On Building Real Time Intelligent Agricultural Commodity Trading Models
Proceedings - IEEE 8th International Conference on Big Data Computing Service and Applications, BigDataService 2022
The global population is expected to reach 9.7 billion in 2050, according to the UN News . This suggests that food, agriculture, and global commodity trading are essential and critical to human beings. To stabilize food price and better understand and predict the market trend, people need a real-time efficient online platform as an intelligent trading tool to support dynamic agriculture commodity trading. However, current trading platforms lack Al-powered solutions to support traders and investors with dynamic commodity market analysis based on historical big data, accurate forecasts on market trends and trading price forecasts. This paper focuses on this demand by studying and comparing existing machine learning models for intelligent trading and price prediction. The paper presents three improved machine learning models based on LSTM, GRU, and SARIMA, and proposes an advanced deep learning LSTM model with time series and multi-variant features to forecast crop market trends with predicted prices. As a result, our proposed agriculture trading models for crops (corn, oats, soybean, and soybean oil) based the improved LSTM provide great accurate prediction results (>0.95%). Based on our comparative evaluation results, the proposed model outperforms other existing models. The research results show a great potential application for a future intelligent trading platform which provides traders with real-time data driven market analysis and accurate predictions on market trends and commodity trading prices.
commodity trading price prediction, intelligent agriculture commodity trading, smart agriculture
Jiayu Zhou, Jing Ye, Yue Ouyang, Manyuan Tong, Xuedong Pan, and Jerry Gao. "On Building Real Time Intelligent Agricultural Commodity Trading Models" Proceedings - IEEE 8th International Conference on Big Data Computing Service and Applications, BigDataService 2022 (2022): 89-95. https://doi.org/10.1109/BigDataService55688.2022.00021