Analysis of Lumber Prices Time Series Using Long Short-Term Memory Artificial Neural Networks
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 recess...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Forests |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4907/12/4/428 |
| _version_ | 1797539072233701376 |
|---|---|
| author | Dercilio Junior Verly Lopes Gabrielly dos Santos Bobadilha Amanda Peres Vieira Bedette |
| author_facet | Dercilio Junior Verly Lopes Gabrielly dos Santos Bobadilha Amanda Peres Vieira Bedette |
| author_sort | Dercilio Junior Verly Lopes |
| collection | DOAJ |
| description | 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 (<i>MSE</i>), root mean squared error (<i>RMSE</i>), and mean absolute error (<i>MAE</i>) 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. |
| first_indexed | 2024-03-10T12:40:10Z |
| format | Article |
| id | doaj.art-faa3a54e27604775ad4ca9e15fba7573 |
| institution | Directory Open Access Journal |
| issn | 1999-4907 |
| language | English |
| last_indexed | 2024-03-10T12:40:10Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forests |
| spelling | doaj.art-faa3a54e27604775ad4ca9e15fba75732023-11-21T13:58:20ZengMDPI AGForests1999-49072021-04-0112442810.3390/f12040428Analysis of Lumber Prices Time Series Using Long Short-Term Memory Artificial Neural NetworksDercilio Junior Verly Lopes0Gabrielly dos Santos Bobadilha1Amanda Peres Vieira Bedette2Department of Sustainable Bioproducts/Forest and Wildlife Research Center (FWRC), College of Forest Resources (CFR), Mississippi State University, Mississippi State, MS 39762, USADepartment of Sustainable Bioproducts/Forest and Wildlife Research Center (FWRC), College of Forest Resources (CFR), Mississippi State University, Mississippi State, MS 39762, USADepartment of Sustainable Bioproducts/Forest and Wildlife Research Center (FWRC), College of Forest Resources (CFR), Mississippi State University, Mississippi State, MS 39762, USAThis 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 (<i>MSE</i>), root mean squared error (<i>RMSE</i>), and mean absolute error (<i>MAE</i>) 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.https://www.mdpi.com/1999-4907/12/4/428machine-learningneural networksrandom lengthstock pricesforecastingLSTM |
| spellingShingle | Dercilio Junior Verly Lopes Gabrielly dos Santos Bobadilha Amanda Peres Vieira Bedette Analysis of Lumber Prices Time Series Using Long Short-Term Memory Artificial Neural Networks Forests machine-learning neural networks random length stock prices forecasting LSTM |
| title | Analysis of Lumber Prices Time Series Using Long Short-Term Memory Artificial Neural Networks |
| title_full | Analysis of Lumber Prices Time Series Using Long Short-Term Memory Artificial Neural Networks |
| title_fullStr | Analysis of Lumber Prices Time Series Using Long Short-Term Memory Artificial Neural Networks |
| title_full_unstemmed | Analysis of Lumber Prices Time Series Using Long Short-Term Memory Artificial Neural Networks |
| title_short | Analysis of Lumber Prices Time Series Using Long Short-Term Memory Artificial Neural Networks |
| title_sort | analysis of lumber prices time series using long short term memory artificial neural networks |
| topic | machine-learning neural networks random length stock prices forecasting LSTM |
| url | https://www.mdpi.com/1999-4907/12/4/428 |
| work_keys_str_mv | AT derciliojuniorverlylopes analysisoflumberpricestimeseriesusinglongshorttermmemoryartificialneuralnetworks AT gabriellydossantosbobadilha analysisoflumberpricestimeseriesusinglongshorttermmemoryartificialneuralnetworks AT amandaperesvieirabedette analysisoflumberpricestimeseriesusinglongshorttermmemoryartificialneuralnetworks |