative importance at 32.41%, GreensInRegulation is crucial at East Lake, emphasizing the need to hit greens consistently to set up scoring opportunities. This value is higher than the PGA Tour average of 29.77%, reinforcing the importance of approach accuracy on this course.
Scrambling: Scrambling has a significant impact with 29.57%, closely matching the tour average of 27.02%. This suggests that the ability to recover and save par when missing greens is essential for good scoring at East Lake.
PPGIR: PPGIR (Putts Per GIR) is also important at 24.39%, although slightly lower than the tour average of 30.13%. This might indicate that while putting is always critical, the emphasis at East Lake may lean more towards approach play and scrambling.
Summary: The analysis highlights the importance of GreensInRegulation and Scrambling at East Lake, both of which play a slightly larger role in determining scores here compared to the PGA Tour averages. The findings suggest that the course demands a high level of precision in hitting greens and recovering when missing them. The slightly lower importance of DrivingDistance and PPGIR indicates that, while still important, these metrics may not be as decisive as approach accuracy and scrambling ability at East Lake.
Relative Importance (as a percentage):
- Par3: 18.66%
- Par4: 70.74%
- Par5: 10.60%
Par3: The relative importance of Par3 performance is 18.66%, slightly higher than the PGA Tour average of 17.32%. This suggests that East Lake's par-3 holes play a more significant role in determining overall scores than at other PGA Tour courses.
Par4: The overwhelming importance of Par4 performance at 70.74% reflects the critical nature of par-4 holes at East Lake, consistent with their prominence and difficulty on the course. This value is also higher than the tour average of 67.12%, further emphasizing their significance.
Par5: Par5 performance, with a relative importance of 10.60%, is lower than the tour average of 15.56%. This suggests that scoring on par-5s, while beneficial, may not be as crucial at East Lake, where par-4s are more defining.
Summary: The findings underscore the critical importance of par-4 performance at East Lake, which plays an even larger role than on the PGA Tour overall. The slightly higher importance of Par3 performance also highlights the unique challenges posed by East Lake's par-3 holes. Conversely, the relatively lower importance of Par5 performance suggests that while advantageous, success on these holes may not be as critical for overall scoring compared to par-3s and par-4s.
Top 5 Ranked Players - 2024 Tour Championship
The table below shows the top-5 ranked players and their average estimated scores from the different Random Forest models above.
| Player | Score |
|---|---|
| Scottie Scheffler | 66.88 |
| Ludvig Aberg | 67.06 |
| Xander Schauffele | 68.49 |
| Aaron Rai | 68.24 |
| Tommy Fleetwood | 68.25 |
Estimated scores for all players can be found here.