Characteristic mango price forecasting using combined deep-learning optimization model

• Published in: PloS one Vol. 18; no. 4; p. e0283584
• Main Authors: Ma, Xiaoya, Tong, Jin, Huang, Wu, Lin, Haitao
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 13.04.2023; Public Library of Science (PLoS)
• Subjects: Accuracy; Back propagation; Back propagation networks; Biology and Life Sciences; China; Computer and Information Sciences; Decision making; Deep Learning; Econometrics; Forecasting; Forecasting techniques; Forecasts and trends; Fruits; Learning; Long short-term memory; Mangifera; Mangoes; Modelling; Neural networks; Neural Networks, Computer; Optimization; Optimization models; People and Places; Physical Sciences; Prices; Pricing; Propagation; Regional development; Regional planning; Research and Analysis Methods; Short term memory; Social Sciences; Wholesale industry; China; India
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0283584

Accurate product price forecasting is helpful for scientific decision-making and precise industrial planning. As a characteristic fruit that drives regional development, mango price prediction is of great significance to several economies. However, owing to the strong volatility of mango prices, forecasting is vulnerable to uncertainties and is very challenging. In this study, a deep-learning combination forecasting model based on a back-propagation (BP) long short-term memory (LSTM) neural network is proposed. Using daily mango price data from a large fruit wholesale trading center in China from January 2 nd , 2014, to April 18 th , 2022, mango price changes are learned and predicted to support the fruit industry. The results show that the root mean-square error, mean absolute percentage error, and the R 2 determination coefficient of the BP-LSTM combination model are 0.0175, 0.14%, and 0.9998, respectively. The prediction results of the combined model are better than those of the separate BP and LSTM models. Furthermore, it best fits the actual price profile and has better generalizability.