Minkey Chang — Data Scientist
Data scientist working on multivariate time series: representation learning, forecasting, and reinforcement learning for decisions under uncertainty. Recent work includes identifiable latent representations for multivariate series and portfolio optimization under recursive utility, with applied projects in macro nowcasting, high-frequency trading, and synthetic credit data. Trained in economics and statistics.
Selected Publications & Projects
iVDFM in the proceedings track; poster session at KIAS, Seoul (July 2026).
FinAI @ ICLR 2026 — financial AI workshop (Rio, April 2026).
Book on building agents with LangChain and LangGraph (Wikidocs, May 2026).
Climate visualization for South Korea (GitHub Page).
Work Experience
Blog
Driving through underground rocks
Steering a drill bit through rock you cannot see: why a good particle filter still drifts, and how simulation fixed the drift.
Can we really get alpha from market data?
The efficient market view, the micro alpha counter-argument, and why a weak signal only becomes a position once you know its uncertainty.
What works for forecasting macro economic series with deep learning?
Korean output and investment nowcasting with seven deep models: what the data allows, which families worked, and why it depends on the target.
Could multivariate time series have their own representations?
Why forecast embeddings are not factors, and how identifiable innovations with diagonal dynamics recover them without losing forecast quality.
Can we make a more risk-aware portfolio agent from utility theory?
Epstein–Zin recursive utility inside actor–critic RL: the Bellman backup that changes, and what it did on Korean ETF splits.
Classifying bird sounds in the field
Sound as a picture: what a spectrogram is, why the mel scale matches how we hear, and how a network finds a bird call in the image.
Creating and Evaluating Synthetic Tabular Data
Sequential synthesis for credit bureau data, and three checks: pMSE distinguishability, confidence interval overlap, and attribute disclosure.