Noldo

ANN MACD Future Forecast (SPY 1D)

NOTE : Deep learning was conducted in a narrow sample set for testing purposes. So this script is Experimental .

This system is based on the following article and is inspired by an external program:

https://hackernoon.com/everything-you-ne...

None of the artificial neural networks in Tradingview work and are not based on completely correct logic. Unlike others in this system:

IMPORTANT NOTE: If the tangent activation function is used, the input data must also have tangent values (compared to the previous values of 1 bar).
Inputs were prepared according to this judgment.

1. The tangent function which is the activation function is written correctly. (The tangent function in the article: ActivationFunctionTanh (v) => (1 - exp (-2 * v)) / (1 + exp (-2 * v)))
2. Missing bias parts in the formulas were added.
3. The output function is taken from the next day (historical), so that the next bar can be predicted, which is the truth.
4.The forecast value of the next bar is subtracted from the current bar change and the market direction is determined.
5.When the future forecast and the current close are added together, the resulting data is called seed.
The seed carries data both from the present and from yesterday and from the future.
6.And this seed was subjected to the MACD method.
Thus, due to exponential averages, more importance will be given to recent developments and
The acceleration situations will show us the direction.
However, a short position should be taken for crossover and a long position for crossunder .
Because the predicted values ​​work in reverse.Even though we use the same period (9,12,26) it is much faster!
7. There is no future code that can cause Repaint.
However, the color after closing should be checked.

The system is completely correct.
However, a very narrow sample was selected.
100 data: Tangent diffs ; volume change, bollinger bands values changes (Upband , Midband , Lowband) and LazyBear's Squeeze Momentum Indicator (SQZMOM_LB) change and the next bar data (historical) price change were put into the deep learning test.

IMPORTANT NOTE : The larger the sample set and the more effective dependent variables, the higher the hit rate of the deep learning test!
EDIT : This code is open source under the MIT License. If you have any improvements or corrections to suggest, please send me a pull request via the github repository https://github.com/user-Noldo

Stay tuned. Best regards!
เอกสารเผยแพร่: Added max_bars_back for reduce calculation loads. Thanks @rhanna for warn me .
Note : Use that only SPY (AMEX:SPY) . Because deep learning calculations based on this chart.
I m working with BTC Deep Learning script . I will publish it soon ! Best regards.
เอกสารเผยแพร่: Plot codes updated.
เอกสารเผยแพร่: Switchable barcolor preference added.
ลบออกจากสคริปส์โปรด เพิ่มเข้าไปในสคริปส์โปรด
BTC version :
ตอบกลับ
Thanks for sharing, but when i try to add it to my chart then i'm getting the following error http://prntscr.com/pdxu0y

How can i fix this?
ตอบกลับ
Noldo rhanna
ตอบกลับ
@Noldo, no i tried it on ETHUSD, can i use this script only for SPY?
ตอบกลับ
Noldo rhanna
@rhanna, Yes , because this script calculated with SPY data and indicators on SPY. But thanks for that feedback. The calculations are so heavy for pine so i may add max_bars_back function. BTW I'm working on BTC Deep Learning script now .(15 mins ) I ll post it after i finish. (y)
ตอบกลับ
@Noldo, thanks buddy, i appreciate it. keep up the good work.
+1 ตอบกลับ
Noldo rhanna
@rhanna, Bug fixed .
ตอบกลับ
@Noldo, awesome, thanks a lot.
ตอบกลับ
one of my fav scripts out there, thanks :)
this works very nice on 1min chart: https://anonymousfiles.io/DxRX0W4M/

cheers
ตอบกลับ
Noldo scamArtist
@scamArtist, Thanks !
looks good, but even if we use the tangents, I recommend using the appropriate period (1D).
The sample is narrow, so use it only for ideas when processing.
ตอบกลับ
หน้าแรก ตัวช่วยคัดกรองหุ้น ตัวคัดกรองฟอเร็กซ์ ตัวคัดกรองคริปโต ปฏิทินเศรษฐกิจ มันทำงานได้อย่างไร ข้อมูลสำคัญของชาร์ต ราคา กฎของบ้าน ผู้ดูแลการใช้งาน เว็บไซต์ & โบรกเกอร์ โซลูชั่น วิดเจ็ต โซลูชั่นชาร์ต ศูนย์ช่วยเหลือ คำร้องขอเพิ่มเติมลักษณะและบริการ บล็อก & ข่าว คำถามที่พบบ่อย วิกิ Twitter
ข้อมูลส่วนตัว ตั้งค่าประวัติ บัญชีและการเรียกเก็บเงิน เหรียญ TradingView ตั๋วการขอความสนับสนุนของฉัน ศูนย์ช่วยเหลือ ไอเดียที่ถูกตีพิมพ์ ผู้ติดตาม กำลังติดตาม ข้อความส่วนตัว แชท ออกจากระบบ