WU junfeng’s research while affiliated with Nanjing University of Information Science and Technology and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (4)


Portfolio management based on a reinforcement learning framework
  • Article

May 2024

·

34 Reads

·

2 Citations

Journal of Forecasting

Wu Junfeng

·

Li Yaoming

·

Tan Wenqing

·

Chen Yun

Portfolio management is crucial for investors. We propose a dynamic portfolio management framework based on reinforcement learning using the proximal policy optimization algorithm. The two‐part framework includes a feature extraction network and a full connected network. First, the majority of the previous research on portfolio management based on reinforcement learning has been dedicated to discrete action spaces. We propose a potential solution to the problem of a continuous action space with a constraint (i.e., the sum of the portfolio weights is equal to 1). Second, we explore different feature extraction networks (i.e., convolutional neural network [CNN], long short‐term memory [LSTM] network, and convolutional LSTM network) combined with our system, and we conduct extensive experiments on the six kinds of assets, including 16 features. The empirical results show that the CNN performs best in the test set. Last, we discuss the effect of the trading frequency on our trading system and find that the monthly trading frequency has a higher Sharpe ratio in the test set than other trading frequencies.



Analysis of Risk Correlations among Stock Markets during the COVID-19 Pandemic

June 2022

·

32 Reads

·

27 Citations

International Review of Financial Analysis

The outbreak of the COVID-19 pandemic significantly negatively impacted the global economy and stock markets. This paper investigates the stock-market tail risks caused by the COVID-19 pandemic and how the pandemic affects the risk correlations among the stock markets worldwide. The conditional autoregressive value at risk (CAViaR) model is used to measure the tail risks of 28 selected stock markets. Furthermore, risk correlation networks are constructed to describe the risk correlations among stock markets during different periods. Through dynamic analysis of the risk correlations, the influence of the COVID-19 pandemic on stock markets worldwide is examined quantitatively. The results show the following: (i) The COVID-19 pandemic has caused significant tail risks in stock markets in most countries, while the stock markets of a few countries have been unaffected by the pandemic. (ii) The topology of risk correlation networks has become denser during the COVID-19 pandemic. The impact of the COVID-19 pandemic makes it easier for risk to transfer among stock markets. (iii) The increase in the closeness of the risk relationship between countries with lower economic correlation has become much higher than that between counties with higher economic correlation during the COVID-19 pandemic. For researchers and policy-makers, these findings reveal practical implications of the risk correlations among stock markets.


Risk Transfer between Stock and Open-Ended Equity Fund Markets in China Based on a Multi-layer Network Model

November 2020

·

69 Reads

·

5 Citations

Physica A Statistical Mechanics and its Applications

Due to the holding relationship between open-ended equity funds (OEFs) and stocks, risks can spread between stock and OEF markets directly. To develop an effective response strategy for this risk transfer, this paper constructs an interdependent stock-fund network to describe the relationship between the two markets and proposes a risk transfer model to investigate the risk transfer process between them. This model is applied to stock and OEF markets in China. Through a sensitivity analysis of three variables including the initial impact level of risk, the OEF liquidation line, and the stock discount rate, the changes in the OEF liquidation rate and the stock index under different conditions are analysed quantitatively. The results show the following: (1) The OEF liquidation rate and stock index have obvious percolation processes with the changes in the three parameters; (2) Risks are transferred between the two markets more rapidly when the parameters are larger than their thresholds; and (3) Affected by the size of the OEFs and the market value of the stocks, the initial impact level of risk and the OEF liquidation line have more significant impacts on the two markets than the stock discount rate. The proposed models can assist the decision makers in better understanding the risk transfer process between stock and OEF markets and to select effective strategies to respond to different risks.

Citations (2)


... Research has applied the standard fixed-effects regression approach [19][20][21][22][23][24][25]37,38] or the event methodology [39][40][41][42][43][44] to better capture the effects of COVID-19 on stock market performance and responsiveness. The emergence of COVID-19, and government interventions either to control the spread of the virus or regenerate growth have been found to affect trading volumes, stock returns, and financial market volatility across major stock markets [19][20][21][22][23][24][25]37,38,45] and financial contagion due to market integration [42,[46][47][48][49][50]. ...

Reference:

Evaluating the responsiveness of Caribbean stock markets – The case of COVID-19
Analysis of Risk Correlations among Stock Markets during the COVID-19 Pandemic
  • Citing Article
  • June 2022

International Review of Financial Analysis

... Secondly, we use a simulation approach to modeling the downward spiral phenomenon. We extend the framework of [19] by incorporating two important factors into the model: the flow-performance relationship of mutual funds and the price impact on the stocks due to the illiquidity problem. Finally, we quantify the systemic risk (including both direct and indirect risk) with the relative systemic loss of market capitalizations induced by each financial stock and rank the stocks based on their contributions to systemic risks. ...

Risk Transfer between Stock and Open-Ended Equity Fund Markets in China Based on a Multi-layer Network Model
  • Citing Article
  • November 2020

Physica A Statistical Mechanics and its Applications