Thermal coal futures trading volume predictions through the neural network

Journal of Modelling in Management, Год журнала: 2024, Номер unknown

Опубликована: Сен. 16, 2024

Purpose Predicting commodity futures trading volumes represents an important matter to policymakers and a wide spectrum of market participants. The purpose this study is concentrate on the energy sector explore volume prediction issue for thermal coal traded in Zhengzhou Commodity Exchange China with daily data spanning January 2016–December 2020. Design/methodology/approach nonlinear autoregressive neural network adopted performance examined based upon variety settings over algorithms model estimations, numbers hidden neurons delays ratios splitting series into training, validation testing phases. Findings A relatively simple setting arrived at that leads predictions good accuracy stabilities maintains small errors up 99.273 th quantile observed volume. Originality/value results could, one hand, serve as standalone technical predictions. They other be combined different (fundamental) forming perspectives trends carrying out policy analysis.

Язык: Английский

---

Forecasts of coking coal futures price indices through Gaussian process regressions

Mineral Economics, Год журнала: 2024, Номер unknown

Опубликована: Сен. 17, 2024

Язык: Английский

---

Peanut oil price change forecasts through the neural network

foresight, Год журнала: 2025, Номер unknown

Опубликована: Янв. 14, 2025

Purpose For a wide range of market actors, including policymakers, forecasting changes in commodity prices is crucial. As one essential edible oil, peanut oil’s price swings are certainly important to predict. In this paper, the weekly wholesale index for period January 1, 2010 10, 2020 used address specific challenge Chinese market. Design/methodology/approach The nonlinear auto-regressive neural network (NAR-NN) model method used. Forecasting performance based on various settings, such as training techniques, delay counts, hidden neuron counts and data segmentation ratios, assessed build final specification. Findings With training, validation testing root mean square errors 5.89, 4.96 5.57, respectively, produces reliable accurate forecasts. Here, paper demonstrates applicability NAR-NN approach predictions. Originality/value On hand, findings may be independent technical movement Conversely, they included forecast combinations with forecasts derived from other models form viewpoints patterns policy research.

Язык: Английский

---

Predicting Scrap Steel Prices Through Machine Learning for South China

Materials Circular Economy, Год журнала: 2025, Номер 7(1)

Опубликована: Янв. 6, 2025

Язык: Английский

---

Machine learning gold price forecasting

International Journal of Management Science and Engineering Management, Год журнала: 2025, Номер unknown, С. 1 - 13

Опубликована: Янв. 21, 2025

Язык: Английский

---

Machine learning platinum price predictions

The Engineering Economist, Год журнала: 2025, Номер unknown, С. 1 - 27

Опубликована: Фев. 12, 2025

Throughout history, governments and investors have placed trust in price predictions for a wide range of commodities. This research explores the complex problem forecasting daily platinum prices United States using time-series data spanning from January 02, 1969 to March 15, 2024. Estimates not received enough attention previous studies this important assessment commodity pricing. Here, projections are created by Gaussian process regression algorithms that estimated with use cross-validation procedures Bayesian optimization techniques. Arriving at relative root mean square error 1.5486%, our empirical prediction method yields relatively precise out-of-sample phase covering 04/03/2013–03/15/2024. Price models can be used make informed decisions regarding business.

Язык: Английский

---

Machine learning price index forecasts of flat steel products

Mineral Economics, Год журнала: 2024, Номер unknown

Опубликована: Июль 22, 2024

Язык: Английский

---

Predicting open interest in thermal coal futures using machine learning

Mineral Economics, Год журнала: 2024, Номер unknown

Опубликована: Окт. 23, 2024

Язык: Английский

---

Machine learning Brent crude oil price forecasts

Innovation and Emerging Technologies, Год журнала: 2024, Номер 11

Опубликована: Янв. 1, 2024

Forecasts regarding the prices of energy commodities have long been significant to many market players. Our research examines price Brent crude oil on a daily basis in order address issue. The series under investigation has financial ramifications, and sample spans 10 years, from April 7, 2014 March 28, 2024. In this case, cross-validation procedures Bayesian optimization approaches are used construct Gaussian process regression methods, resulting strategies generate estimates. For out-of-sample evaluation period 24, 2022 2024, our empirical prediction technique yields relatively accurate projections prices, as indicated by relative root mean square error 0.2814%. Price models provide governments investors with knowledge they need make informed decisions market.

Язык: Английский

---

Predictions of residential property price indices for China via machine learning models

Quality & Quantity, Год журнала: 2025, Номер unknown

Опубликована: Фев. 11, 2025

Язык: Английский

---