The research question
Does an intraday pattern remain observable when the clock and executable price are specified correctly?
A study of rolling evaluation for intraday index models, examining how parameter selection changes across market conditions.
The technical work
Session-aware data preparation, event-driven simulation, walk-forward evaluation and risk controls.
The challenge is to connect the economic idea to a precise, reviewable experiment. Data transformations, the moment of a decision and the interpretation of the resulting return series all belong to that specification.
What to challenge
These are evaluation considerations for this domain, not a checklist presented as already passed.
- Exchange calendars and daylight-saving transitions
- Decision-to-fill ordering
- Spread and slippage at the actual session
- Sufficient independent trades rather than dense correlated bars
The data boundary
Timestamped intraday prices, session calendars and execution information. Coarser bars cannot silently substitute for the original timeframe.
Descriptions are intentionally high-level. Parameters, execution rules and non-public source data are not published here. Withholding an implementation is different from overstating its evidence.
The interesting question is not whether a backtest looks good. It is what would have to be true for the result to mean something.
For the broader framework, see validation. For the engineering context, see the research stack.