Latest News
- — Our preprint “A Lightweight Detector Ensemble for Univariate Time-Series Anomaly Detection” is on SSRN.
- — Our preprint “Your AI, On a Dial: Controlling Investment Bias in LLMs with a Single Neuron” is on arXiv.
- — Gave an oral presentation on Gerber-shrinkage covariance at the Financial AI session of the 2026 KIIE Spring Conference, Gyeongju.
About Me
I am an undergraduate researcher in the Financial Engineering Lab. (advised by Prof. Hyeongwoo Kong) at the Division of Finance & AI, Hankuk University of Foreign Studies (HUFS). I work at the intersection of quantitative finance and machine learning. My research interests center on Portfolio Optimization, Decision-Focused Learning, and Large Language Models in Finance, with secondary interests in graph neural networks, synthetic data, and explainable AI.
I plan to pursue an integrated M.S./Ph.D. in Financial Engineering beginning in 2027.
Education
- Hankuk University of Foreign Studies (HUFS), South Korea
B.S. in AI Convergence, Division of Finance & AI, 2027 (expected) · GPA 4.23 / 4.5
Experience
- Visiting Research Student, Korea Financial Telecommunications & Clearings Institute (KFTC), 2026.03 – 2026.07 / 2026.10 –
- Undergraduate Researcher, Financial Engineering Lab., HUFS, 2025.07 –
- Research Assistant, UNIST (external collaboration), 2026.03 – 2026.07
- Department Assistant, Division of Finance & AI, HUFS, 2024.09 – 2026.02 / 2026.09 –
Publications
- A Lightweight Detector Ensemble for Univariate Time-Series Anomaly Detection
Sahong Park, Hyeongwoo Kong+
SSRN preprint, 2026 - Your AI, On a Dial: Controlling Investment Bias in LLMs with a Single Neuron
Sahong Park, Suhwan Park, Hoyoung Lee, Gakyung Kwon, Wonbin Ahn, Jaewon Choi, Alejandro Lopez-Lira, Yoon Kim, Chanyeol Choi, Hyeongwoo Kong+, Yongjae Lee+
arXiv preprint (2608.22852), 2026 - Gerber-Shrinkage Covariance: Global Minimum Variance Portfolio via Correlation-Based Dynamic Blending
Sahong Park, Hyeongwoo Kong
Korean Institute of Industrial Engineers (KIIE) Spring Conference 2026, Oral Presentation
Ongoing Work
- Portfolio Optimization
Developing the Gerber-shrinkage covariance work (GerberShrink, KIIE 2026) further. - Investment Bias in LLMs
- Multivariate Time-Series Anomaly Detection
Projects
- KFTC × UNIST · 2026
AI-based Anti-Money Laundering Detection
Suspicious transaction detection on payment networks with graph neural networks.
Honors & Awards
- Academic Merit Scholarship, HUFS, 2025 – 2026
- Choi Eon-do Scholarship, AB Choi Family Foundation, 2025
- Graduate Assistantship, HUFS, 2024 – 2025
- Academic Excellence Scholarship, Gumi City Scholarship Foundation, 2024
Talks & Presentations
- KIIE Spring Conference 2026, Oral Presentation
GerberShrink: Correlation-based Portfolio Optimization - HUFS Winter 2025 Departmental Research Symposium
Decision-Focused Learning for Minimum Variance Portfolio Optimization - HUFS Summer 2025 Departmental Research Symposium
LLM-Based Owner Risk Sentiment and Stock Return Analysis
Organizing & Advising
- Data Analysis & Technology (DAT), HUFS student academic society (~25 members/semester)
Executive Member (Spring 2025) → President (Fall 2025) → Advisor (Spring 2026) - ITDA — Seoul Metropolitan Data Science Society, Spring 2026
Advisor (topic proposal & preliminary reviewer). Proposed the inaugural research topic, GNN-Based Abusive Review Detection in E-Commerce.
Journal Club
Show list (2025 – 2026)
- Solving the Index Tracking Problem Based on a Convex Reformulation for Cointegration — Finance Research Letters 2020
- Decision-Focused Learning via Tangent-Space Projection of Prediction Error (PEAR) — ICML 2026
- Estimating Covariance for Global Minimum Variance Portfolio: A Decision-Focused Learning Approach — ICAIF 2025
- coVariance Neural Networks — NeurIPS 2022
- Nonparametric Stein-type Shrinkage Covariance Matrix Estimators in High-Dimensional Settings — CSDA 2015
- The Gerber Statistic: A Robust Co-Movement Measure for Portfolio Optimization — JPM 2022
- ProtoHedge: Interpretable Hedging with Market Prototypes — ICAIF 2025
- Enhancing Mean–Variance Portfolio Optimization through GANs-based Anomaly Detection — Annals of OR 2025
- War Discourse & Disaster Premium: 160 Years of Evidence from the Stock Market — RFS 2025
- Association-Focused Path Aggregation for Graph Fraud Detection — NeurIPS 2025
- D-EMAML: Dual-Edge Motif Neural Networks for Enhanced Anti-Money Laundering Detection — AAAI 2026
- Regime-Aware Risk Parity — JPM 2026
- Pretraining Task Diversity and the Emergence of Non-Bayesian In-Context Learning — NeurIPS 2023
- KAN: Kolmogorov–Arnold Networks — ICLR 2025
- An Overview of Machine Learning for Portfolio Optimization — JPM 2024
- Attention Factors for Statistical Arbitrage — ICAIF 2025
- NeuralBeta: Estimating Beta Using Deep Learning — ICAIF 2025
- Denoising Diffusion Probabilistic Model for Realistic Financial Correlation Matrices — ICAIF 2024
- Accurate Multivariate Stock Movement Prediction via Data-Axis Transformer (DTML) — KDD 2021
- Multiply Robust Estimation for Local Distribution Shifts with Multiple Domains — ICML 2024
- TabM: Advancing Tabular Deep Learning with Parameter-Efficient Ensembling — ICLR 2025
- XGBoost: A Scalable Tree Boosting System — KDD 2016