Idea by: Apelsin
mq5 code by: barabashkakvn
The EA uses a very simple neural network unit
double n1=((ma_h1[1]-ma_h1[2])/ma_h1[1])*p1+((ma_h1[2]-ma_h1[3])/ma_h1[3])*p2+((ma_h1[3]-ma_h1[4])/ma_h1[4])*p3; n1=(MathRound(n1*10000)); double n2=((ma_h4[1]-ma_h4[2])/ma_h4[2])*q1+((ma_h4[2]-ma_h4[3])/ma_h4[3])*q2+((ma_h4[3]-ma_h4[4])/ma_h4[4])*q3; n2=(MathRound(n2*10000)); double n3=((ma_d1[1]-ma_d1[2])/ma_d1[2])*k1+((ma_d1[2]-ma_d1[3])/ma_d1[3])*k2+((ma_d1[3]-ma_d1[4])/ma_d1[4])*k3; n3=(MathRound(n3*10000)); if((n1>0 && n2>0 && n3>0)) m_need_open_buy=true; if((n1>0 && n2<0 && n3<0)) m_need_open_sell=true;
based on the signals from three indicators iMA (Moving Average, MA) on H1, H4, and D1.
Recommendations on Optimization
Optimization is performed in two stages (1 and 2 in the picture below).
After stages one and two
select among the top ten ones the version that provides equally good results on both backtest and forward.
