Platform Features for Factor Screening, Realistic Backtests, and Live Validation
Summary
This user proposal for a quantitative trading platform focuses on making research and strategy evaluation more credible. Suggestions include allowing users to schedule live strategy runs, screening factors using their information coefficients over prior periods, and offering marketplaces for data or factors. It also proposes adding market impact assumptions to backtests and holding a live trading competition with verified accounts so users can distinguish live-validated strategies from simulated results.
The central research lesson is that factor selection and strategy evaluation depend on more than headline backtest returns: historical factor behavior, trading costs, capacity, and live execution all matter. The post offers opinions and product ideas rather than empirical tests or detailed methods. It does not define the information coefficient window, impact-cost model, verification rules, or how live performance should be compared. Its concerns about concentrated, high-turnover strategies are qualitative and are not supported with specific performance evidence.
Key ideas
- The author proposes using past information coefficients to screen factors for current use.
- Backtests should account for market impact to better reflect the costs of trading constrained strategies.
- Verified live trading records could provide evidence beyond simulated strategy rankings.
- Data and factor access are proposed as useful marketplace offerings alongside finished strategies.
- The proposals are conceptual and do not specify evaluation methods or provide empirical results.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.