<em>l</em><sub>1</sub>-Regularization in Portfolio Selection with Machine Learning
In this work, we investigate the application of Deep Learning in Portfolio selection in a Markowitz mean-variance framework. We refer to a <inline-formula><math display="inline"><semantics><msub><mi>l</mi><mn>1</mn></msub></semantics...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/4/540 |
| _version_ | 1797478344102510592 |
|---|---|
| author | Stefania Corsaro Valentina De Simone Zelda Marino Salvatore Scognamiglio |
| author_facet | Stefania Corsaro Valentina De Simone Zelda Marino Salvatore Scognamiglio |
| author_sort | Stefania Corsaro |
| collection | DOAJ |
| description | In this work, we investigate the application of Deep Learning in Portfolio selection in a Markowitz mean-variance framework. We refer to a <inline-formula><math display="inline"><semantics><msub><mi>l</mi><mn>1</mn></msub></semantics></math></inline-formula> regularized multi-period model; the choice of the <inline-formula><math display="inline"><semantics><msub><mi>l</mi><mn>1</mn></msub></semantics></math></inline-formula> norm aims at producing sparse solutions. A crucial issue is the choice of the regularization parameter, which must realize a trade-off between fidelity to data and regularization. We propose an algorithm based on neural networks for the automatic selection of the regularization parameter. Once the neural network training is completed, an estimate of the regularization parameter can be computed via forward propagation. Numerical experiments and comparisons performed on real data validate the approach. |
| first_indexed | 2024-03-09T21:30:35Z |
| format | Article |
| id | doaj.art-81cdb2fe93db49fda8603821bbfeff8e |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T21:30:35Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-81cdb2fe93db49fda8603821bbfeff8e2023-11-23T20:56:19ZengMDPI AGMathematics2227-73902022-02-0110454010.3390/math10040540<em>l</em><sub>1</sub>-Regularization in Portfolio Selection with Machine LearningStefania Corsaro0Valentina De Simone1Zelda Marino2Salvatore Scognamiglio3Department of Management and Quantitative Studies, Parthenope University of Naples, 80133 Naples, ItalyDepartment of Mathematics and Physics, University of Campania “Luigi Vanvitelli”, 81100 Caserta, ItalyDepartment of Management and Quantitative Studies, Parthenope University of Naples, 80133 Naples, ItalyDepartment of Management and Quantitative Studies, Parthenope University of Naples, 80133 Naples, ItalyIn this work, we investigate the application of Deep Learning in Portfolio selection in a Markowitz mean-variance framework. We refer to a <inline-formula><math display="inline"><semantics><msub><mi>l</mi><mn>1</mn></msub></semantics></math></inline-formula> regularized multi-period model; the choice of the <inline-formula><math display="inline"><semantics><msub><mi>l</mi><mn>1</mn></msub></semantics></math></inline-formula> norm aims at producing sparse solutions. A crucial issue is the choice of the regularization parameter, which must realize a trade-off between fidelity to data and regularization. We propose an algorithm based on neural networks for the automatic selection of the regularization parameter. Once the neural network training is completed, an estimate of the regularization parameter can be computed via forward propagation. Numerical experiments and comparisons performed on real data validate the approach.https://www.mdpi.com/2227-7390/10/4/540deep learningmulti-period portfolio optimization<i>l</i><sub>1</sub>-normsplit Bregman |
| spellingShingle | Stefania Corsaro Valentina De Simone Zelda Marino Salvatore Scognamiglio <em>l</em><sub>1</sub>-Regularization in Portfolio Selection with Machine Learning Mathematics deep learning multi-period portfolio optimization <i>l</i><sub>1</sub>-norm split Bregman |
| title | <em>l</em><sub>1</sub>-Regularization in Portfolio Selection with Machine Learning |
| title_full | <em>l</em><sub>1</sub>-Regularization in Portfolio Selection with Machine Learning |
| title_fullStr | <em>l</em><sub>1</sub>-Regularization in Portfolio Selection with Machine Learning |
| title_full_unstemmed | <em>l</em><sub>1</sub>-Regularization in Portfolio Selection with Machine Learning |
| title_short | <em>l</em><sub>1</sub>-Regularization in Portfolio Selection with Machine Learning |
| title_sort | em l em sub 1 sub regularization in portfolio selection with machine learning |
| topic | deep learning multi-period portfolio optimization <i>l</i><sub>1</sub>-norm split Bregman |
| url | https://www.mdpi.com/2227-7390/10/4/540 |
| work_keys_str_mv | AT stefaniacorsaro emlemsub1subregularizationinportfolioselectionwithmachinelearning AT valentinadesimone emlemsub1subregularizationinportfolioselectionwithmachinelearning AT zeldamarino emlemsub1subregularizationinportfolioselectionwithmachinelearning AT salvatorescognamiglio emlemsub1subregularizationinportfolioselectionwithmachinelearning |