# Samu Scalper AI

A local AI-based scalping expert advisor for MetaTrader 4 using neural networks, evolutionary ensemble, and rule-based engine.

Canonical: https://prismaticalgos.com/compendium/algo/11957-samu-scalper-ai
Record ID: 11957
Catalog rank: 1795 (reading order, not performance)
Snapshot: 2026-10-31 15:46 UTC
Family: Statistical, Quantitative & Machine Learning (I)
Source: https://github.com/ifilex/samuscalper
Evidence label (unverified): source_code

## Scope and limitations

These are machine-extracted research records, not verified trading systems. Catalog rank measures specification detail and claimed evidence, not profitability. The catalog extraction pipeline did not independently backtest these records. Its separate selected testing ledger does not validate the wider corpus. Rules, labels and parameters can be incomplete or wrong; consult the original source and its reuse terms.

No endorsement, ownership claim or source-code reuse permission is implied.

## Extraction warnings

Signal warnings: TIME-ONLY ENTRY: the entry conditions reference only clock time or session, with no market condition. This opens positions on a schedule.
Opacity warnings: PARTLY OPAQUE ENTRY: 2.0 of 4 entry conditions reference a value the source never published. The rest is specified.
Build warnings: MT4_ONLY: the captured source is MQL4 / written for MetaTrader 4. It needs porting (order functions, indicator handles) before it runs on MT5.

## Recorded profile

- symbols: EURUSD, GBPUSD, USDJPY, AUDUSD, USDCAD, NZDUSD, USDCHF, EURJPY, GBPJPY, EURGBP
- timeframes: various
- sessions: 08:00–20:00 GMT
- market_regime: any

## Indicators

- RSI: {"period": 14}; applied to: close
- MACD: {"fast_period": 12, "signal_period": 9, "slow_period": 26}; applied to: close
- EMA: {"period": 20}; applied to: close
- EMA: {"period": 50}; applied to: close
- Bollinger Bands: {}; applied to: close
- ATR: {"period": 14}; applied to: close
- Stochastic: {"period": 14}; applied to: close
- CCI: {"period": 14}; applied to: close
- Hourly Cycle: {}; applied to: time
- Daily Cycle: {}; applied to: time

## Recorded long-entry rules

- neural network output > ±0.30
- ensemble output > ±0.25

## Recorded short-entry rules

- neural network output < -±0.30
- ensemble output < -±0.25

## Recorded exit rules

- stop loss based on ATR
- take profit based on ATR
- quick exit for profit
- time limit
- partial close
- adjust stop to entry
- trailing stop based on ATR
- close on float back from peak
- additional entries based on signal and adverse distance

## Recorded filters

- news filter
- max spread 2.0 pips

## Risk controls

- Stop loss: based on ATR
- Take profit: based on ATR
- Position sizing: Kelly criterion with 20% fraction