About FillForward

Hello Gorkem,

The difference in behavior you're observing between data[self.symbol].IsFillForward and data.Bars[self.symbol].IsFillForward is likely due to the way the data is accessed in the Slice object.

In the first case, data[self.symbol] is accessing the TradeBar object directly, which contains the IsFillForward property. This property indicates whether the data point is a fill-forward data point, meaning it was created to fill a gap in data.

In the second case, data.Bars[self.symbol] is accessing the TradeBars collection in the Slice object, which contains all the TradeBar objects for the current time slice. The IsFillForward property in this case is indicating whether the TradeBar for the specific symbol is a fill-forward data point.

Regarding your question about changing the fill-forward logic, the current implementation in LEAN, the engine powering QuantConnect, uses the previous data point when there is no data point for the current slice. This is the default behavior and it's not currently possible to change this logic. The fill-forward feature is designed to ensure that there is always data at each time step in your algorithm, which is important for many trading models.

Here is how you can disable fill-forward for a security in Python:

self.symbol = self.AddEquity("SPY", fillForward=False).Symbol

This will prevent LEAN from filling forward missing data points. However, please note that if you disable fill forward, you may get stale fills or you may see trade volume as zero.

For more information, you can refer to the QuantConnect documentation.

I hope this helps! Let me know if you have any other questions.