A Three-Stage Quantitative Trading Competition and Training Program
Summary
This document outlines a recurring BigQuant program for people developing quantitative trading skills. It has three stages: an online selection round in which participants submit factor models built from a provided template; training for selected entrants; and a semifinal round involving independently designed models and simulated trading. The program describes a fixed data source and backtest interval for the first round, where rankings depend on long-side returns, and a half-month simulation for the later round.
The training topics include Python and data handling, factor research, strategy development, machine learning, high-frequency factor processing, and reproducing research reports. The document also lists awards and possible career opportunities, but it provides no evidence about participant outcomes or the predictive quality of submitted factors. Rankings based on returns over specified periods may be sensitive to the chosen data, evaluation window, and risk characteristics; the rules described do not explain risk adjustment or safeguards against overfitting.
Key ideas
- The program selects participants through factor submissions evaluated on specified data and a defined backtest period.
- Selected participants receive instruction in quantitative research, strategy development, and data analysis.
- The final stage evaluates independently built models through a short simulated trading period.
- Return-based rankings can favor short-term outcomes, while the document does not describe risk adjustment or overfitting controls.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.