Modeling the Yield Curve of BRICS Countries: Parametric vs. Machine Learning Techniques
We compare parametric and machine learning techniques (namely: Neural Networks) for in–sample modeling of the yield curve of the BRICS countries (Brazil, Russia, India, China, South Africa). To such aim, we applied the Dynamic De Rezende–Ferreira five–factor model with time–varying decay parameters...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Risks |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9091/10/2/36 |
| _version_ | 1797476779148967936 |
|---|---|
| author | Oleksandr Castello Marina Resta |
| author_facet | Oleksandr Castello Marina Resta |
| author_sort | Oleksandr Castello |
| collection | DOAJ |
| description | We compare parametric and machine learning techniques (namely: Neural Networks) for in–sample modeling of the yield curve of the BRICS countries (Brazil, Russia, India, China, South Africa). To such aim, we applied the Dynamic De Rezende–Ferreira five–factor model with time–varying decay parameters and a Feed–Forward Neural Network to the bond market data of the BRICS countries. To enhance the flexibility of the parametric model, we also introduce a new procedure to estimate the time varying parameters that significantly improve its performance. Our contribution spans towards two directions. First, we offer a comprehensive investigation of the bond market in the BRICS countries examined both by time and maturity; working on five countries at once we also ensure that our results are not specific to a particular data–set; second we make recommendations concerning modelling and estimation choices of the yield curve. In this respect, although comparing highly flexible estimation methods, we highlight superior in–sample capabilities of the neural network in all the examined markets and then suggest that machine learning techniques can be a valid alternative to more traditional methods also in presence of marked turbulence. |
| first_indexed | 2024-03-09T21:08:33Z |
| format | Article |
| id | doaj.art-ca687c0f00854b61b9ff01f9c2989f27 |
| institution | Directory Open Access Journal |
| issn | 2227-9091 |
| language | English |
| last_indexed | 2024-03-09T21:08:33Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Risks |
| spelling | doaj.art-ca687c0f00854b61b9ff01f9c2989f272023-11-23T21:56:44ZengMDPI AGRisks2227-90912022-02-011023610.3390/risks10020036Modeling the Yield Curve of BRICS Countries: Parametric vs. Machine Learning TechniquesOleksandr Castello0Marina Resta1School of Social Sciences, Department of Economics and Business Studies, University of Genova, 16126 Genova, ItalySchool of Social Sciences, Department of Economics and Business Studies, University of Genova, 16126 Genova, ItalyWe compare parametric and machine learning techniques (namely: Neural Networks) for in–sample modeling of the yield curve of the BRICS countries (Brazil, Russia, India, China, South Africa). To such aim, we applied the Dynamic De Rezende–Ferreira five–factor model with time–varying decay parameters and a Feed–Forward Neural Network to the bond market data of the BRICS countries. To enhance the flexibility of the parametric model, we also introduce a new procedure to estimate the time varying parameters that significantly improve its performance. Our contribution spans towards two directions. First, we offer a comprehensive investigation of the bond market in the BRICS countries examined both by time and maturity; working on five countries at once we also ensure that our results are not specific to a particular data–set; second we make recommendations concerning modelling and estimation choices of the yield curve. In this respect, although comparing highly flexible estimation methods, we highlight superior in–sample capabilities of the neural network in all the examined markets and then suggest that machine learning techniques can be a valid alternative to more traditional methods also in presence of marked turbulence.https://www.mdpi.com/2227-9091/10/2/36BRICSDe Rezende–Ferreira modelArtificial Neural Network (ANN)Feed–Forward Neural Network (FFNN)emerging marketsterm structure |
| spellingShingle | Oleksandr Castello Marina Resta Modeling the Yield Curve of BRICS Countries: Parametric vs. Machine Learning Techniques Risks BRICS De Rezende–Ferreira model Artificial Neural Network (ANN) Feed–Forward Neural Network (FFNN) emerging markets term structure |
| title | Modeling the Yield Curve of BRICS Countries: Parametric vs. Machine Learning Techniques |
| title_full | Modeling the Yield Curve of BRICS Countries: Parametric vs. Machine Learning Techniques |
| title_fullStr | Modeling the Yield Curve of BRICS Countries: Parametric vs. Machine Learning Techniques |
| title_full_unstemmed | Modeling the Yield Curve of BRICS Countries: Parametric vs. Machine Learning Techniques |
| title_short | Modeling the Yield Curve of BRICS Countries: Parametric vs. Machine Learning Techniques |
| title_sort | modeling the yield curve of brics countries parametric vs machine learning techniques |
| topic | BRICS De Rezende–Ferreira model Artificial Neural Network (ANN) Feed–Forward Neural Network (FFNN) emerging markets term structure |
| url | https://www.mdpi.com/2227-9091/10/2/36 |
| work_keys_str_mv | AT oleksandrcastello modelingtheyieldcurveofbricscountriesparametricvsmachinelearningtechniques AT marinaresta modelingtheyieldcurveofbricscountriesparametricvsmachinelearningtechniques |