TY - GEN
T1 - Value at Risk Estimation with Hybrid-SVR-GARCH-KDE Model for LQ45 Portfolio Optimization
AU - Wara, Shindi Shella May
AU - Prastyo, Dedy Dwi
AU - Kuswanto, Heri
N1 - Publisher Copyright:
© 2023 American Institute of Physics Inc.. All rights reserved.
PY - 2023/1/27
Y1 - 2023/1/27
N2 - Stock is a financial instrument that has a high variation. One way to determine the risk of a stock is to estimate the Value at Risk. However, Value at Risk cases tend to have fluctuating variations over time and are difficult to model because they are hypothesized to be non-linear. To capture this, modeling is carried out with Generalized Autoregressive Conditional Heteroscedasticity (GARCH). Meanwhile, identification of non-linear models can be solved using machine learning methods, one of which is Support Vector Regression (SVR) which is sensitive to over fitting cases. To produce an optimal model, reinforced with Kernel Density Estimation (KDE). By using this combination, the hybrid SVR-GARCH-KDE method is obtained. The results of this method can show that the Hybrid-SVR-GARCH-KDE method is good for estimating the Value at Risk on return of LQ45 stock price data for the period January 2018 to March 2021 which has the smallest PEB and PBV. From this method, portfolio optimization was carried out and resulted in a decision that investments in the Trade, Services, and Investment sectors as well as mining were profitable for investors.
AB - Stock is a financial instrument that has a high variation. One way to determine the risk of a stock is to estimate the Value at Risk. However, Value at Risk cases tend to have fluctuating variations over time and are difficult to model because they are hypothesized to be non-linear. To capture this, modeling is carried out with Generalized Autoregressive Conditional Heteroscedasticity (GARCH). Meanwhile, identification of non-linear models can be solved using machine learning methods, one of which is Support Vector Regression (SVR) which is sensitive to over fitting cases. To produce an optimal model, reinforced with Kernel Density Estimation (KDE). By using this combination, the hybrid SVR-GARCH-KDE method is obtained. The results of this method can show that the Hybrid-SVR-GARCH-KDE method is good for estimating the Value at Risk on return of LQ45 stock price data for the period January 2018 to March 2021 which has the smallest PEB and PBV. From this method, portfolio optimization was carried out and resulted in a decision that investments in the Trade, Services, and Investment sectors as well as mining were profitable for investors.
UR - http://www.scopus.com/inward/record.url?scp=85147303377&partnerID=8YFLogxK
U2 - 10.1063/5.0107539
DO - 10.1063/5.0107539
M3 - Conference contribution
AN - SCOPUS:85147303377
T3 - AIP Conference Proceedings
BT - 3rd International Conference on Science, Mathematics, Environment, and Education
A2 - Indriyanti, Nurma Yunita
A2 - Sari, Meida Wulan
PB - American Institute of Physics Inc.
T2 - 3rd International Conference on Science, Mathematics, Environment, and Education: Flexibility in Research and Innovation on Science, Mathematics, Environment, and Education for Sustainable Development, ICoSMEE 2021
Y2 - 27 July 2021 through 28 July 2021
ER -