Implementation of a Commitment Machine for an Adaptive and Robust Expected Shortfall Estimation
This study proposes a metaheuristic for the selection of models among different Expected Shortfall (ES) estimation methods. The proposed approach, denominated “Commitment Machine” (CM), has a strong focus on assets cross-correlation and allows to measure adaptively the ES, dynamically evaluating whi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-08-01
|
| Series: | Frontiers in Artificial Intelligence |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2021.732805/full |
| _version_ | 1818609881039503360 |
|---|---|
| author | Marco Bagnato Anna Bottasso Pier Giuseppe Giribone Pier Giuseppe Giribone |
| author_facet | Marco Bagnato Anna Bottasso Pier Giuseppe Giribone Pier Giuseppe Giribone |
| author_sort | Marco Bagnato |
| collection | DOAJ |
| description | This study proposes a metaheuristic for the selection of models among different Expected Shortfall (ES) estimation methods. The proposed approach, denominated “Commitment Machine” (CM), has a strong focus on assets cross-correlation and allows to measure adaptively the ES, dynamically evaluating which is the most performing method through the minimization of a loss function. The CM algorithm compares four different ES estimation techniques which all take into account the interaction effects among assets: a Bayesian Vector autoregressive model, Stochastic Differential Equation (SDE) numerical schemes with Exponential Weighted Moving Average (EWMA), a Generalized AutoRegressive Conditional Heteroskedasticity (GARCH) volatility model and a hybrid method that integrates Dynamic Recurrent Neural Networks together with a Monte Carlo approach. The integration of traditional Monte Carlo approaches with Machine Learning technologies and the heterogeneity of dynamically selected methodologies lead to an improved estimation of the ES. The study describes the techniques adopted by the CM and the logic behind model selection; moreover, it provides a market application case of the proposed metaheuristic, by simulating an equally weighted multi-asset portfolio. |
| first_indexed | 2024-12-16T15:05:35Z |
| format | Article |
| id | doaj.art-8ca383e7b1eb4c2caa70e820cc4ff77a |
| institution | Directory Open Access Journal |
| issn | 2624-8212 |
| language | English |
| last_indexed | 2024-12-16T15:05:35Z |
| publishDate | 2021-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Artificial Intelligence |
| spelling | doaj.art-8ca383e7b1eb4c2caa70e820cc4ff77a2022-12-21T22:27:09ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122021-08-01410.3389/frai.2021.732805732805Implementation of a Commitment Machine for an Adaptive and Robust Expected Shortfall EstimationMarco Bagnato0Anna Bottasso1Pier Giuseppe Giribone2Pier Giuseppe Giribone3Data and AI, SoftJam, Genoa, ItalyDepartment of Economics, University of Genoa, Genoa, ItalyDepartment of Economics, University of Genoa, Genoa, ItalyFinancial Engineering and Data Mining, Banca CARIGE, Genoa, ItalyThis study proposes a metaheuristic for the selection of models among different Expected Shortfall (ES) estimation methods. The proposed approach, denominated “Commitment Machine” (CM), has a strong focus on assets cross-correlation and allows to measure adaptively the ES, dynamically evaluating which is the most performing method through the minimization of a loss function. The CM algorithm compares four different ES estimation techniques which all take into account the interaction effects among assets: a Bayesian Vector autoregressive model, Stochastic Differential Equation (SDE) numerical schemes with Exponential Weighted Moving Average (EWMA), a Generalized AutoRegressive Conditional Heteroskedasticity (GARCH) volatility model and a hybrid method that integrates Dynamic Recurrent Neural Networks together with a Monte Carlo approach. The integration of traditional Monte Carlo approaches with Machine Learning technologies and the heterogeneity of dynamically selected methodologies lead to an improved estimation of the ES. The study describes the techniques adopted by the CM and the logic behind model selection; moreover, it provides a market application case of the proposed metaheuristic, by simulating an equally weighted multi-asset portfolio.https://www.frontiersin.org/articles/10.3389/frai.2021.732805/fullexpected shortfallmonte carlo methodsstochastic differential equationbayesian vector autoregressivedynamic neural networksnonlinear auto-regressive networks |
| spellingShingle | Marco Bagnato Anna Bottasso Pier Giuseppe Giribone Pier Giuseppe Giribone Implementation of a Commitment Machine for an Adaptive and Robust Expected Shortfall Estimation Frontiers in Artificial Intelligence expected shortfall monte carlo methods stochastic differential equation bayesian vector autoregressive dynamic neural networks nonlinear auto-regressive networks |
| title | Implementation of a Commitment Machine for an Adaptive and Robust Expected Shortfall Estimation |
| title_full | Implementation of a Commitment Machine for an Adaptive and Robust Expected Shortfall Estimation |
| title_fullStr | Implementation of a Commitment Machine for an Adaptive and Robust Expected Shortfall Estimation |
| title_full_unstemmed | Implementation of a Commitment Machine for an Adaptive and Robust Expected Shortfall Estimation |
| title_short | Implementation of a Commitment Machine for an Adaptive and Robust Expected Shortfall Estimation |
| title_sort | implementation of a commitment machine for an adaptive and robust expected shortfall estimation |
| topic | expected shortfall monte carlo methods stochastic differential equation bayesian vector autoregressive dynamic neural networks nonlinear auto-regressive networks |
| url | https://www.frontiersin.org/articles/10.3389/frai.2021.732805/full |
| work_keys_str_mv | AT marcobagnato implementationofacommitmentmachineforanadaptiveandrobustexpectedshortfallestimation AT annabottasso implementationofacommitmentmachineforanadaptiveandrobustexpectedshortfallestimation AT piergiuseppegiribone implementationofacommitmentmachineforanadaptiveandrobustexpectedshortfallestimation AT piergiuseppegiribone implementationofacommitmentmachineforanadaptiveandrobustexpectedshortfallestimation |