Finding Strong Intraday Trading Windows by Removing Weak Intervals

Summary

This article presents a method for identifying time windows in which an existing trading system performs better. A library analyzes the system’s trading history, removes weaker intervals, and reports results for the remaining periods. In its scalper example, the reported total profit and profit factor rise as one, then two, then three intervals are excluded. The article also describes connecting the calculation to the platform’s optimization criterion so the tester can evaluate a system using its best interval.

The example illustrates a way to reduce reliance on intuition and avoid repeatedly testing manually chosen time filters. However, the reported improvement comes from selecting intervals on the observed test history, which can overfit noise. The document does not describe out-of-sample validation, costs, or how performance behaves across different market conditions. It covers intraday windows, while intra-week intervals are identified as unfinished work. The figures therefore demonstrate the tool’s output, not proof that the resulting schedule will remain profitable.

Key ideas

• The library searches a system’s trading history for intraday intervals with stronger reported results.
• It removes weaker time windows and summarizes the performance of the intervals that remain.
• The scalper example shows improved aggregate profit and profit factor after successive interval removals.
• The tool can be linked to an optimizer’s custom criterion to evaluate the system on a selected interval.
• Selecting windows on the same history can overfit, and the document does not report out-of-sample validation.
• The described implementation addresses intraday timing, while intra-week interval analysis is not yet implemented.

Tags

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