Machine-Learning-Z-Score-Tradingview

Viewing 2 posts - 1 through 2 (of 2 total)

Author

Posts

09/04/2025 at 10:58 AM #250346 quote

Ciccarelli Franco

Participant

Junior

Richiedo , se è possibile, la traduzione di questo indicatore.

https://it.tradingview.com/script/oJKrJF4L-Machine-Learning-Z-Score-Buy-and-Sell-SS/

Grazie

09/10/2025 at 10:21 AM #250617 quote

Iván González

Moderator

Master

Ecco l’indicatore. Non avendo ancora la possibilità di creare funzioni proprie, mi è risultato complesso programmare la correlazione e consuma molte risorse.
Nell’indicatore vedrai che per impostazione predefinita utilizzo un’approssimazione e, nel caso si desideri il coefficiente di Pearson, suggerisco di attivare l’opzione per calcolare solo sulle ultime X barre (200 per esempio).

//-------------------------------------------------------------
// PRC_Machine Learning Z-Score by Steversteves
// version = 0
// 10.09.25
// Iván González @ www.prorealcode.com
// Sharing ProRealTime knowledge
//-------------------------------------------------------------
//defparam calculateonlastbars=200
//-------------------------------------------------------------
// ===== Input parameters =====
//-------------------------------------------------------------
autoadjust = 1   // 1 = true, 0 = false
lengthinput = 75 // default length if autoadjust = 0
plottgt = 1      // 1 = true, 0 = false
manualprice = 0  // 1 = true, 0 = false
pullbacksd = 1.0 // pullback standard deviation factor
aproxCorr = 1 // 1 = use R2 , 0 = use pearson correlation (uncomment defparam line)
barcolor = 1 // 1 = true, 0 = false
//-------------------------------------------------------------
// Correlation calculation
//-------------------------------------------------------------
if aproxCorr then
   // ===== Correlation approximation with R2 =====
   cor1 = R2[50](close)
   cor2 = R2[100](close)
   cor3 = R2[150](close)
   cor4 = R2[200](close)
   cor5 = R2[250](close)
   cor6 = R2[300](close)
   cor7 = R2[350](close)
   cor8 = R2[400](close)
   cor9 = R2[450](close)
   cor10 = R2[500](close)
else
   // ===== Pearson Correlation =====
   // --- Pearson correlation for 50 ---
   len = 50
   sumX = 0
   sumY = 0
   sumXY = 0
   sumX2 = 0
   sumY2 = 0
   
   FOR i = 0 TO len-1 DO
      xi = barindex[i]
      yi = close[i]
      sumX = sumX + xi
      sumY = sumY + yi
      sumXY = sumXY + xi * yi
      sumX2 = sumX2 + xi * xi
      sumY2 = sumY2 + yi * yi
   NEXT
   
   n = len
   num = n * sumXY - sumX * sumY
   den = SQRT((n * sumX2 - sumX * sumX) * (n * sumY2 - sumY * sumY))
   
   IF den <> 0 THEN
      cor1 = ABS(num / den)
   ELSE
      cor1 = 0
   ENDIF
   
   // --- Pearson correlation for 100 ---
   len = 100
   sumX = 0
   sumY = 0
   sumXY = 0
   sumX2 = 0
   sumY2 = 0
   
   FOR i = 0 TO len-1 DO
      xi = barindex[i]
      yi = close[i]
      sumX = sumX + xi
      sumY = sumY + yi
      sumXY = sumXY + xi * yi
      sumX2 = sumX2 + xi * xi
      sumY2 = sumY2 + yi * yi
   NEXT
   
   n = len
   num = n * sumXY - sumX * sumY
   den = SQRT((n * sumX2 - sumX * sumX) * (n * sumY2 - sumY * sumY))
   
   IF den <> 0 THEN
      cor2 = ABS(num / den)
   ELSE
      cor2 = 0
   ENDIF
   
   // --- Pearson correlation for 150 ---
   len = 150
   sumX = 0
   sumY = 0
   sumXY = 0
   sumX2 = 0
   sumY2 = 0
   
   FOR i = 0 TO len-1 DO
      xi = barindex[i]
      yi = close[i]
      sumX = sumX + xi
      sumY = sumY + yi
      sumXY = sumXY + xi * yi
      sumX2 = sumX2 + xi * xi
      sumY2 = sumY2 + yi * yi
   NEXT
   
   n = len
   num = n * sumXY - sumX * sumY
   den = SQRT((n * sumX2 - sumX * sumX) * (n * sumY2 - sumY * sumY))
   
   IF den <> 0 THEN
      cor3 = ABS(num / den)
   ELSE
      cor3 = 0
   ENDIF
   
   // --- Pearson correlation for 200 ---
   len = 200
   sumX = 0
   sumY = 0
   sumXY = 0
   sumX2 = 0
   sumY2 = 0
   
   FOR i = 0 TO len-1 DO
      xi = barindex[i]
      yi = close[i]
      sumX = sumX + xi
      sumY = sumY + yi
      sumXY = sumXY + xi * yi
      sumX2 = sumX2 + xi * xi
      sumY2 = sumY2 + yi * yi
   NEXT
   
   n = len
   num = n * sumXY - sumX * sumY
   den = SQRT((n * sumX2 - sumX * sumX) * (n * sumY2 - sumY * sumY))
   
   IF den <> 0 THEN
      cor4 = ABS(num / den)
   ELSE
      cor4 = 0
   ENDIF
   
   // --- Pearson correlation for 250 ---
   len = 250
   sumX = 0
   sumY = 0
   sumXY = 0
   sumX2 = 0
   sumY2 = 0
   
   FOR i = 0 TO len-1 DO
      xi = barindex[i]
      yi = close[i]
      sumX = sumX + xi
      sumY = sumY + yi
      sumXY = sumXY + xi * yi
      sumX2 = sumX2 + xi * xi
      sumY2 = sumY2 + yi * yi
   NEXT
   
   n = len
   num = n * sumXY - sumX * sumY
   den = SQRT((n * sumX2 - sumX * sumX) * (n * sumY2 - sumY * sumY))
   
   IF den <> 0 THEN
      cor5 = ABS(num / den)
   ELSE
      cor5 = 0
   ENDIF
   
   // --- Pearson correlation for 300 ---
   len = 300
   sumX = 0
   sumY = 0
   sumXY = 0
   sumX2 = 0
   sumY2 = 0
   
   FOR i = 0 TO len-1 DO
      xi = barindex[i]
      yi = close[i]
      sumX = sumX + xi
      sumY = sumY + yi
      sumXY = sumXY + xi * yi
      sumX2 = sumX2 + xi * xi
      sumY2 = sumY2 + yi * yi
   NEXT
   
   n = len
   num = n * sumXY - sumX * sumY
   den = SQRT((n * sumX2 - sumX * sumX) * (n * sumY2 - sumY * sumY))
   
   IF den <> 0 THEN
      cor6 = ABS(num / den)
   ELSE
      cor6 = 0
   ENDIF
   
   // --- Pearson correlation for 350 ---
   len = 350
   sumX = 0
   sumY = 0
   sumXY = 0
   sumX2 = 0
   sumY2 = 0
   
   FOR i = 0 TO len-1 DO
      xi = barindex[i]
      yi = close[i]
      sumX = sumX + xi
      sumY = sumY + yi
      sumXY = sumXY + xi * yi
      sumX2 = sumX2 + xi * xi
      sumY2 = sumY2 + yi * yi
   NEXT
   
   n = len
   num = n * sumXY - sumX * sumY
   den = SQRT((n * sumX2 - sumX * sumX) * (n * sumY2 - sumY * sumY))
   
   IF den <> 0 THEN
      cor7 = ABS(num / den)
   ELSE
      cor7 = 0
   ENDIF
   
   // --- Pearson correlation for 400 ---
   len = 400
   sumX = 0
   sumY = 0
   sumXY = 0
   sumX2 = 0
   sumY2 = 0
   
   FOR i = 0 TO len-1 DO
      xi = barindex[i]
      yi = close[i]
      sumX = sumX + xi
      sumY = sumY + yi
      sumXY = sumXY + xi * yi
      sumX2 = sumX2 + xi * xi
      sumY2 = sumY2 + yi * yi
   NEXT
   
   n = len
   num = n * sumXY - sumX * sumY
   den = SQRT((n * sumX2 - sumX * sumX) * (n * sumY2 - sumY * sumY))
   
   IF den <> 0 THEN
      cor8 = ABS(num / den)
   ELSE
      cor8 = 0
   ENDIF
   
   // --- Pearson correlation for 450 ---
   len = 450
   sumX = 0
   sumY = 0
   sumXY = 0
   sumX2 = 0
   sumY2 = 0
   
   FOR i = 0 TO len-1 DO
      xi = barindex[i]
      yi = close[i]
      sumX = sumX + xi
      sumY = sumY + yi
      sumXY = sumXY + xi * yi
      sumX2 = sumX2 + xi * xi
      sumY2 = sumY2 + yi * yi
   NEXT
   
   n = len
   num = n * sumXY - sumX * sumY
   den = SQRT((n * sumX2 - sumX * sumX) * (n * sumY2 - sumY * sumY))
   
   IF den <> 0 THEN
      cor9 = ABS(num / den)
   ELSE
      cor9 = 0
   ENDIF
   
   // --- Pearson correlation for 500 ---
   len = 500
   sumX = 0
   sumY = 0
   sumXY = 0
   sumX2 = 0
   sumY2 = 0
   
   FOR i = 0 TO len-1 DO
      xi = barindex[i]
      yi = close[i]
      sumX = sumX + xi
      sumY = sumY + yi
      sumXY = sumXY + xi * yi
      sumX2 = sumX2 + xi * xi
      sumY2 = sumY2 + yi * yi
   NEXT
   
   n = len
   num = n * sumXY - sumX * sumY
   den = SQRT((n * sumX2 - sumX * sumX) * (n * sumY2 - sumY * sumY))
   
   IF den <> 0 THEN
      cor10 = ABS(num / den)
   ELSE
      cor10 = 0
   ENDIF
endif

maxcor = MAX(MAX(MAX(MAX(MAX(cor1,cor2),cor3),MAX(cor4,cor5)),MAX(cor6,cor7)),MAX(MAX(cor8,cor9),cor10))

IF autoadjust = 1 THEN
   IF maxcor = cor1 THEN
      len = 50
   ELSIF maxcor = cor2 THEN
      len = 100
   ELSIF maxcor = cor3 THEN
      len = 150
   ELSIF maxcor = cor4 THEN
      len = 200
   ELSIF maxcor = cor5 THEN
      len = 250
   ELSIF maxcor = cor6 THEN
      len = 300
   ELSIF maxcor = cor7 THEN
      len = 350
   ELSIF maxcor = cor8 THEN
      len = 400
   ELSIF maxcor = cor9 THEN
      len = 450
   ELSE
      len = 500
   ENDIF
ELSE
   len = lengthinput
ENDIF
//-------------------------------------------------------------
// ===== Z-Score calculations =====
//-------------------------------------------------------------
a = Average[len](close)        // mean
b = Std[len](close)            // standard deviation
c = (close - a) / b            // z-score

sma = Average[len](c)          // smoothed z-score

IF manualprice = 1 THEN
   z0 = a + pullbacksd * b
ELSE
   z0 = a + sma * b
ENDIF

highz = Highest[len](c)
lowz  = Lowest[len](c)

//-------------------------------------------------------------
// ===== Buy & Sell logic =====
//-------------------------------------------------------------
ONCE buywait = 0
ONCE sellwait = 0

lowestprice = Lowest[20](low)
highestprice = Highest[20](high)
atr = AverageTrueRange[14](close)

// ---- Buy signal ----
IF c <= lowz THEN
   buywait = buywait + 1
   IF buywait > 8 THEN
      DRAWARROWUP(barindex,low-0.35*atr)coloured(0,255,0)
      DRAWTEXT("Z-Score= #c#", barindex, lowestprice - 3*atr) COLOURED("darkgreen")
      DRAWTEXT("Cor Length= #len#", barindex, lowestprice - 2*atr) COLOURED("darkgreen")
      DRAWTEXT("TP= #z0#", barindex, lowestprice - atr) COLOURED("darkgreen")
      IF plottgt = 1 THEN
         DRAWSEGMENT(barindex, z0, barindex+100, z0) coloured(0,255,0)
      ENDIF
      buywait = 0
   ENDIF
ENDIF

// ---- Sell signal ----
IF c >= highz THEN
   sellwait = sellwait + 1
   IF sellwait > 8 THEN
      DRAWARROWDOWN(barindex,high+0.35*atr)coloured(255,0,0)
      DRAWTEXT("Z-Score= #c#", barindex, highestprice + 3*atr) COLOURED("darkred")
      DRAWTEXT("Cor Length= #len#", barindex, highestprice + 2*atr) COLOURED("darkred")
      DRAWTEXT("TP= #z0#", barindex, highestprice + 1*atr) COLOURED("darkred")
      IF plottgt = 1 THEN
         DRAWSEGMENT(barindex, z0, barindex+100, z0) COLOURED(255,0,0)
      ENDIF
      sellwait = 0
   ENDIF
ENDIF
//-------------------------------------------------------------
// ===== Bar colors =====
//-------------------------------------------------------------
overbought = c >= 2
oversold   = c <= -2
if barcolor then
   IF overbought THEN
      DRAWCANDLE(open,high,low,close) COLOURED("fuchsia")
   ELSIF oversold THEN
      DRAWCANDLE(open,high,low,close) COLOURED("black")
   ENDIF
endif
//-------------------------------------------------------------
return

Author

Posts

Viewing 2 posts - 1 through 2 (of 2 total)

You must be logged in to reply to this topic.

Machine-Learning-Z-Score-Tradingview

ProBuilder: Indicatori & Strumenti Personalizzati

New Reply

Author

Ciccarelli Franco @ciccarelli-franco Participant

Summary

This topic contains 1 reply,
has 2 voices, and was last updated by Iván González
4 months, 3 weeks ago.

Topic Details

Forum:	ProBuilder: Indicatori & Strumenti Personalizzati
Language:	Italian
Started:	09/04/2025
Status:	Active
Attachments:	No files

Expert Services

No recent search

Machine-Learning-Z-Score-Tradingview

Machine-Learning-Z-Score-Tradingview ProBuilder: Indicatori & Strumenti Personalizzati

Author

Summary

Topic Details

About personal data collected

Get Assistance

Assistance Type

Your Need

Proposed Solutions

Choose Assistance Type

Your Need

Programming Help

Download Codes

Trading Help

ProRealTime Information

Account Assistance

Paid Programming Help

Machine-Learning-Z-Score-Tradingview

ProBuilder: Indicatori & Strumenti Personalizzati