Soybean Price Trend Forecast Using Deep Learning Techniques Based on Prices and Text Sentiments

Roberto F. Silva (), Angel F. M. Paula (), Gustavo M. Mostaço (), Anna H. R. Costa and Carlos E. Cugnasca ()
Additional contact information
Roberto F. Silva: Department of Computer Engineering and Digital Systems, Escola Politécnica da Universidade de São Paulo (USP)
Angel F. M. Paula: Department of Computer Engineering and Digital Systems, Escola Politécnica da Universidade de São Paulo (USP)
Gustavo M. Mostaço: Department of Computer Engineering and Digital Systems, Escola Politécnica da Universidade de São Paulo (USP)
Anna H. R. Costa: Department of Computer Engineering and Digital Systems, Escola Politécnica da Universidade de São Paulo (USP)
Carlos E. Cugnasca: Department of Computer Engineering and Digital Systems, Escola Politécnica da Universidade de São Paulo (USP)

A chapter in Information and Communication Technologies for Agriculture—Theme II: Data, 2022, pp 235-266 from Springer

Abstract: Abstract Predicting product prices is an essential activity in agricultural value chains. It can improve decision making and revenues for all agents. This chapter explores the use of deep learning techniques for predicting soybeans price trends in Brazil. A long short-term memory neural network (LSTM) forecasts the price signal. A convolutional neural network (CNN) generates a sentiment signal based on the sentiment analysis of news headlines. A multi-layer perceptron (MLP) is also evaluated to generate the sentiment signal, and an ensemble model, composed of both signals, prices and sentiment, is implemented. The four models (LSTM, CNN, and two ensembles with different weights for each signal) are evaluated in terms of their ability to predict the daily price trend. A hyperparameter analysis is conducted for all models, using the mean squared error (MSE) as a metric. Three models obtained the best result (0.60): (i) the LSTM alone; (ii) an ensemble model composed of a simple averaging of the signals; and (iii) an ensemble model composed of 90% price and 10% sentiment. The main findings are: (i) the analysis of the impact of hyperparameters on the models; (ii) the use of dictionaries has not significantly improved the sentiment prediction; (iii) the use of more than 50% of weight in the sentiment signal leads to worse predictions; and (iv) the CNN model provided a better sentiment signal than the MLP model. The benefits and possible uses of the models are discussed. The methodology used can be implemented for other products. Future work is related to improving data sets and implementing econometric models, unsupervised learning, and deep reinforcement learning.

Keywords: Agricultural; Forecasting; Deep learning; Machine learning; Prices; Sentiments (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:spochp:978-3-030-84148-5_10

Ordering information: This item can be ordered from
http://www.springer.com/9783030841485

DOI: 10.1007/978-3-030-84148-5_10

Access Statistics for this chapter

More chapters in Springer Optimization and Its Applications from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().