Extrapolator: Advanced Time Series Price Forecasting Indicator

Related: EVT Crash Gauge: Advanced Tail-Risk Measurement - another powerful indicator for MetaTrader 5 traders.

Extrapolator is the result of extensive research in time series forecasting, designed to predict future price movements.

Also recommended: Footprint X Ray: Advanced Order Flow and Volume Delta Analysis - similar indicator with strong performance on MetaTrader 5.

This indicator visually represents forecasted prices with two distinct lines: a blue line indicating historical model prices on training bars, and a red line showing the predicted future prices.

The indicator offers a selection of forecasting methods via the 'method' input variable:

- Fourier series extrapolation, with frequencies calculated using the Quinn-Fernandes algorithm.
- Autocorrelation method.
- Weighted Burg method.
- Burg method with Helme-Nikias weighting function.
- Itakura-Saito (geometric) method.
- Modified covariance method.

Methods 2 through 6 employ linear prediction. Linear prediction involves calculating future values as a linear combination of past values. Assuming a price range X[0]..X[n-1] where the lowest index represents the most recent prices, the forecasting of the future price X[n] is calculated as:
X[n] = a[1]*X[n-1] + ... + a[p]*X[n-p]
Where:
- a[i=1..p] are the model coefficients.
- p is the model order.

Methods 2 through 6 determine the 'a[]' coefficients by minimizing the mean-root-square error over the last n-p training bars.
A zero-error forecast on training bars can be achieved by directly solving the aforementioned linear equation system where n=2*p, using the Levinson-Durbin algorithm. This approach is known as the Prony method, but it suffers from unstable future value forecasts and is therefore not included.

Additional input parameters include:

- lastbar: The index of the last bar in the previous data set.
- pastbars: The number of preceding bars used for future value prediction.
- lporder: The order of the linear prediction model, expressed as a fraction of the number of previous bars (0 to 1).
- futbars: The number of future bars to be forecasted.
- harmno: The maximum number of frequencies to consider for method 1 (a value of 0 selects all frequencies).
- freqtol: A measure of inaccuracy in frequency calculation for method 1 (values greater than 0.001 may lead to convergence issues).
- burgwin: The weighting function index for method 2 (0 for rectangular, 1 for Hamming, 2 for parabolic).

This indicator was initially developed in MQL4 and first published in December 2026.

You may also like: super trend quant pro elite: advanced adaptive trend analysis - excellent alternative for indicator users on MetaTrader 5.

#property copyright "robotfx"
#property link "https://robotfx.org"
#property version   "1.00"
#property indicator_chart_window
#property indicator_buffers 2
#property indicator_plots   2
#property indicator_type1   draw_line
#property indicator_color1  red
#property indicator_style1  style_solid
#property indicator_width1  1

.......

• This tool is provided for educational and testing purposes only.
• Past performance does not guarantee future results.
• Trading involves substantial risk of loss. Use on a demo account first.
• Results may vary depending on market conditions, broker, and settings.
• We recommend thorough backtesting and forward testing before using with real funds.