TSF — Time Series Forecast

The least-squares regression line extended one bar ahead: what the fit predicts the next close will be. Leads LSMA by exactly one slope-step.

Signature

TSF(period, on=<source>)

Argument	Type	Required	Notes
period	int Param or literal	Yes	Regression window. Default 14, bounds 2–400.
on=	symbol, OHLCV field, or indicator	No	Source. Defaults to the trade symbol’s close.

Formula

$$ \text{TSF} = \text{intercept} + \text{slope},n $$

(LSMA evaluates the same line at n-1.)

Warmup

period bars; the raw close until the window fills.

Reading the value

tsf.value
tsf.value > self.trade.close

Example

class ForecastGap(Strategy):
    """Enter when the forecast sits meaningfully above the current close."""
    trade = Symbol()
    sizing = FixedCapital()

    def execute(self):
        tsf = TSF(14, on=self.trade)
        if tsf.value > self.trade.close * 1.01 and self.trade.is_flat:
            self.buy(self.trade, reason="Forecast above price")
        if tsf.value < self.trade.close and self.trade.is_long:
            self.sell(self.trade, self.trade.position, reason="Forecast rolled over")

Notes

• Standard time series forecast (TA-Lib TSF).
• A forecast, not a prophecy: it is the straight-line extension of the last n bars, so it is exactly as good as the assumption that the trend continues.
• Proven by an assert-via-trade run on SPY daily (matched a strategy-side OLS reference to 1e-3 on every bar; zero alarm trades).