EMA Warm-Up Data as a Cause of Missing Simulation Signals
Summary
This forum thread concerns a strategy that produced normal backtest behavior but no signals after submission to simulated trading. The user had removed a binding between the strategy’s start date and its live-trading parameter, then waited several days without seeing signals or position information. A thread note points to a possible cause: when the bound start date yields only one day of data, exponential moving average calculations may not have enough history to initialize.
The thread does not include a diagnosis of the persistent no-signal behavior or a confirmed fix. It gives no strategy logic, market results, or details sufficient to determine whether the simulation engine, signal conditions, or data window caused the problem. Its useful general lesson is that indicator calculations need an adequate historical warm-up period, and backtest and simulation data windows may differ. The EMA explanation is presented as a troubleshooting note, not as a verified resolution of this user’s case.
Key ideas
- An EMA may fail to initialize meaningfully when the strategy receives too little historical data.
- A start-date setting that limits data to one day is identified as a possible source of missing indicators.
- A strategy can behave differently in backtest and simulation when their data windows or execution contexts differ.
- The thread does not establish why signals remained absent or confirm a solution.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.