Brazilian Exchange Rate Forecasting in High Frequency
We investigated the predictability of the Brazilian exchange rate at High Frequency (1, 5 and 15 minutes), using local and global economic variables as predictors. In addition to the Linear Regression method, we use Machine Learning algorithms such as Ridge, Lasso, Elastic Net, Random Forest and Gradient Boosting. When considering contemporary predictors, it is possible to outperform the Random Walk at all frequencies, with local economic variables having greater predictive power than global ones. Machine Learning methods are also capable of reducing the mean squared error. When we consider only lagged predictors, it is possible to beat the Random Walk if we also consider the Brazilian Real futures as an additional predictor, for the frequency of one minute and up to two minutes ahead, confirming the importance of the Brazilian futures market in determining the spot exchange rate.
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Language: | English |
| Published: |
Inter-American Development Bank
|
| Subjects: | Exchange Rate, Interest Rate, Educational Institution, Oil Price, Economy, N76 - Latin America • Caribbean, O13 - Agriculture • Natural Resources • Energy • Environment • Other Primary Products, C22 - Time-Series Models • Dynamic Quantile Regressions • Dynamic Treatment Effect Models • Diffusion Processes, C53 - Forecasting and Prediction Methods • Simulation Methods, Q47 - Energy Forecasting, Forecasting;High Frequency;Brazil, |
| Online Access: | http://dx.doi.org/10.18235/0004488 https://publications.iadb.org/en/brazilian-exchange-rate-forecasting-high-frequency |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
dig-bid-node-32712 |
|---|---|
| record_format |
koha |
| spelling |
dig-bid-node-327122022-10-03T18:13:58ZBrazilian Exchange Rate Forecasting in High Frequency 2022-09-29T00:09:00+0000 http://dx.doi.org/10.18235/0004488 https://publications.iadb.org/en/brazilian-exchange-rate-forecasting-high-frequency Inter-American Development Bank Exchange Rate Interest Rate Educational Institution Oil Price Economy N76 - Latin America • Caribbean O13 - Agriculture • Natural Resources • Energy • Environment • Other Primary Products C22 - Time-Series Models • Dynamic Quantile Regressions • Dynamic Treatment Effect Models • Diffusion Processes C53 - Forecasting and Prediction Methods • Simulation Methods Q47 - Energy Forecasting Forecasting;High Frequency;Brazil We investigated the predictability of the Brazilian exchange rate at High Frequency (1, 5 and 15 minutes), using local and global economic variables as predictors. In addition to the Linear Regression method, we use Machine Learning algorithms such as Ridge, Lasso, Elastic Net, Random Forest and Gradient Boosting. When considering contemporary predictors, it is possible to outperform the Random Walk at all frequencies, with local economic variables having greater predictive power than global ones. Machine Learning methods are also capable of reducing the mean squared error. When we consider only lagged predictors, it is possible to beat the Random Walk if we also consider the Brazilian Real futures as an additional predictor, for the frequency of one minute and up to two minutes ahead, confirming the importance of the Brazilian futures market in determining the spot exchange rate. Inter-American Development Bank José Luiz Rossi Carlos Piccioni Marina Rossi Daniel Cajueiro IDB Publications Brazil Southern Cone en |
| institution |
BID |
| collection |
DSpace |
| country |
Estados Unidos |
| countrycode |
US |
| component |
Bibliográfico |
| access |
En linea |
| databasecode |
dig-bid |
| tag |
biblioteca |
| region |
America del Norte |
| libraryname |
Biblioteca Felipe Herrera del BID |
| language |
English |
| topic |
Exchange Rate Interest Rate Educational Institution Oil Price Economy N76 - Latin America • Caribbean O13 - Agriculture • Natural Resources • Energy • Environment • Other Primary Products C22 - Time-Series Models • Dynamic Quantile Regressions • Dynamic Treatment Effect Models • Diffusion Processes C53 - Forecasting and Prediction Methods • Simulation Methods Q47 - Energy Forecasting Forecasting;High Frequency;Brazil Exchange Rate Interest Rate Educational Institution Oil Price Economy N76 - Latin America • Caribbean O13 - Agriculture • Natural Resources • Energy • Environment • Other Primary Products C22 - Time-Series Models • Dynamic Quantile Regressions • Dynamic Treatment Effect Models • Diffusion Processes C53 - Forecasting and Prediction Methods • Simulation Methods Q47 - Energy Forecasting Forecasting;High Frequency;Brazil |
| spellingShingle |
Exchange Rate Interest Rate Educational Institution Oil Price Economy N76 - Latin America • Caribbean O13 - Agriculture • Natural Resources • Energy • Environment • Other Primary Products C22 - Time-Series Models • Dynamic Quantile Regressions • Dynamic Treatment Effect Models • Diffusion Processes C53 - Forecasting and Prediction Methods • Simulation Methods Q47 - Energy Forecasting Forecasting;High Frequency;Brazil Exchange Rate Interest Rate Educational Institution Oil Price Economy N76 - Latin America • Caribbean O13 - Agriculture • Natural Resources • Energy • Environment • Other Primary Products C22 - Time-Series Models • Dynamic Quantile Regressions • Dynamic Treatment Effect Models • Diffusion Processes C53 - Forecasting and Prediction Methods • Simulation Methods Q47 - Energy Forecasting Forecasting;High Frequency;Brazil Inter-American Development Bank Brazilian Exchange Rate Forecasting in High Frequency |
| description |
We investigated the predictability of the Brazilian exchange rate at High Frequency (1, 5 and 15 minutes), using local and global economic variables as predictors. In addition to the Linear Regression method, we use Machine Learning algorithms such as Ridge, Lasso, Elastic Net, Random Forest and Gradient Boosting. When considering contemporary predictors, it is possible to outperform the Random Walk at all frequencies, with local economic variables having greater predictive power than global ones. Machine Learning methods are also capable of reducing the mean squared error. When we consider only lagged predictors, it is possible to beat the Random Walk if we also consider the Brazilian Real futures as an additional predictor, for the frequency of one minute and up to two minutes ahead, confirming the importance of the Brazilian futures market in determining the spot exchange rate. |
| author2 |
José Luiz Rossi |
| author_facet |
José Luiz Rossi Inter-American Development Bank |
| topic_facet |
Exchange Rate Interest Rate Educational Institution Oil Price Economy N76 - Latin America • Caribbean O13 - Agriculture • Natural Resources • Energy • Environment • Other Primary Products C22 - Time-Series Models • Dynamic Quantile Regressions • Dynamic Treatment Effect Models • Diffusion Processes C53 - Forecasting and Prediction Methods • Simulation Methods Q47 - Energy Forecasting Forecasting;High Frequency;Brazil |
| author |
Inter-American Development Bank |
| author_sort |
Inter-American Development Bank |
| title |
Brazilian Exchange Rate Forecasting in High Frequency |
| title_short |
Brazilian Exchange Rate Forecasting in High Frequency |
| title_full |
Brazilian Exchange Rate Forecasting in High Frequency |
| title_fullStr |
Brazilian Exchange Rate Forecasting in High Frequency |
| title_full_unstemmed |
Brazilian Exchange Rate Forecasting in High Frequency |
| title_sort |
brazilian exchange rate forecasting in high frequency |
| publisher |
Inter-American Development Bank |
| url |
http://dx.doi.org/10.18235/0004488 https://publications.iadb.org/en/brazilian-exchange-rate-forecasting-high-frequency |
| work_keys_str_mv |
AT interamericandevelopmentbank brazilianexchangerateforecastinginhighfrequency |
| _version_ |
1809108349553213440 |