Iterative Strategy Testing and Dynamic Single-Stock Position Control

Summary

The author recounts developing and repeatedly revising a set of strategies, then lays out a research-to-deployment process. It begins by defining intended capital capacity, trading costs and order size, the balance between win rate and payoff, training data and features, entry and holding rules, and portfolio and per-stock controls. The author recommends repeated backtests, recording statistics after each change, and trying to find conditions that would invalidate the strategy. Strategies that survive this challenge should be paper traded for an extended period, ideally through a falling market, before another round of review and possible live use.

For single-stock control, the post describes capping each position and adjusting holdings dynamically around a cost basis, while managing gains and losses separately. These are personal guidelines rather than a reproducible tested system: the post provides no performance data, precise adjustment rules, or evidence that the process generalizes. Repeatedly tuning against historical results may also leave strategies vulnerable to overfitting.

Key ideas

• Strategy design should account for capital capacity, trading costs, selection quality, entry timing, holding period, and position controls.
• The author recommends recording statistics after each backtest revision and actively trying to disprove the strategy.
• Strategies that survive historical challenges should be paper traded through varied market conditions before live deployment.
• Per-stock exposure is capped, with dynamic adds or reductions used to manage the cost basis and open gains or losses.
• The recommendations are personal and lack documented performance evidence or fully specified rules.

Tags

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