| Autor: |
Caiyu Jiang, Jianhua Wang |
| Jazyk: |
angličtina |
| Rok vydání: |
2022 |
| Předmět: |
|
| Zdroj: |
Mathematics, Vol 11, Iss 1, p 19 (2022) |
| Druh dokumentu: |
article |
| ISSN: |
2227-7390 |
| DOI: |
10.3390/math11010019 |
| Popis: |
It was shown that deep reinforcement learning (DRL) has the potential to solve portfolio management problems in recent years. The Twin Delayed Deep Deterministic policy gradient algorithm (TD3) is an actor-critic method, a typical DRL method in continuous action space. Despite the success of DRL in financial trading, surprisingly, most of the literature ignores the element of risk control. The research is proposed to combine long- and short-term risk (LSTR) control with the TD3 algorithm to build a portfolio model with risk management capabilities. Using Chinese stock data from the Shanghai Stock Exchange, we train and validate the proposed portfolio model. Performances were compared to the TD3 model without risk control. The results indicated that our proposal offers better risk control and investment returns. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
|
Nepřihlášeným uživatelům se plný text nezobrazuje |
K zobrazení výsledku je třeba se přihlásit.
|
