The study "Palladium Price Predictions via Machine Learning" by Bingzi Jin and Xiaojie Xu aims to predict daily palladium prices for the United States using time series data from January 5, 1977, to March 26, 2024. The research addresses the challenge of accurate price predictions, which have been crucial for governments and investors. The authors employ Gaussian process regression algorithms, cross-validation, and Bayesian optimization to generate price estimates. Their empirical model achieves a relative root mean square error of 0.4598% for the out-of-sample period from March 24, 2017, to March 26, 2024. This method provides valuable insights for informed decision-making in the palladium industry. The study highlights the importance of time series forecasts for commodity prices and the potential of machine learning in enhancing predictive accuracy.The study "Palladium Price Predictions via Machine Learning" by Bingzi Jin and Xiaojie Xu aims to predict daily palladium prices for the United States using time series data from January 5, 1977, to March 26, 2024. The research addresses the challenge of accurate price predictions, which have been crucial for governments and investors. The authors employ Gaussian process regression algorithms, cross-validation, and Bayesian optimization to generate price estimates. Their empirical model achieves a relative root mean square error of 0.4598% for the out-of-sample period from March 24, 2017, to March 26, 2024. This method provides valuable insights for informed decision-making in the palladium industry. The study highlights the importance of time series forecasts for commodity prices and the potential of machine learning in enhancing predictive accuracy.