Uyen Pham
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Uyen Pham has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Vladik Kreinovich
Department of Computer Science, University of Texas at El Paso, 500 W. University, El Paso, TX 79968, USA
4 shared publications - Hien D. Nguyen
University of Information Technology
2 shared publications - Hoa Le
Daiichi Sankyo, Inc, Basking Ridge, USA
2 shared publications - Sang Vu
University of Information Technology
2 shared publications Thien Dinh Nguyen
University of Economics and Law, VNU-HCM
2 shared publications- Aaron Velasco
University of Texas at El Paso
1 shared publication
Latest Publications
- Open Access
- 29 October 2026
- Published by Springer Nature in Applied Network Science
Integrating customer behaviors and data on social networks for personalized real estate decision support
- 29 October 2026
- Published by Springer Nature in Applied Network Science
Open AccessIntegrating customer behaviors and data on social networks for personalized real estate decision support
- Open Access
- 23 October 2026
- Published by MDPI AG in Preprints.org
Non-Linear Dynamics of Herding Behavior in Frontier Equity Markets: Quantile Regression and Markov-Switching Evidence from Vietnam
Using daily data from 100 HOSE-listed stocks over January 2018–October 2026, this study examines herding behavior in the Vietnamese stock market using Quantile Regression and Markov-Switching Dynamic Regression. Negative and statistically significant coefficients on squared market returns establish persistent herding across nearly all interior dispersion quantiles. Herding is present in both rising and falling markets and across liquidity segments, while Wald tests do not support statistically significant directional or liquidity asymmetry. A two-regime model identifies stable and high-volatility states, with herding substantially stronger in the turbulent regime. Sub-period analysis shows that herding was weaker before COVID-19 and intensified through the pandemic, recovery, and post-pandemic periods. The findings contribute evidence on the non-linear and regime-dependent behavior of investors in a retail-dominated frontier market and offer implications for market surveillance, portfolio risk management, and regime-aware quantitative strategies.
- 23 October 2026
- Published by MDPI AG in Preprints.org
Open AccessNon-Linear Dynamics of Herding Behavior in Frontier Equity Markets: Quantile Regression and Markov-Switching Evidence from Vietnam
Using daily data from 100 HOSE-listed stocks over January 2018–October 2026, this study examines herding behavior in the Vietnamese stock market using Quantile Regression and Markov-Switching Dynamic Regression. Negative and statistically significant coefficients on squared market returns establish persistent herding across nearly all interior dispersion quantiles. Herding is present in both rising and falling markets and across liquidity segments, while Wald tests do not support statistically significant directional or liquidity asymmetry. A two-regime model identifies stable and high-volatility states, with herding substantially stronger in the turbulent regime. Sub-period analysis shows that herding was weaker before COVID-19 and intensified through the pandemic, recovery, and post-pandemic periods. The findings contribute evidence on the non-linear and regime-dependent behavior of investors in a retail-dominated frontier market and offer implications for market surveillance, portfolio risk management, and regime-aware quantitative strategies.
- 12 July 2025
- Published by Springer Nature
- p. 390-402
A Hybrid Knowledge-Based and Machine Learning Approach for Financial Health Prediction in Small and Medium-Sized Enterprises
- 12 July 2025
- Published by Springer Nature
- p. 390-402
A Hybrid Knowledge-Based and Machine Learning Approach for Financial Health Prediction in Small and Medium-Sized Enterprises
- 10 November 2024
- Published by Springer Nature
- p. 167-173
Local-Global Support for Earth Sciences: Economic Analysis
- 10 November 2024
- Published by Springer Nature
- p. 167-173
Local-Global Support for Earth Sciences: Economic Analysis
- 2 June 2024
- Published by Springer Nature
- p. 161-167
Why Rectified Linear Unit Is Efficient in Machine Learning: One More Explanation
- 2 June 2024
- Published by Springer Nature
- p. 161-167
Why Rectified Linear Unit Is Efficient in Machine Learning: One More Explanation
- 31 October 2023
- Published by Springer Nature
- p. 178-185
Fair Bankruptcy Solutions Under Interval Uncertainty
- 31 October 2023
- Published by Springer Nature
- p. 178-185
Fair Bankruptcy Solutions Under Interval Uncertainty
- 30 July 2022
- Published by Springer Nature
- p. 377-392
A New Approach for Estimating Probability Density Function with Fuzzy Data
- 30 July 2022
- Published by Springer Nature
- p. 377-392
A New Approach for Estimating Probability Density Function with Fuzzy Data
- 30 July 2022
- Published by Springer Nature
- p. 3-6
Why Quantiles Are a Good Description of Volatility in Economics: A Pedagogical Explanation
- 30 July 2022
- Published by Springer Nature
- p. 3-6
Why Quantiles Are a Good Description of Volatility in Economics: A Pedagogical Explanation
- 27 July 2021
- Published by Springer Nature
- p. 575-585
LASSO Regression and Its Application in Forecasting Macro Economic Indicators: A Study on Vietnam’s Exports
- 27 July 2021
- Published by Springer Nature
- p. 575-585
LASSO Regression and Its Application in Forecasting Macro Economic Indicators: A Study on Vietnam’s Exports
- 19 April 2021
- Published by Springer Nature in Soft Computing
- Vol. 25 (12) , 7877-7885
Multi-agent reinforcement learning approach for hedging portfolio problem
Developing a hedging strategy to reduce risk of losses for a given set of stocks in a portfolio is a difficult task due to cost of the hedge. In Vietnam stock market, cross-hedge is involved hedging a long position of a stock because there is no put option for the stock. In addition, only VN30 stock index futures contracts are traded on Hanoi Stock Exchange. Inspired by recently achievement of deep reinforcement learning, we explore feasibility to construct a hedging strategy automatically by leveraging cooperative multi-agent in reinforcement learning techniques without advanced domain knowledge. In this work, we use 10 popular stocks on Ho Chi Minh Stock Exchange, and VN30F1M (VN30 Index Futures contracts within one month settlement) to develop a stock market simulator (including transaction fee, tax, and settlement date of transactions) for reinforcement learning agent training. We use daily return as input data for training process. Results suggest that the agent can learn trading and hedging policy to make profit and reduce losses. Furthermore, we also find that our agent can protect portfolios and make positive profit in case market collapses systematically. In practice, this work can help Vietnam’s stock market investors to improve performance and reduce losses in trading, especially when the volatility cannot be controlled.
- 19 April 2021
- Published by Springer Nature in Soft Computing
- Vol. 25 (12) , 7877-7885
Multi-agent reinforcement learning approach for hedging portfolio problem
Developing a hedging strategy to reduce risk of losses for a given set of stocks in a portfolio is a difficult task due to cost of the hedge. In Vietnam stock market, cross-hedge is involved hedging a long position of a stock because there is no put option for the stock. In addition, only VN30 stock index futures contracts are traded on Hanoi Stock Exchange. Inspired by recently achievement of deep reinforcement learning, we explore feasibility to construct a hedging strategy automatically by leveraging cooperative multi-agent in reinforcement learning techniques without advanced domain knowledge. In this work, we use 10 popular stocks on Ho Chi Minh Stock Exchange, and VN30F1M (VN30 Index Futures contracts within one month settlement) to develop a stock market simulator (including transaction fee, tax, and settlement date of transactions) for reinforcement learning agent training. We use daily return as input data for training process. Results suggest that the agent can learn trading and hedging policy to make profit and reduce losses. Furthermore, we also find that our agent can protect portfolios and make positive profit in case market collapses systematically. In practice, this work can help Vietnam’s stock market investors to improve performance and reduce losses in trading, especially when the volatility cannot be controlled.