Analysis of Lumber Prices Time Series Using Long Short-Term Memory Artificial Neural Networks

Dercilio Junior Verly Lopes,Amanda Peres Vieira Bedette,Gabrielly Dos Santos Bobadilha

doi:10.3390/f12040428

Dercilio Junior Verly Lopes, Amanda Peres Vieira Bedette + Show 1 more

Open Access

https://doi.org/10.3390/f12040428

Copy DOI

Journal: Forests	Publication Date: Apr 2, 2021
Citations: 9	License type: CC BY 4.0

Affiliation: Mississippi State University

Abstract

This manuscript confirms the feasibility of using a long short-term memory (LSTM) recurrent neural network (RNN) to forecast lumber stock prices during the great and Coronavirus disease 2019 (COVID-19) pandemic recessions in the USA. The database was composed of 5012 data entries divided into recession periods. We applied a timeseries cross-validation that divided the dataset into an 80:20 training/validation ratio. The network contained five LSTM layers with 50 units each followed by a dense output layer. We evaluated the performance of the network via mean squared error (MSE), root mean squared error (RMSE), and mean absolute error (MAE) for 30, 60, and 120 timesteps and the recession periods. The metrics results indicated that the network was able to capture the trend for both recession periods with a remarkably low degree of error. Timeseries forecasting may help the forest and forest product industries to manage their inventory, transportation costs, and response readiness to critical economic events.

Highlights

Memory Artificial Neural Networks.The United States forest products industry was hit hard during the Coronavirus disease 2019 (COVID-19) pandemic due to decreases in construction demand, mainly in the states that deemed construction to be non-essential [1]
We first analyzed the feasibility of using long short-term memory artificial recurrent neural networks to predict Random Length lumber stock prices during the great recession period (2007–2009) and COVID-19 pandemic recession period (2020–)
We first analyzed the feasibility of using long short-term memory artificial recurrent neural networks to predict Random Length lumber stock prices during the great recession neural networks to predict Random Length lumber stock prices during the great recession period (2007–2009) and COVID-19 pandemic recession period (2020–)

Summary

Introduction

The United States forest products industry was hit hard during the Coronavirus disease 2019 (COVID-19) pandemic due to decreases in construction demand, mainly in the states that deemed construction to be non-essential [1]. With the economic downturn, many forest products industries had to stop their operations or even close their business. With the issued shelter-in place orders across the United States, there was an unprecedented consumption of lumber. Individual homeowners were more active in building, repairing, and upgrading household spaces. Lumber price in the stock market reached a record high in the month of August 2020 due to low supply and high demand [2]

Methods

Results

Conclusion