.png){kind=icon}
.png){kind=icon}
Return
Portfolio optimization using deep learning with risk aversion utility function
.png){kind=icon}
PRE
AI
DOI：10.1016/j.frl.2025.106761.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper explores portfolio optimization with deep learning (DL), which can model non-linear returns that traditional methods cannot capture. While Sharpe loss addresses the risk-return trade-off in DL-based portfolio construction, it has limitations, including interpretability issues with negative PnL and biased gradients under stochastic gradient descent (SGD). We propose a new loss function based on a risk-averse utility function, which provides unbiased gradients and clear interpretation even with negative PnL. Additionally, we use DL outputs as adjustments to baseline weights, achieving improved portfolio performance. Experiments on S&P 500 data show that our method outperforms Sharpe loss-based models across several metrics, including the Sharpe ratio.
Keywords:
Portfolio optimization
Deep learning
Risk-averse utility
Sharpe loss
Journal
IF:
6.9
Papers:
9.0K
Citations:
2.8W
Organization
No organization information available