Learning fused lasso parameters in portfolio selection via neural networks

被引：0

作者：

Corsaro S. ^{[1
]}

De Simone V. ^{[2
]}

Marino Z. ^{[1
]}

Scognamiglio S. ^{[1
]}

机构：

[1] Department of Management and Quantitative Studies, Parthenope University of Naples, Via Generale Parisi 13, Napoli

[2] Department of Mathematics and Physics, University of Campania “Luigi Vanvitelli”, Viale Lincoln 5, Caserta

来源：

Quality & Quantity | 2024年 / 58卷 / 5期

关键词：

Fused lasso; Long short-term memory; Neural network; Portfolio selection; Regularization parameters;

D O I：

10.1007/s11135-024-01858-1

中图分类号：

学科分类号：

摘要：

In recent years, fused lasso models are becoming popular in several fields, such as computer vision, classification and finance. In portfolio selection, they can be used to penalize active positions and portfolio turnover. Despite efficient algorithms and software for solving non-smooth optimization problems have been developed, the amount of regularization to apply is a critical issue, especially if we have to achieve a financial aim. We propose a data-driven approach for learning the regularization parameters in a fused lasso formulation of the multi-period portfolio selection problem, able to realize a given financial target. We design a neural network architecture based on recurrent networks for learning the functional dependence between the regularization parameters and the input data. In particular, the Long Short-Term Memory networks are considered for their ability to process sequential data, such as the time series of the asset returns. Numerical experiments performed on market data show the effectiveness of our approach. © The Author(s) 2024.

引用

页码：4281 / 4299

页数：18

共 32 条

[1]

Abedin M.Z., Moon M.H., Hassan M.K., Hajek P., Deep learning-based exchange rate prediction during the covid-19 pandemic, Ann. Oper. Res, pp. 1-52, (2021)

[2]

Beer J.C., Aizenstein H.J., Anderson S.J., Krafty R.T., Incorporating prior information with fused sparse group lasso: application to prediction of clinical measures from neuroimages, Biometrics, 75, 4, pp. 1299-1309, (2019)

[3]

Bruni R., Cesarone F., Scozzari A., Tardella F., Real-world datasets for portfolio selection and solutions of some stochastic dominance portfolio models, Data in Brief, pp. 185-209, (2016)

[4]

Chen Z., Consigli G., Liu J., Li G., Fu T., Hu Q., Multi-period risk measures and optimal investment policies, Optimal Financial Decision Making Under Uncertainty, pp. 1-34, (2017)

[5]

Corsaro S., De Simone V., Adaptive l<sub>1</sub>-regularization for short-selling control in portfolio selection, Comput. Optim. Appl, 72, pp. 457-478, (2019)

[6]

Corsaro S., De Simone V., Marino Z., Perla F., L<sub>1</sub>-regularization for multi-period portfolio selection, Ann. Oper. Res, 294, pp. 75-86, (2020)

[7]

Corsaro S., De Simone V., Marino Z., Fused lasso approach in portfolio selection, Ann. Oper. Res, 299, pp. 47-59, (2021)

[8]

Corsaro S., De Simone V., Marino Z., Split Bregman iteration for multi-period mean variance portfolio optimization, Appl. Math. Comput, 392, (2021)

[9]

Corsaro S., De Simone V., Marino Z., Scognamiglio S., l1-regularization in portfolio selection with machine learning, Mathematics, 10, (2022)

[10]

De Haas R., Van Horen N., International shock transmission after the lehman brothers collapse: Evidence from syndicated lending, Am. Econ. Rev, 102, 3, pp. 231-237, (2012)

← 1 2 3 4 →