Forecasting the term structure of commodities future prices using machine learning

Figueiredo, Mário A. T.; Saporito, Yuri F.

doi:10.1007/s42521-022-00069-3

Cited by 3 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They engaged in informal conversations regarding the effect's potential causes and identified seasonal hedging pressures and market sentiment. In their study of commodity futures prices conducted in 2023, Figueiredo and Saporito utilized machine learning to examine commodity price movements with seasonal trends [11]. These studies show that researchers are increasingly turning to machine learning to study commodity futures prices with seasonality, indicating that the field of study is entering a new era.…”

Section: Introductionmentioning

confidence: 99%

Time Series Analysis of Grains Commodity Futures Price Trends

Shao

2024

HSET

View full text Add to dashboard Cite

This study delves into forecasting commodity price trends, explicitly utilizing the ETS and SARIMA models to analyze grains-Soybeans, Corn, Wheat and Soybean Meal. The research underscores the intrinsic seasonal and cyclical attributes of these commodities. While the ETS model provides initial predictions, it reveals limitations in accuracy. Subsequently, the SARIMA model, incorporating seasonal parameters, emerges as a more dependable predictor of price trends. The study emphasizes the significance of considering external factors, such as geopolitics and alterations in transport routes, especially concerning high-value commodities like soybeans. By enhancing forecast precision, the paper underscores the necessity for meticulous model selection, acknowledging the intricate dynamics of seasonal fluctuations in commodity futures prices. In conclusion, the SARIMA model stands out for its superior ability to capture and predict the nuances of seasonal patterns, providing valuable insights for investors and researchers navigating the complex landscape of commodity markets. Its comprehensive analysis of seasonal trends and precise forecasting capabilities make it a preferred choice for understanding and anticipating the complexities of commodity price movements.

show abstract

Section: Introductionmentioning

confidence: 99%