EMA Crossover Screening Requires Sufficient History and Filtering
Summary
This forum reply addresses a stock-selection condition that compares a five-period exponential moving average with a 169-period average. It explains that the longer average requires a data history spanning at least 169 days before the condition can produce values. It also clarifies that expressing the comparison as a feature yields a binary indicator: one when the shorter average exceeds the longer average and zero otherwise.
The reply suggests adding a filtering step to use that condition for stock selection and links to an example implementation. It does not provide the implementation details in the supplied text, nor does it evaluate the crossover as a strategy. There are no backtest results, discussion of signal timing, treatment of missing observations, or risk controls, so the exchange helps diagnose a data and workflow issue but does not establish that the rule is profitable.
Key ideas
- A 169-period EMA needs a sufficiently long history before it can be calculated.
- Comparing the short and long EMAs as a feature produces a binary condition.
- A filtering step is suggested to use the condition for stock selection.
- The exchange gives no evidence that the EMA rule has trading value.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.