Bumho Son
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Bumho Son has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Jaewook Lee
Seoul National University
8 shared publications - Huisu Jang
School of Finance, Soongsil University, Seoul, Korea
4 shared publications - Hyungjin Ko
Department of Consumer Science, Sungkyunkwan University, Seoul, South Korea
4 shared publications Yunyoung Lee
4 shared publications- Seongwan Park
Department of Industrial Engineering, Seoul National University, Seoul, South Korea
2 shared publications - Woojin Jeong
Seoul National University, Seoul, Republic of Korea
2 shared publications
Latest Publications
- Open Access
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 1546-1565
Balancing Explainability and Privacy in Bank Failure Prediction: A Differentially Private Glass-Box Approach
Predicting bank failures is a critical task requiring balancing the need for model explainability with the necessity of preserving data privacy. Traditional machine learning models often lack transparency, which poses challenges for stakeholders who need to understand the factors leading to predictions. In this study, we employ differentially private glass-box models, namely Explainable Boosting Machine (EBM) and Neural Additive Models (NAM), to address these issues. We analyzed data from 21,243 American banks spanning from 1969 to 2021, focusing on key financial ratios. By applying Differential Privacy (DP) to these models, we aimed to protect sensitive financial data while evaluating the trade-offs between privacy, accuracy, and explainability. Our main findings are as follows: i) In the absence of privacy constraints, the models consistently identified Asset Turnover, Total Debt / Invested Capital, and ROE ratios as the most influential factors in predicting bank failure, in that order. ii) When the privacy budget ϵ ≤ 1, only EBM maintained significant performance. iii) The reduction in explainability due to privacy protection was more pronounced for variables with initially lower explanatory power, while Asset Turnover retained its explanatory power even at ϵ = 0.01. These findings provide valuable insights for banks, policymakers, and investors, suggesting that glass-box models can offer a promising solution for reliable and explainable bank failure prediction under privacy constraints.
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 1546-1565
Open AccessBalancing Explainability and Privacy in Bank Failure Prediction: A Differentially Private Glass-Box Approach
Predicting bank failures is a critical task requiring balancing the need for model explainability with the necessity of preserving data privacy. Traditional machine learning models often lack transparency, which poses challenges for stakeholders who need to understand the factors leading to predictions. In this study, we employ differentially private glass-box models, namely Explainable Boosting Machine (EBM) and Neural Additive Models (NAM), to address these issues. We analyzed data from 21,243 American banks spanning from 1969 to 2021, focusing on key financial ratios. By applying Differential Privacy (DP) to these models, we aimed to protect sensitive financial data while evaluating the trade-offs between privacy, accuracy, and explainability. Our main findings are as follows: i) In the absence of privacy constraints, the models consistently identified Asset Turnover, Total Debt / Invested Capital, and ROE ratios as the most influential factors in predicting bank failure, in that order. ii) When the privacy budget ϵ ≤ 1, only EBM maintained significant performance. iii) The reduction in explainability due to privacy protection was more pronounced for variables with initially lower explanatory power, while Asset Turnover retained its explanatory power even at ϵ = 0.01. These findings provide valuable insights for banks, policymakers, and investors, suggesting that glass-box models can offer a promising solution for reliable and explainable bank failure prediction under privacy constraints.
- 4 August 2024
- Published by Elsevier in Finance Research Letters
- Vol. 68
Influence and predictive power of sentiment: Evidence from the lithium market
- 4 August 2024
- Published by Elsevier in Finance Research Letters
- Vol. 68
Influence and predictive power of sentiment: Evidence from the lithium market
- 20 November 2023
- Published by Elsevier in Future Generation Computer Systems
- Vol. 153, 70-83
Unraveling the MEV enigma: ABI-free detection model using Graph Neural Networks
- 20 November 2023
- Published by Elsevier in Future Generation Computer Systems
- Vol. 153, 70-83
Unraveling the MEV enigma: ABI-free detection model using Graph Neural Networks
- 13 October 2023
- Published by Elsevier in Research in International Business and Finance
- Vol. 67
Portfolio insurance strategy in the cryptocurrency market
- 13 October 2023
- Published by Elsevier in Research in International Business and Finance
- Vol. 67
Portfolio insurance strategy in the cryptocurrency market
- Open Access
Unraveling the MEV Enigma: ABI-Free Detection Model using Graph Neural Networks
The detection of Maximal Extractable Value (MEV) in blockchain is crucial for enhancing blockchain security, as it enables the evaluation of potential consensus layer risks, the effectiveness of anti-centralization solutions, and the assessment of user exploitation. However, existing MEV detection methods face limitations due to their low recall rate, reliance on pre-registered Application Binary Interfaces (ABIs) and the need for continuous monitoring of new DeFi services. In this paper, we propose ArbiNet, a novel GNN-based detection model that offers a low-overhead and accurate solution for MEV detection without requiring knowledge of smart contract code or ABIs. We collected an extensive MEV dataset, surpassing currently available public datasets, to train ArbiNet. Our implemented model and open dataset enhance the understanding of the MEV landscape, serving as a foundation for MEV quantification and improved blockchain security.
Open AccessUnraveling the MEV Enigma: ABI-Free Detection Model using Graph Neural Networks
The detection of Maximal Extractable Value (MEV) in blockchain is crucial for enhancing blockchain security, as it enables the evaluation of potential consensus layer risks, the effectiveness of anti-centralization solutions, and the assessment of user exploitation. However, existing MEV detection methods face limitations due to their low recall rate, reliance on pre-registered Application Binary Interfaces (ABIs) and the need for continuous monitoring of new DeFi services. In this paper, we propose ArbiNet, a novel GNN-based detection model that offers a low-overhead and accurate solution for MEV detection without requiring knowledge of smart contract code or ABIs. We collected an extensive MEV dataset, surpassing currently available public datasets, to train ArbiNet. Our implemented model and open dataset enhance the understanding of the MEV landscape, serving as a foundation for MEV quantification and improved blockchain security.
- 2 March 2023
- Published by Wiley in Journal of Forecasting
- Vol. 42 (7) , 1539-1559
Forecasting global stock market volatility: The impact of volatility spillover index in spatial‐temporal graph‐based model
The shocks on certain market spread to other markets due to the financial linkages of global economy, which is known as volatility spillover effect. In this study, we propose a volatility forecasting model for global market indices using the spatial‐temporal graph neural network (GNN). The volatility spillover between markets are reflected in the model by estimating the linkage between markets, which is the input of GNN, using the volatility spillover index. An empirical analysis is conducted on eight representative global market indices. From the out‐of‐sample results, we found the following features. First, the proposed spatial‐temporal GNN spillover model outperforms the benchmark models in short‐ and mid‐term forecasting. Second, the forecasting accuracy highly depends on the inclusion of the market index with a high volatility spillover effect. Including S&P500, which contains the highest net spillover index, effectively helps to forecast the volatilities of other markets. Third, the investor can gain economic gain by using predicted volatility from proposed model in the mean‐variance framework.
- 2 March 2023
- Published by Wiley in Journal of Forecasting
- Vol. 42 (7) , 1539-1559
Forecasting global stock market volatility: The impact of volatility spillover index in spatial‐temporal graph‐based model
The shocks on certain market spread to other markets due to the financial linkages of global economy, which is known as volatility spillover effect. In this study, we propose a volatility forecasting model for global market indices using the spatial‐temporal graph neural network (GNN). The volatility spillover between markets are reflected in the model by estimating the linkage between markets, which is the input of GNN, using the volatility spillover index. An empirical analysis is conducted on eight representative global market indices. From the out‐of‐sample results, we found the following features. First, the proposed spatial‐temporal GNN spillover model outperforms the benchmark models in short‐ and mid‐term forecasting. Second, the forecasting accuracy highly depends on the inclusion of the market index with a high volatility spillover effect. Including S&P500, which contains the highest net spillover index, effectively helps to forecast the volatilities of other markets. Third, the investor can gain economic gain by using predicted volatility from proposed model in the mean‐variance framework.
- Top Cited Papers
- 25 March 2022
- Published by Elsevier in Finance Research Letters
- Vol. 47
The economic value of NFT: Evidence from a portfolio analysis using mean–variance framework
- 25 March 2022
- Published by Elsevier in Finance Research Letters
- Vol. 47
Top Cited PapersThe economic value of NFT: Evidence from a portfolio analysis using mean–variance framework
- 1 January 2022
- Published by Elsevier in Finance Research Letters
- Vol. 44
Graph-based multi-factor asset pricing model
- 1 January 2022
- Published by Elsevier in Finance Research Letters
- Vol. 44
Graph-based multi-factor asset pricing model
- Open Access
- 18 February 2020
- Published by MDPI AG in Sustainability
- Vol. 12 (4) , 1529
A Scalable IoT Protocol via an Efficient DAG-Based Distributed Ledger Consensus
The Internet of Things (IoT) suffers from various security vulnerabilities. The use of blockchain technology can help resolve these vulnerabilities, but some practical problems in terms of scalability continue to hinder the adaption of blockchain for application in the IoT. The directed acyclic graph (DAG)-based Tangle model proposed by the IOTA Foundation aims to avoid transaction fees by employing a different protocol from that used in the blockchain. This model uses the Markov chain Monte Carlo (MCMC) algorithm to update a distributed ledger. However, concerns about centralization by the coordinator nodes remain. Additionally, the economic incentive to choose the algorithm is insufficient. The present study proposes a light and efficient distributed ledger update algorithm that regards only the subtangle of each step by considering the Bayesian inference. Experimental results have confirmed that the performance of the proposed methodology is similar to that of the existing methodology, and the proposed methodology enables a faster computation time. It also provides the same resistance to possible attacks, and for the same reasons, as does the MCMC algorithm.
- 18 February 2020
- Published by MDPI AG in Sustainability
- Vol. 12 (4) , 1529
Open AccessA Scalable IoT Protocol via an Efficient DAG-Based Distributed Ledger Consensus
The Internet of Things (IoT) suffers from various security vulnerabilities. The use of blockchain technology can help resolve these vulnerabilities, but some practical problems in terms of scalability continue to hinder the adaption of blockchain for application in the IoT. The directed acyclic graph (DAG)-based Tangle model proposed by the IOTA Foundation aims to avoid transaction fees by employing a different protocol from that used in the blockchain. This model uses the Markov chain Monte Carlo (MCMC) algorithm to update a distributed ledger. However, concerns about centralization by the coordinator nodes remain. Additionally, the economic incentive to choose the algorithm is insufficient. The present study proposes a light and efficient distributed ledger update algorithm that regards only the subtangle of each step by considering the Bayesian inference. Experimental results have confirmed that the performance of the proposed methodology is similar to that of the existing methodology, and the proposed methodology enables a faster computation time. It also provides the same resistance to possible attacks, and for the same reasons, as does the MCMC algorithm.
- Open Access
- 25 June 2019
- Published by MDPI AG in Sustainability
- Vol. 11 (12) , 3489
Loss-Driven Adversarial Ensemble Deep Learning for On-Line Time Series Analysis
Developing a robust and sustainable system is an important problem in which deep learning models are used in real-world applications. Ensemble methods combine diverse models to improve performance and achieve robustness. The analysis of time series data requires dealing with continuously incoming instances; however, most ensemble models suffer when adapting to a change in data distribution. Therefore, we propose an on-line ensemble deep learning algorithm that aggregates deep learning models and adjusts the ensemble weight based on loss value in this study. We theoretically demonstrate that the ensemble weight converges to the limiting distribution, and, thus, minimizes the average total loss from a new regret measure based on adversarial assumption. We also present an overall framework that can be applied to analyze time series. In the experiments, we focused on the on-line phase, in which the ensemble models predict the binary class for the simulated data and the financial and non-financial real data. The proposed method outperformed other ensemble approaches. Moreover, our method was not only robust to the intentional attacks but also sustainable in data distribution changes. In the future, our algorithm can be extended to regression and multiclass classification problems.
- 25 June 2019
- Published by MDPI AG in Sustainability
- Vol. 11 (12) , 3489
Open AccessLoss-Driven Adversarial Ensemble Deep Learning for On-Line Time Series Analysis
Developing a robust and sustainable system is an important problem in which deep learning models are used in real-world applications. Ensemble methods combine diverse models to improve performance and achieve robustness. The analysis of time series data requires dealing with continuously incoming instances; however, most ensemble models suffer when adapting to a change in data distribution. Therefore, we propose an on-line ensemble deep learning algorithm that aggregates deep learning models and adjusts the ensemble weight based on loss value in this study. We theoretically demonstrate that the ensemble weight converges to the limiting distribution, and, thus, minimizes the average total loss from a new regret measure based on adversarial assumption. We also present an overall framework that can be applied to analyze time series. In the experiments, we focused on the on-line phase, in which the ensemble models predict the binary class for the simulated data and the financial and non-financial real data. The proposed method outperformed other ensemble approaches. Moreover, our method was not only robust to the intentional attacks but also sustainable in data distribution changes. In the future, our algorithm can be extended to regression and multiclass classification problems.