Fresh MQL5 code release – perfect for enhancing your MT4/MT5 strategies.
Overview
Installation and File Structure
The headers are included as <BOSS\...> and the indicator lives in an Indicators\BOSS subfolder, so the layout below has to be preserved.
|
File |
Description |
|---|---|
|
Indicators\BOSS\BOSSRegime.mq5 |
The indicator. Trains a BOSS ensemble on recent history at load time and colour-codes the regime lane. |
|
Include\BOSS\FourierTransform.mqh |
CDFT: real-input Fourier front end over ALGLIB's FFT, returning the low coefficients for SFA. |
|
Include\BOSS\SFA.mqh |
CMCB and CSFA: learned equi-depth binning per coefficient slot, and window to word. |
|
Include\BOSS\BOSS.mqh |
CBossHistogram, CBossTransform, CBossClassifier and CBossEnsemble: the bag, the BOSS distance, and the voting ensemble. |
|
Include\BOSS\RegimeLabeler.mqh |
CRegimeLabeler: rule-based trend / range / volatile labels from autocorrelation and volatility. |
Recover from drawdowns intelligently with the Auto Recovery Expert Advisor for MT4/MT5. Perfect for hedging strategies. Learn more.
Input Parameters
|
Parameter |
Default |
What it does |
|---|---|---|
|
Segment |
120 |
Bars per classified segment. BOSS represents a series by the distribution of words its sliding window produces, so the segment has to be long enough to yield many words. |
|
WordLen |
2 |
Fourier coefficients kept, each contributing two letters. The measured robust operating point; raising it overfits noise. |
|
Alphabet |
4 |
Letters available per coefficient slot. Allowed range is 2 to 10. |
|
TrainBars |
2000 |
History bars used to train the ensemble, taken from closed bars only. Fewer bars means faster loading and a narrower sample of regimes. |
|
TrendACF |
0.05 |
Lag-1 autocorrelation above which the labeler calls a training segment trending. Lowered from the class default of 0.15 to balance the training classes, since a strict threshold leaves too few trend examples to learn from. |
|
VolHighMult |
1.3 |
Volatility above this multiple of the mean segment volatility marks a training segment volatile. Relative, not absolute, so it adapts to the instrument. |
|
ShowLabel |
true | Draw a text label naming the current regime in the chart corner. |
Research Basis
The implementation follows the two papers that define the method:
- Patrick Schäfer, The BOSS is concerned with time series classification in the presence of noise, Data Mining and Knowledge Discovery, 2015. The bag-of-words representation, the BOSS distance, and the ensemble with its 92% retention rule.
- Patrick Schäfer and Mikael Högqvist, SFA: A Symbolic Fourier Approximation and Index for Similarity Search in High Dimensional Datasets, EDBT 2012. Symbolic Fourier Approximation and Multiple Coefficient Binning.
One point is worth stating plainly. The labels the ensemble learns from are generated by a simple statistical rule rather than by hand, so the indicator learns to reproduce that rule from window shape alone. It is a transparent, mechanical definition of regime, not an oracle, and a richer or forward-looking labeler would give BOSS a cleaner target. The engine is built so that swapping the labeler is a small change.
A companion article builds every layer from scratch, explains the mathematics, and runs the full benchmark against Dynamic Time Warping: Bag-of-SFA-Symbols (BOSS) in MQL5: Symbolic Time-Series Classification for Market Regimes.
Level up your trading with professional RobotFX expert advisors and indicators. Visit robotfx.org for proven MT4/MT5 tools.
75666
