Determinants of Scoring in the World Wide Technology Championship
This analysis is based on scores and stats from individual rounds in the last ten World Wide Technology Championships: 4,100 rounds in total. Note: this event was played at El Camaleon Golf Course until 2022.
Section 1: Absolute Correlation Coefficients with Score
Key Points:
- Greens in Regulation (GIR) has a consistently high correlation with score across years.
- PPGIR (Putts Per Green in Regulation) shows a strong correlation, particularly in recent years, reaching 0.63 in 2023.
- Scrambling exhibits moderate correlation, underscoring its role in score recovery, especially notable in previous years.
Differences in 2023 at El Cardonal at Diamante Cabo San Lucas: The 2023 event saw a decrease in correlation for Scrambling and Driving Accuracy, reflecting course layout differences from El Camaleon.
Key Points:
- Par-4 Holes consistently show high correlation with score, particularly strong across years.
- Par-5 Holes have moderate correlation, peaking in 2018 and 2023, highlighting the scoring potential on longer holes.
- Par-3 Holes show lower but stable correlation, indicating consistency without substantial influence on overall performance.
Differences in 2023 at El Cardonal at Diamante Cabo San Lucas: The 2023 event showed a slight decline in the Par-4 correlation, likely due to layout adjustments, with an increase in the Par-5 correlation indicating more impactful scoring on these holes.
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:
- PPGIR (37.37%) emerged as the most critical factor, indicating the substantial influence of putting on score.
- Scrambling (30.92%) also showed high importance, reinforcing the need for recovery skills.
- Greens in Regulation (23.07%) was significant, aligning with the general trend that approach accuracy impacts scoring.
Comparison with PGA Tour Averages: The traditional metric importances differ slightly from the PGA averages (PPGIR: 30.13%, Scrambling: 27.02%, GIR: 29.77%) with PPGIR and Scrambling showing higher importance. The data suggests an increased emphasis on short game and recovery for the analysed tournaments.
Key Points:
- Par-4 (63.60%) was the dominant metric, aligning with the PGA average (67.12%) and highlighting the score influence of Par-4 holes.
- Par-5 (20.99%) showed moderate importance, indicating opportunities to score on longer holes.
- Par-3 (15.41%) had the least impact, yet still played a role in overall scoring.
Comparison with PGA Tour Averages: The importance levels align closely with PGA averages (Par-3: 17.32%, Par-4: 67.12%, Par-5: 15.56%), confirming that Par-4 performance is critical, while Par-5 offers scoring opportunities.
Top 5 Ranked Players - 2024 World Wide Technology Championship
The table below shows the top-5 ranked players and their average estimated scores from the different Random Forest models above.
| Rank | Surname | Firstname | Average Predicted Score |
|---|---|---|---|
| 1 | Shipley | Neal | 68.93 |
| 2 | Noh | Seung-Yul | 69.08 |
| 3 | Smotherman | Austin | 69.09 |
| 4 | Vegas | Jhonattan | 69.12 |
| 5 | Hoey | Rico | 69.18 |
Estimated scores for all players can be found here.