Emmanuel Lwele, Sabuni Emmanuel, Sitali Gabriel Sitali
arXiv 14 Nov 2025 · Finance — Portfolio Management
arXiv:2511.11481 · PDF · DOI · OpenAlex · Extracted main text
This paper presents a deep reinforcement learning (DRL) framework for dynamic portfolio optimization under market uncertainty and risk. The proposed model integrates a Sharpe ratio-based reward function with direct risk control mechanisms, including maximum drawdown and volatility constraints. Proximal Policy Optimization (PPO) is employed to learn adaptive asset allocation strategies over historical financial time series. Model performance is benchmarked against mean-variance and equal-weight portfolio strategies using backtesting on high-performing equities. Results indicate that the DRL agent stabilizes volatility successfully but suffers from degraded risk-adjusted returns due to over-conservative policy convergence, highlighting the challenge of balancing exploration, return maximization, and risk mitigation. The study underscores the need for improved reward shaping and hybrid risk-aware strategies to enhance the practical deployment of DRL-based portfolio allocation models.
appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | Zuzana Janková (2021) A Bibliometric Analysis of Artificial Intelligence Technique in Financial Market | 0.644 | 2 | 2 | 100% |
| 2 | Zhong, Xiao and Enke, David (2019) Predicting the daily return direction of the stock market using hybrid machine learning algorithms | 0.644 | 2 | 2 | 100% |
| 3 | Lim, Shiau Hong and Malik, Ilyas (2022) Distributional reinforcement learning for risk-sensitive policies | 0.405 | 1 | 1 | 100% |
| 4 | Harnpadungkij, Thammasorn and Chaisangmongkon, Warasinee and Phuncho… (2019) Risk-Sensitive Portfolio Management by using Distributional Reinforcement Learning | 0.405 | 1 | 1 | 100% |
| 5 | Basak, Suryoday and Kar, Saibal and Saha, Snehanshu and Khaidem, Luc… (2019) Predicting the direction of stock market prices using tree-based classifiers | 0.405 | 1 | 1 | 100% |
| 6 | Ghasemzadeha, Mohammad and Mohammad-Karimi, Naeimeh and Ansari-Saman… (2020) Machine learning algorithms for time series in financial markets | 0.405 | 1 | 1 | 100% |
| 7 | Kilimci, Zeynep Hilal and Duvar, Ramazan (2020) An efficient word embedding and deep learning based model to forecast the direction of stock exchange market using Twitter and f… | 0.405 | 1 | 1 | 100% |
| 8 | Molina, Gabriel (2016) Stock trading with recurrent reinforcement learning (RRL) | 0.405 | 1 | 1 | 100% |
| 9 | Moody, John and Wu, Lizhong and Liao, Yuansong and Saffell, Matthew (1998) Performance functions and reinforcement learning for trading systems and portfolios | 0.405 | 1 | 1 | 100% |
| 10 | Reddy, V Kranthi Sai and Sai, Kranthi (2018) Stock market prediction using machine learning | 0.405 | 1 | 1 | 100% |
Showing the top 10 of 10 scored citations.