.png){kind=icon}
.png){kind=icon}
Return
Multitrend Conditional Value at Risk for Portfolio Optimization
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2022.3183891.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Trend representation has been attracting more and more attention recently in portfolio optimization (PO) via machine learning methods. It adopts concepts and phenomena from the field of empirical and behavioral finance when little prior knowledge is obtained or strict statistical assumptions cannot be guaranteed. It is used mostly in estimating the expected asset returns, but hardly in measuring risk. To fill this gap, we propose a novel multitrend conditional value at risk (MT-CVaR), which embeds multiple trends and their influences in CVaR. Besides, we propose a novel PO model with this MT-CVaR as the risk metric and then design a solving algorithm based on the interior point method to compute the portfolio. Extensive experiments on six benchmark datasets from diverse financial markets with different frequencies show that MT-CVaR achieves the state-of-the-art investing performance and risk management.
Keywords:
Market research
Portfolios
Optimization
Reactive power
Estimation
Task analysis
Information science
Conditional value at risk (CVaR)
interior point method
multiple trends
portfolio optimization (PO)
Journal
IF:
8.9
Papers:
7.5K
Citations:
7.2W