Global Forest Change dataset

to use random forests: when you want a strong baseline with minimal hyperparameter tuning

Random forests are ideal for robust baseline models with minimal hyperparameter tuning

Boosting (machine learning)

Boosting reduces bias in ML models

cross-entropy equals negative log-likelihood for classification

Cross-entropy measures the difference between predicted probabilities and true labels, thus it equals negative log-likelihood, reflecting the cost of incorrect predictions

log-loss / cross-entropy loss penalizes: confident wrong predictions more heavily

Log-loss penalizes confident incorrect predictions more heavily

to use XGBoost: for tabular data where you want the best possible performance

Use XGBoost for high-performance predictions on structured tabular data

Regression discontinuity design

RDD uses a sharp threshold for treatment assignment