Peanut oil price change forecasts through the neural network
Прогнозы изменения цен на арахисовое масло с помощью нейронной сети
2025-01-14
SCID: 54.1/ds6ek5s5
Discuss with AI
NAR-NNnonlinear auto-regressive neural networkpeanut oil price forecastingroot mean square errorweekly wholesale price index
Figures from the paper
Abstract (AI)
Purpose For a wide range of market actors, including policymakers, forecasting changes in commodity prices is crucial. As one of essential edible oil, peanut oil’s price swings are certainly important to predict. In this paper, the weekly wholesale price index for the period of January 1, 2010 to January 10, 2020 is used to address this specific forecasting challenge for the Chinese market. Design/methodology/approach The nonlinear auto-regressive neural network (NAR-NN) model is the forecasting method used. Forecasting performance based on various settings, such as training techniques, delay counts, hidden neuron counts and data segmentation ratios, are assessed to build the final specification. Findings With training, validation and testing root mean square errors of 5.89, 4.96 and 5.57, respectively, the final model produces reliable and accurate forecasts. Here, this paper demonstrates the applicability of the NAR-NN approach for commodity price predictions. Originality/value On the one hand, the findings may be used as independent technical price movement predictions. Conversely, they may be included in forecast combinations with forecasts derived from other models to form viewpoints of commodity price patterns for policy research.
Key Findings
1
A nonlinear auto-regressive neural network (NAR-NN) was applied to forecast weekly wholesale peanut oil price index in China (2010-01-01 to 2020-01-10).
2
Model selection explored training techniques, delay counts, hidden neuron counts, and data segmentation ratios to determine the final specification.
3
The final NAR-NN achieved training, validation, and testing RMSEs of 5.89, 4.96, and 5.57 respectively, indicating reliable and accurate forecasts.
4
The study demonstrates the applicability of NAR-NN for commodity price prediction and suggests its forecasts can be used standalone or combined with other models for policy research.
Research Object
Weekly wholesale price index of peanut oil in the Chinese market (Jan 1, 2010–Jan 10, 2020)
Research Subject
Forecasting changes in the peanut oil weekly wholesale price index using a nonlinear auto-regressive neural network (NAR-NN), including assessment of model settings (training technique, delay count, hidden neurons, data segmentation) and forecast accuracy (RMSE)
Publication Details
Publication Date
2025-01-14
Journal
Publisher
ISSN
Cited by
213
Access Type
Author Information
Download PDF
Subscribe to digest