Forecasting Brazilian Ethanol Spot Prices Using LSTM
Ethanol is one of the most used fuels in Brazil, which is the second-largest producer of this biofuel in the world. The uncertainty of price direction in the future increases the risk for agents operating in this market and can affect a dependent price chain, such as food and gasoline. This paper us...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/14/23/7987 |
| _version_ | 1797507868027518976 |
|---|---|
| author | Gustavo Carvalho Santos Flavio Barboza Antônio Cláudio Paschoarelli Veiga Mateus Ferreira Silva |
| author_facet | Gustavo Carvalho Santos Flavio Barboza Antônio Cláudio Paschoarelli Veiga Mateus Ferreira Silva |
| author_sort | Gustavo Carvalho Santos |
| collection | DOAJ |
| description | Ethanol is one of the most used fuels in Brazil, which is the second-largest producer of this biofuel in the world. The uncertainty of price direction in the future increases the risk for agents operating in this market and can affect a dependent price chain, such as food and gasoline. This paper uses the architecture of recurrent neural networks—Long short-term memory (LSTM)—to predict Brazilian ethanol spot prices for three horizon-times (12, 6 and 3 months ahead). The proposed model is compared to three benchmark algorithms: Random Forest, SVM Linear and RBF. We evaluate statistical measures such as MSE (Mean Squared Error), MAPE (Mean Absolute Percentage Error), and accuracy to assess the algorithm robustness. Our findings suggest LSTM outperforms the other techniques in regression, considering both MSE and MAPE but SVM Linear is better to identify price trends. Concerning predictions per se, all errors increase during the pandemic period, reinforcing the challenge to identify patterns in crisis scenarios. |
| first_indexed | 2024-03-10T04:54:33Z |
| format | Article |
| id | doaj.art-a4c6057b8bb2459db3235f0adb06c8d2 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T04:54:33Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-a4c6057b8bb2459db3235f0adb06c8d22023-11-23T02:20:56ZengMDPI AGEnergies1996-10732021-11-011423798710.3390/en14237987Forecasting Brazilian Ethanol Spot Prices Using LSTMGustavo Carvalho Santos0Flavio Barboza1Antônio Cláudio Paschoarelli Veiga2Mateus Ferreira Silva3Electrical Engineering School, Federal University of Uberlândia, Uberlândia 38408-100, BrazilSchool of Business and Management, Federal University of Uberlândia, Uberlândia 38408-100, BrazilElectrical Engineering School, Federal University of Uberlândia, Uberlândia 38408-100, BrazilSchool of Accounting, Federal University of Uberlândia, Uberlândia 38408-100, BrazilEthanol is one of the most used fuels in Brazil, which is the second-largest producer of this biofuel in the world. The uncertainty of price direction in the future increases the risk for agents operating in this market and can affect a dependent price chain, such as food and gasoline. This paper uses the architecture of recurrent neural networks—Long short-term memory (LSTM)—to predict Brazilian ethanol spot prices for three horizon-times (12, 6 and 3 months ahead). The proposed model is compared to three benchmark algorithms: Random Forest, SVM Linear and RBF. We evaluate statistical measures such as MSE (Mean Squared Error), MAPE (Mean Absolute Percentage Error), and accuracy to assess the algorithm robustness. Our findings suggest LSTM outperforms the other techniques in regression, considering both MSE and MAPE but SVM Linear is better to identify price trends. Concerning predictions per se, all errors increase during the pandemic period, reinforcing the challenge to identify patterns in crisis scenarios.https://www.mdpi.com/1996-1073/14/23/7987price predictiontrend predictionLSTMSVMRandom ForestMAPE |
| spellingShingle | Gustavo Carvalho Santos Flavio Barboza Antônio Cláudio Paschoarelli Veiga Mateus Ferreira Silva Forecasting Brazilian Ethanol Spot Prices Using LSTM Energies price prediction trend prediction LSTM SVM Random Forest MAPE |
| title | Forecasting Brazilian Ethanol Spot Prices Using LSTM |
| title_full | Forecasting Brazilian Ethanol Spot Prices Using LSTM |
| title_fullStr | Forecasting Brazilian Ethanol Spot Prices Using LSTM |
| title_full_unstemmed | Forecasting Brazilian Ethanol Spot Prices Using LSTM |
| title_short | Forecasting Brazilian Ethanol Spot Prices Using LSTM |
| title_sort | forecasting brazilian ethanol spot prices using lstm |
| topic | price prediction trend prediction LSTM SVM Random Forest MAPE |
| url | https://www.mdpi.com/1996-1073/14/23/7987 |
| work_keys_str_mv | AT gustavocarvalhosantos forecastingbrazilianethanolspotpricesusinglstm AT flaviobarboza forecastingbrazilianethanolspotpricesusinglstm AT antonioclaudiopaschoarelliveiga forecastingbrazilianethanolspotpricesusinglstm AT mateusferreirasilva forecastingbrazilianethanolspotpricesusinglstm |