Quantitative research for low- and medium-frequency trading

His main research areas are low- and medium-frequency trading, time-series analysis, strategy testing, market trends, trend-reversal signals, risk management and strategy performance evaluation. Rather than simply fitting models to historical data, research at Topalpha puts the weight on whether results hold up across different market phases, how well an approach adapts when market structure changes, and the relationship between expected return and the risk taken to earn it.

Alongside his research role, Son works directly on turning research findings into systems that operate in real conditions. His background in software engineering, Python, data processing and system architecture lets him connect the whole path — from forming a research hypothesis, testing it against data and assessing its risk, to building the internal systems that support Topalpha's research and trading operations. This approach narrows the gap between quantitative research and applying its results in real market conditions.

Son holds a Doctor of Business Administration (DBA), with research focused on applying artificial intelligence and machine learning to financial trading and quantitative decision-making. A grounding that spans finance, economics, technology and quantitative research underpins his interdisciplinary approach at Topalpha.

Through his work at Topalpha, Son aims to build a systematic process for low- and medium-frequency trading, grounded in data and risk-aware thinking, and to keep a clear record of how that process performs in practice.