Quantitative Factor Research and a Momentum ETF Rotation Strategy

Summary

This meetup Q&A surveys quantitative research topics, including collecting and cleaning market data, creating features, training models, and evaluating strategies through backtests. It lists possible information sources beyond price and volume, such as company fundamentals, macroeconomic releases, news, alternative data, and derivatives markets. It also outlines equal weighting, historical performance, machine learning, optimization, and expert judgment as approaches to assigning factor weights, while describing factor testing through return, information coefficient, and backtest analysis.

The clearest concrete strategy is an ETF rotation rule based on recent returns: before each session, compare each ETF’s 20-day gain, invest fully in the strongest ETF when its gain is positive, switch when another ETF leads, and exit when all gains are negative. The document mentions a reported annualized backtest return near 50%, but gives no period, methodology, costs, or drawdown details; it explicitly says simulation and drawdown control are needed. Its broader advice is introductory and does not establish that any method will generalize to live trading.

Key ideas

• Quantitative research combines data preparation, feature construction, model building, backtesting, and ongoing monitoring.
• Potential factor sources include fundamentals, macroeconomic data, news, alternative data, and derivatives markets.
• Factor weights may be chosen through equal weighting, historical tests, machine learning, optimization, or judgment.
• The ETF rotation example invests in the strongest positive 20-day performer and exits when all candidates are negative.
• The cited backtest lacks enough detail to establish live performance, and drawdowns require attention.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.