Glossary
Quantitative investing
Investing by rules and models built from data, where a computer program rather than a person decides what to buy and sell.
On this page
Quantitative investing means choosing investments with mathematical models and fixed rules instead of case-by-case judgment. Analysts look for patterns in prices, financial statements or other data, test them on history with backtesting, and let a program place the trades. Signals range from slow factors, such as cheapness or momentum, to very short-term price patterns and mean reversion.
The best-known record
Renaissance Technologies, founded by the mathematician Jim Simons, runs the Medallion Fund, which averaged about 66% a year before fees and 39% after from 1988 to 2018, as reported by Gregory Zuckerman from private records. It is closed to outsiders. In 2020 Medallion gained 76% while the firm's public funds lost money, a reminder that one firm's methods do not transfer across strategies.
Limits
- Overfitting. A model tuned to past data can find patterns that were luck.
- Capacity. Short-term edges shrink as more money chases them.
- Crowding. When many funds hold the same factor bets, they can lose together.
Funds that package simple factor rules for the public are often sold as smart beta.
Related terms
Sources and further reading
- Zuckerman — The Man Who Solved the Market: How Jim Simons Launched the Quant Revolution, 2019
- Institutional Investor — Renaissance’s Medallion Fund surged 76% in 2020 but funds open to outsiders tanked, January 13, 2021
