ChatGPT is an advanced language model that can help you write code more efficiently and accurately. By using ChatGPT, you can generate high-quality Pinescript code without the need for extensive coding knowledge or experience.
In this article, we will focus on using the free version of ChatGPT to code Pinescript indicators and strategies. We'll provide step-by-step instructions, highlighting potential issues you may encounter and how to resolve them. By the end of this article, you'll have the tools you need to leverage ChatGPT to create profitable trading strategies.
So, whether you're an experienced trader or just starting out, read on to discover how you can use ChatGPT to revolutionize your Pinescript coding, and even explore the other exciting possibilities it offers.
Things to know before we continue
💡ChatGPT can generate Pinescript code for both versions 4 and 5, but it's important to note that there are some differences between the two versions. It's recommended to specify which version you want your code written in before using ChatGPT. Additionally, it's worth noting that ChatGPT has more knowledge of Pinescript version 4, so you may want to consider having it write code in version 4 and then use the Tradingview editor to convert it to version 5.
💡It's true that ChatGPT can help you generate Pinescript code without extensive coding knowledge. However, for more complex scripts, it's recommended to have a basic understanding of Pinescript to make the most of ChatGPT. That way, you can better understand the generated code and make adjustments as needed.
💡ChatGPT is a tool that can help you improve your Pinescript coding, not a replacement for it. It's best to use ChatGPT to solve specific issues or come up with solutions for certain parts of your code rather than relying on it to write the entire code for you.
WHAT WE WILL BE CODING FOR OUR FIRST EXAMPLE.
🔸In our example, we will be coding an indicator that uses two moving averages with exposed periods to determine the direction of the market. Additionally, we will be using the stochastic RSI indicator as a momentum indicator to determine when to buy in an uptrend and when to sell in a downtrend. After we have created this script as an indicator, we will use ChatGPT to convert it to a strategy. This will enable us to backtest it using the Tradingview backtesting framework.
Lets begin.
1: The first thing we want to do is let CHatGPT know exactly what we want it to do. And have it come up with a solution to the issue. For our example we are going to type the following below.
Note how I specified the version of pinescript we will be coding in.
2: I am going to let ChatGPT know the description of the indicator we are going to code
🔸As you can see, ChatGPT provided me with Pinescript based on the information I provided. It is worth noting that, while this code worked for me, others may receive slightly different code due to the nature of ChatGPT's predictions. Additionally, ChatGPT explained the code in further detail in its response. Our next step is to test the code to determine whether it meets our requirements, and to note any issues we encounter. If there are any issues, we will provide them to ChatGPT for further assistance. To begin, I will copy and paste the generated code into the Pinescript editor without making any modifications, and attempt to add the script to the chart.
For reference here is the code provided by GPT below :
//version=4
study(title="Moving Average and Stochastic RSI Indicator", shorttitle="MA+Stoch RSI", overlay=false)
// Input variables
ma1_length = input(title="MA1 Length", type=input.integer, defval=20, minval=1)
ma2_length = input(title="MA2 Length", type=input.integer, defval=50, minval=1)
stoch_length = input(title="Stochastic RSI Length", type=input.integer, defval=14, minval=1)
overbought = input(title="Overbought Level", type=input.integer, defval=80)
oversold = input(title="Oversold Level", type=input.integer, defval=20)
// Calculate moving averages
ma1 = sma(close, ma1_length)
ma2 = sma(close, ma2_length)
// Calculate Stochastic RSI
rsi1 = rsi(close, stoch_length)
rsiH = highest(rsi1, stoch_length)
rsiL = lowest(rsi1, stoch_length)
stoch = (rsi1 - rsiL) / (rsiH - rsiL) * 100
// Determine trend direction based on MA crossover
trendUp = ma1 > ma2 ? true : false
trendDown = ma1 < ma2 ? true : false
// Determine buy and sell signals based on Stochastic RSI
buySignal = trendUp and crossover(stoch, oversold)
sellSignal = trendDown and crossunder(stoch, overbought)
// Plot signals on chart
plotshape(buySignal, style=shape.arrowup, location=location.belowbar, color=color.green, size=size.small, text="Buy")
plotshape(sellSignal, style=shape.arrowdown, location=location.abovebar, color=color.red, size=size.small, text="Sell")
🔸The code had no syntax errors and met all the requirements specified in my prompt. The periods for the moving averages and the stochastic RSI were exposed, allowing them to be adjusted as needed. However, there is one issue that is not a result of ChatGPT, but rather caused by my failure to specify it in the prompt. The indicator is not being overlaid on the chart and is instead being displayed as an oscillator in a separate window below, similar to the RSI indicator. However, for our purposes, we want the indicator to be displayed over the candles themselves.
3: After testing the code and verifying that it meets my requirements, I will provide feedback to GPT that the code is functioning properly. However, I will also request that the indicator be displayed over the candles instead of in a separate window. It's important to communicate clearly with GPT to avoid any unnecessary changes to the code.
🔸Now we will test the code again.
Updated code listed below
//version=4
study(title="Moving Average and Stochastic RSI Indicator", shorttitle="MA+Stoch RSI", overlay=true)
// Input variables
ma1_length = input(title="MA1 Length", type=input.integer, defval=20, minval=1)
ma2_length = input(title="MA2 Length", type=input.integer, defval=50, minval=1)
stoch_length = input(title="Stochastic RSI Length", type=input.integer, defval=14, minval=1)
overbought = input(title="Overbought Level", type=input.integer, defval=80)
oversold = input(title="Oversold Level", type=input.integer, defval=20)
// Calculate moving averages
ma1 = sma(close, ma1_length)
ma2 = sma(close, ma2_length)
// Calculate Stochastic RSI
rsi1 = rsi(close, stoch_length)
rsiH = highest(rsi1, stoch_length)
rsiL = lowest(rsi1, stoch_length)
stoch = (rsi1 - rsiL) / (rsiH - rsiL) * 100
// Determine trend direction based on MA crossover
trendUp = ma1 > ma2 ? true : false
trendDown = ma1 < ma2 ? true : false
// Determine buy and sell signals based on Stochastic RSI
buySignal = trendUp and crossover(stoch, oversold)
sellSignal = trendDown and crossunder(stoch, overbought)
// Plot signals on chart
plotshape(buySignal, style=shape.arrowup, location=location.belowbar, color=color.green, size=size.small, text="Buy")
plotshape(sellSignal, style=shape.arrowdown, location=location.abovebar, color=color.red, size=size.small, text="Sell")
🔸Great. Now the code is displaying as we would want it to as well!.
4: Now, let's make some improvements to the code. In addition to generating buy and sell signals, I would also like to see the moving averages displayed on the chart. This will allow me to visually understand why the signals are being generated.
Code reference below:
//version=4
study(title="Moving Average and Stochastic RSI Indicator", shorttitle="MA+Stoch RSI", overlay=true)
// Input variables
ma1_length = input(title="MA1 Length", type=input.integer, defval=20, minval=1)
ma2_length = input(title="MA2 Length", type=input.integer, defval=50, minval=1)
stoch_length = input(title="Stochastic RSI Length", type=input.integer, defval=14, minval=1)
overbought = input(title="Overbought Level", type=input.integer, defval=80)
oversold = input(title="Oversold Level", type=input.integer, defval=20)
// Calculate moving averages
ma1 = sma(close, ma1_length)
ma2 = sma(close, ma2_length)
// Calculate Stochastic RSI
rsi1 = rsi(close, stoch_length)
rsiH = highest(rsi1, stoch_length)
rsiL = lowest(rsi1, stoch_length)
stoch = (rsi1 - rsiL) / (rsiH - rsiL) * 100
// Determine trend direction based on MA crossover
trendUp = ma1 > ma2 ? true : false
trendDown = ma1 < ma2 ? true : false
// Determine buy and sell signals based on Stochastic RSI
buySignal = trendUp and crossover(stoch, oversold)
sellSignal = trendDown and crossunder(stoch, overbought)
// Plot signals on chart
plotshape(buySignal, style=shape.arrowup, location=location.belowbar, color=color.green, size=size.small, text="Buy")
plotshape(sellSignal, style=shape.arrowdown, location=location.abovebar, color=color.red, size=size.small, text="Sell")
// Plot moving averages on chart
plot(ma1, color=color.blue)
plot(ma2, color=color.orange)
🔸Great! Now that we can see the moving averages, we have a better understanding of why the buy and sell signals are being generated. However, before we convert the indicator into a strategy, we need to make one final adjustment: reducing the number of signals being generated. There are various ways to achieve this such as using an ADX filter or a volatility filter. However, for this example, we will simply limit the number of signals generated for each cross of the moving averages to 1.
5: Final adjustments, During the tutorial, ChatGPT crashed, which can happen from time to time. If this happens, simply create a new chat session, copy the code from PineScript, and ask ChatGPT what the script does. Once ChatGPT advises you, you can ask it to act as an expert and help you make any necessary adjustments to the code in PineScript version 4.
🔸Here is when we started to have issues.
Here is my prompt and here is the code provided by ChatGPT
//version=4
study(title="Moving Average and Stochastic RSI Indicator", shorttitle="MA+Stoch RSI", overlay=true)
// Input variables
ma1_length = input(title="MA1 Length", type=input.integer, defval=20, minval=1)
ma2_length = input(title="MA2 Length", type=input.integer, defval=50, minval=1)
stoch_length = input(title="Stochastic RSI Length", type=input.integer, defval=14, minval=1)
overbought = input(title="Overbought Level", type=input.integer, defval=80)
oversold = input(title="Oversold Level", type=input.integer, defval=20)
// Calculate moving averages
ma1 = sma(close, ma1_length)
ma2 = sma(close, ma2_length)
// Calculate Stochastic RSI
rsi1 = rsi(close, stoch_length)
rsiH = highest(rsi1, stoch_length)
rsiL = lowest(rsi1, stoch_length)
stoch = (rsi1 - rsiL) / (rsiH - rsiL) * 100
// Initialize buy and sell signals to false
var buySignal = false
var sellSignal = false
// Determine trend direction based on MA crossover
trendUp = ma1 > ma2 ? true : false
trendDown = ma1 < ma2 ? true : false
// Generate buy signal if a signal has not already been generated and the conditions are met
if trendUp and crossover(stoch, oversold) and not buySignal
buySignal := true
// Generate sell signal if a signal has not already been generated and the conditions are met
if trendDown and crossunder(stoch, overbought) and not sellSignal
sellSignal := true
// Plot signals on chart
plotshape(buySignal, style=shape.arrowup, location=location.belowbar, color=color.green, size=size.small, text="Buy")
plotshape(sellSignal, style=shape.arrowdown, location=location.abovebar, color=color.red, size=size.small, text="Sell")
// Reset buy and sell signals if a new trend develops
if trendUp and sellSignal
sellSignal := false
if trendDown and buySignal
buySignal := false
// Plot moving averages on chart
plot(ma1, color=color.blue)
plot(ma2, color=color.orange)
🔸Once I inputted the code provided I started to get a signal for every candle which is not what we wanted.
So I advised GPT of the issue.
It then attempted to solve the issue but instead it modified the code to only generate a buy signal or sell signal if the moving averages and the stochastic conditions where met all AT THE SAME TIME, Resulting in little to no signals.
//version=4
study(title="Moving Average and Stochastic RSI Indicator", shorttitle="MA+Stoch RSI", overlay=true)
// Input variables
ma1_length = input(title="MA1 Length", type=input.integer, defval=20, minval=1)
ma2_length = input(title="MA2 Length", type=input.integer, defval=50, minval=1)
stoch_length = input(title="Stochastic RSI Length", type=input.integer, defval=14, minval=1)
overbought = input(title="Overbought Level", type=input.integer, defval=80)
oversold = input(title="Oversold Level", type=input.integer, defval=20)
// Calculate moving averages
ma1 = sma(close, ma1_length)
ma2 = sma(close, ma2_length)
// Calculate Stochastic RSI
rsi1 = rsi(close, stoch_length)
rsiH = highest(rsi1, stoch_length)
rsiL = lowest(rsi1, stoch_length)
stoch = (rsi1 - rsiL) / (rsiH - rsiL) * 100
// Determine trend direction based on MA crossover
trendUp = ma1 > ma2 ? true : false
trendDown = ma1 < ma2 ? true : false
// Keep track of current trend direction
var currentTrendUp = trendUp
var currentTrendDown = trendDown
// Determine buy and sell signals based on Stochastic RSI
buySignal = false
sellSignal = false
if trendUp and not currentTrendUp and crossover(stoch, oversold)
buySignal := true
currentTrendUp := true
else if trendDown and not currentTrendDown and crossunder(stoch, overbought)
sellSignal := true
currentTrendDown := true
// Reset trend direction if moving averages cross
if not trendUp and currentTrendUp or not trendDown and currentTrendDown
currentTrendUp := trendUp
currentTrendDown := trendDown
// Plot signals on chart
plotshape(buySignal, style=shape.arrowup, location=location.belowbar, color=color.green, size=size.small, text="Buy")
plotshape(sellSignal, style=shape.arrowdown, location=location.abovebar, color=color.red, size=size.small, text="Sell")
// Plot moving averages on chart
plot(ma1, color=color.blue)
plot(ma2, color=color.orange)
I advised ChatGPT of the issue once again. And was more clear in what I wanted.
This time, GPT was successful in solving the issue and the code was working exactly how I wanted it to. As you can see, one of the major challenges with using GPT to generate code is clearly articulating what you want it to do and limiting the number of iterations and changes it makes to the code. Additionally, providing feedback on what it is doing right and wrong is crucial in achieving the desired outcome.
//version=4
study(title="Moving Average and Stochastic RSI Indicator", shorttitle="MA+Stoch RSI", overlay=true)
// Input variables
ma1_length = input(title="MA1 Length", type=input.integer, defval=20, minval=1)
ma2_length = input(title="MA2 Length", type=input.integer, defval=50, minval=1)
stoch_length = input(title="Stochastic RSI Length", type=input.integer, defval=14, minval=1)
overbought = input(title="Overbought Level", type=input.integer, defval=80)
oversold = input(title="Oversold Level", type=input.integer, defval=20)
// Calculate moving averages
ma1 = sma(close, ma1_length)
ma2 = sma(close, ma2_length)
// Calculate Stochastic RSI
rsi1 = rsi(close, stoch_length)
rsiH = highest(rsi1, stoch_length)
rsiL = lowest(rsi1, stoch_length)
stoch = (rsi1 - rsiL) / (rsiH - rsiL) * 100
// Initialize trend direction and signal variables
var trendUp = ma1 > ma2 ? true : false
var trendDown = ma1 < ma2 ? true : false
var signalUp = false
var signalDown = false
// Determine trend direction based on MA crossover
if ma1 > ma2
trendUp := true
trendDown := false
else
trendUp := false
trendDown := true
// Determine buy and sell signals based on Stochastic RSI
buySignal = false
sellSignal = false
if trendUp and crossover(stoch, oversold) and not signalUp
buySignal := true
signalUp := true
signalDown := false
else if trendDown and crossunder(stoch, overbought) and not signalDown
sellSignal := true
signalUp := false
signalDown := true
// Plot signals on chart
plotshape(buySignal, style=shape.arrowup, location=location.belowbar, color=color.green, size=size.small, text="Buy")
plotshape(sellSignal, style=shape.arrowdown, location=location.abovebar, color=color.red, size=size.small, text="Sell")
// Plot moving averages on chart
plot(ma1, color=color.blue)
plot(ma2, color=color.orange)
6: With our indicator now functioning properly, we can move on to the next step of converting it into a strategy for testing on Tradingview. To accomplish this, we'll need to establish specific take profit and stop loss criteria I've decided to use the price of the slow moving average as the exit of the trades. Which will also act as a trailing stop loss
//version=4
strategy("MA+Stoch RSI Strategy", overlay=true)
// Input variables
ma1_length = input(title="MA1 Length", type=input.integer, defval=20, minval=1)
ma2_length = input(title="MA2 Length", type=input.integer, defval=50, minval=1)
stoch_length = input(title="Stochastic RSI Length", type=input.integer, defval=14, minval=1)
overbought = input(title="Overbought Level", type=input.integer, defval=80)
oversold = input(title="Oversold Level", type=input.integer, defval=20)
// Calculate moving averages
ma1 = sma(close, ma1_length)
ma2 = sma(close, ma2_length)
// Calculate Stochastic RSI
rsi1 = rsi(close, stoch_length)
rsiH = highest(rsi1, stoch_length)
rsiL = lowest(rsi1, stoch_length)
stoch = (rsi1 - rsiL) / (rsiH - rsiL) * 100
// Determine trend direction based on MA crossover
trendUp = ma1 > ma2 ? true : false
trendDown = ma1 < ma2 ? true : false
// Initialize flag variables
var hasBoughtSignal = false
var hasSoldSignal = false
// Generate signals
if trendUp and crossover(stoch, oversold) and not hasBoughtSignal
strategy.entry("Buy", strategy.long)
hasBoughtSignal := true
hasSoldSignal := false
if trendDown and crossunder(stoch, overbought) and not hasSoldSignal
strategy.entry("Sell", strategy.short)
hasBoughtSignal := false
hasSoldSignal := true
// Set stop loss and take profit levels
if strategy.position_size != 0
if strategy.position_size > 0
strategy.exit("StopLoss", "Buy", stop=ma2, qty_percent=100)
strategy.exit("TakeProfit", "Sell", limit=close - (ma2 - close), qty_percent=100)
else
strategy.exit("StopLoss", "Sell", stop=ma2, qty_percent=100)
strategy.exit("TakeProfit", "Buy", limit=close + (close - ma2), qty_percent=100)
// Plot moving averages on chart
plot(ma1, color=color.blue)
plot(ma2, color=color.orange)
And that's it! Our code is complete. The final step is to convert it to version 5
And here is the final code
//version=5
strategy('MA+Stoch RSI Strategy', overlay=true)
// Input variables
ma1_length = input.int(title='MA1 Length', defval=20, minval=1)
ma2_length = input.int(title='MA2 Length', defval=50, minval=1)
stoch_length = input.int(title='Stochastic RSI Length', defval=14, minval=1)
overbought = input(title='Overbought Level', defval=80)
oversold = input(title='Oversold Level', defval=20)
// Calculate moving averages
ma1 = ta.sma(close, ma1_length)
ma2 = ta.sma(close, ma2_length)
// Calculate Stochastic RSI
rsi1 = ta.rsi(close, stoch_length)
rsiH = ta.highest(rsi1, stoch_length)
rsiL = ta.lowest(rsi1, stoch_length)
stoch = (rsi1 - rsiL) / (rsiH - rsiL) * 100
// Determine trend direction based on MA crossover
trendUp = ma1 > ma2 ? true : false
trendDown = ma1 < ma2 ? true : false
// Initialize flag variables
var hasBoughtSignal = false
var hasSoldSignal = false
// Generate signals
if trendUp and ta.crossover(stoch, oversold) and not hasBoughtSignal
strategy.entry('Buy', strategy.long)
hasBoughtSignal := true
hasSoldSignal := false
hasSoldSignal
if trendDown and ta.crossunder(stoch, overbought) and not hasSoldSignal
strategy.entry('Sell', strategy.short)
hasBoughtSignal := false
hasSoldSignal := true
hasSoldSignal
// Set stop loss and take profit levels
if strategy.position_size != 0
if strategy.position_size > 0
strategy.exit('StopLoss', 'Buy', stop=ma2, qty_percent=100)
strategy.exit('TakeProfit', 'Sell', limit=close - (ma2 - close), qty_percent=100)
else
strategy.exit('StopLoss', 'Sell', stop=ma2, qty_percent=100)
strategy.exit('TakeProfit', 'Buy', limit=close + close - ma2, qty_percent=100)
// Plot moving averages on chart
plot(ma1, color=color.new(color.blue, 0))
plot(ma2, color=color.new(color.orange, 0))
🔸I will also publish this script along with this article for others to use. However, I want to stress that this is not a guaranteed profitable system and users should use it at their own risk. This tutorial is simply an example of how to use ChatGPT to create your own script and test it.
🔸While using ChatGPT, you may encounter some issues, such as incomplete responses due to word limits. In such cases, you can refer to the end of the code and ask ChatGPT to provide only the additional part of the response. Additionally, the longer the chat history, the more likely you may encounter issues as GPT makes more modifications to the code. Therefore, it's important to limit the number of changes and provide clear feedback to help GPT understand your desired outcome. You may sometimes need to start a new chat if having many issues.
🔸Another way to utilize GPT for more complex tasks, especially when you already have programming knowledge, is to use it to brainstorm solutions for specific issues instead of writing the code. For example, if you're working with multiple timeframes, GPT may be unable to generate the code for you, but it can help you come up with ideas and potential solutions to the problem. Here is an example below :
In this article, we will focus on using the free version of ChatGPT to code Pinescript indicators and strategies. We'll provide step-by-step instructions, highlighting potential issues you may encounter and how to resolve them. By the end of this article, you'll have the tools you need to leverage ChatGPT to create profitable trading strategies.
So, whether you're an experienced trader or just starting out, read on to discover how you can use ChatGPT to revolutionize your Pinescript coding, and even explore the other exciting possibilities it offers.
Things to know before we continue
💡ChatGPT can generate Pinescript code for both versions 4 and 5, but it's important to note that there are some differences between the two versions. It's recommended to specify which version you want your code written in before using ChatGPT. Additionally, it's worth noting that ChatGPT has more knowledge of Pinescript version 4, so you may want to consider having it write code in version 4 and then use the Tradingview editor to convert it to version 5.
💡It's true that ChatGPT can help you generate Pinescript code without extensive coding knowledge. However, for more complex scripts, it's recommended to have a basic understanding of Pinescript to make the most of ChatGPT. That way, you can better understand the generated code and make adjustments as needed.
💡ChatGPT is a tool that can help you improve your Pinescript coding, not a replacement for it. It's best to use ChatGPT to solve specific issues or come up with solutions for certain parts of your code rather than relying on it to write the entire code for you.
WHAT WE WILL BE CODING FOR OUR FIRST EXAMPLE.
🔸In our example, we will be coding an indicator that uses two moving averages with exposed periods to determine the direction of the market. Additionally, we will be using the stochastic RSI indicator as a momentum indicator to determine when to buy in an uptrend and when to sell in a downtrend. After we have created this script as an indicator, we will use ChatGPT to convert it to a strategy. This will enable us to backtest it using the Tradingview backtesting framework.
Lets begin.
1: The first thing we want to do is let CHatGPT know exactly what we want it to do. And have it come up with a solution to the issue. For our example we are going to type the following below.
Note how I specified the version of pinescript we will be coding in.
2: I am going to let ChatGPT know the description of the indicator we are going to code
🔸As you can see, ChatGPT provided me with Pinescript based on the information I provided. It is worth noting that, while this code worked for me, others may receive slightly different code due to the nature of ChatGPT's predictions. Additionally, ChatGPT explained the code in further detail in its response. Our next step is to test the code to determine whether it meets our requirements, and to note any issues we encounter. If there are any issues, we will provide them to ChatGPT for further assistance. To begin, I will copy and paste the generated code into the Pinescript editor without making any modifications, and attempt to add the script to the chart.
For reference here is the code provided by GPT below :
//version=4
study(title="Moving Average and Stochastic RSI Indicator", shorttitle="MA+Stoch RSI", overlay=false)
// Input variables
ma1_length = input(title="MA1 Length", type=input.integer, defval=20, minval=1)
ma2_length = input(title="MA2 Length", type=input.integer, defval=50, minval=1)
stoch_length = input(title="Stochastic RSI Length", type=input.integer, defval=14, minval=1)
overbought = input(title="Overbought Level", type=input.integer, defval=80)
oversold = input(title="Oversold Level", type=input.integer, defval=20)
// Calculate moving averages
ma1 = sma(close, ma1_length)
ma2 = sma(close, ma2_length)
// Calculate Stochastic RSI
rsi1 = rsi(close, stoch_length)
rsiH = highest(rsi1, stoch_length)
rsiL = lowest(rsi1, stoch_length)
stoch = (rsi1 - rsiL) / (rsiH - rsiL) * 100
// Determine trend direction based on MA crossover
trendUp = ma1 > ma2 ? true : false
trendDown = ma1 < ma2 ? true : false
// Determine buy and sell signals based on Stochastic RSI
buySignal = trendUp and crossover(stoch, oversold)
sellSignal = trendDown and crossunder(stoch, overbought)
// Plot signals on chart
plotshape(buySignal, style=shape.arrowup, location=location.belowbar, color=color.green, size=size.small, text="Buy")
plotshape(sellSignal, style=shape.arrowdown, location=location.abovebar, color=color.red, size=size.small, text="Sell")
🔸The code had no syntax errors and met all the requirements specified in my prompt. The periods for the moving averages and the stochastic RSI were exposed, allowing them to be adjusted as needed. However, there is one issue that is not a result of ChatGPT, but rather caused by my failure to specify it in the prompt. The indicator is not being overlaid on the chart and is instead being displayed as an oscillator in a separate window below, similar to the RSI indicator. However, for our purposes, we want the indicator to be displayed over the candles themselves.
3: After testing the code and verifying that it meets my requirements, I will provide feedback to GPT that the code is functioning properly. However, I will also request that the indicator be displayed over the candles instead of in a separate window. It's important to communicate clearly with GPT to avoid any unnecessary changes to the code.
🔸Now we will test the code again.
Updated code listed below
//version=4
study(title="Moving Average and Stochastic RSI Indicator", shorttitle="MA+Stoch RSI", overlay=true)
// Input variables
ma1_length = input(title="MA1 Length", type=input.integer, defval=20, minval=1)
ma2_length = input(title="MA2 Length", type=input.integer, defval=50, minval=1)
stoch_length = input(title="Stochastic RSI Length", type=input.integer, defval=14, minval=1)
overbought = input(title="Overbought Level", type=input.integer, defval=80)
oversold = input(title="Oversold Level", type=input.integer, defval=20)
// Calculate moving averages
ma1 = sma(close, ma1_length)
ma2 = sma(close, ma2_length)
// Calculate Stochastic RSI
rsi1 = rsi(close, stoch_length)
rsiH = highest(rsi1, stoch_length)
rsiL = lowest(rsi1, stoch_length)
stoch = (rsi1 - rsiL) / (rsiH - rsiL) * 100
// Determine trend direction based on MA crossover
trendUp = ma1 > ma2 ? true : false
trendDown = ma1 < ma2 ? true : false
// Determine buy and sell signals based on Stochastic RSI
buySignal = trendUp and crossover(stoch, oversold)
sellSignal = trendDown and crossunder(stoch, overbought)
// Plot signals on chart
plotshape(buySignal, style=shape.arrowup, location=location.belowbar, color=color.green, size=size.small, text="Buy")
plotshape(sellSignal, style=shape.arrowdown, location=location.abovebar, color=color.red, size=size.small, text="Sell")
🔸Great. Now the code is displaying as we would want it to as well!.
4: Now, let's make some improvements to the code. In addition to generating buy and sell signals, I would also like to see the moving averages displayed on the chart. This will allow me to visually understand why the signals are being generated.
Code reference below:
//version=4
study(title="Moving Average and Stochastic RSI Indicator", shorttitle="MA+Stoch RSI", overlay=true)
// Input variables
ma1_length = input(title="MA1 Length", type=input.integer, defval=20, minval=1)
ma2_length = input(title="MA2 Length", type=input.integer, defval=50, minval=1)
stoch_length = input(title="Stochastic RSI Length", type=input.integer, defval=14, minval=1)
overbought = input(title="Overbought Level", type=input.integer, defval=80)
oversold = input(title="Oversold Level", type=input.integer, defval=20)
// Calculate moving averages
ma1 = sma(close, ma1_length)
ma2 = sma(close, ma2_length)
// Calculate Stochastic RSI
rsi1 = rsi(close, stoch_length)
rsiH = highest(rsi1, stoch_length)
rsiL = lowest(rsi1, stoch_length)
stoch = (rsi1 - rsiL) / (rsiH - rsiL) * 100
// Determine trend direction based on MA crossover
trendUp = ma1 > ma2 ? true : false
trendDown = ma1 < ma2 ? true : false
// Determine buy and sell signals based on Stochastic RSI
buySignal = trendUp and crossover(stoch, oversold)
sellSignal = trendDown and crossunder(stoch, overbought)
// Plot signals on chart
plotshape(buySignal, style=shape.arrowup, location=location.belowbar, color=color.green, size=size.small, text="Buy")
plotshape(sellSignal, style=shape.arrowdown, location=location.abovebar, color=color.red, size=size.small, text="Sell")
// Plot moving averages on chart
plot(ma1, color=color.blue)
plot(ma2, color=color.orange)
🔸Great! Now that we can see the moving averages, we have a better understanding of why the buy and sell signals are being generated. However, before we convert the indicator into a strategy, we need to make one final adjustment: reducing the number of signals being generated. There are various ways to achieve this such as using an ADX filter or a volatility filter. However, for this example, we will simply limit the number of signals generated for each cross of the moving averages to 1.
5: Final adjustments, During the tutorial, ChatGPT crashed, which can happen from time to time. If this happens, simply create a new chat session, copy the code from PineScript, and ask ChatGPT what the script does. Once ChatGPT advises you, you can ask it to act as an expert and help you make any necessary adjustments to the code in PineScript version 4.
🔸Here is when we started to have issues.
Here is my prompt and here is the code provided by ChatGPT
//version=4
study(title="Moving Average and Stochastic RSI Indicator", shorttitle="MA+Stoch RSI", overlay=true)
// Input variables
ma1_length = input(title="MA1 Length", type=input.integer, defval=20, minval=1)
ma2_length = input(title="MA2 Length", type=input.integer, defval=50, minval=1)
stoch_length = input(title="Stochastic RSI Length", type=input.integer, defval=14, minval=1)
overbought = input(title="Overbought Level", type=input.integer, defval=80)
oversold = input(title="Oversold Level", type=input.integer, defval=20)
// Calculate moving averages
ma1 = sma(close, ma1_length)
ma2 = sma(close, ma2_length)
// Calculate Stochastic RSI
rsi1 = rsi(close, stoch_length)
rsiH = highest(rsi1, stoch_length)
rsiL = lowest(rsi1, stoch_length)
stoch = (rsi1 - rsiL) / (rsiH - rsiL) * 100
// Initialize buy and sell signals to false
var buySignal = false
var sellSignal = false
// Determine trend direction based on MA crossover
trendUp = ma1 > ma2 ? true : false
trendDown = ma1 < ma2 ? true : false
// Generate buy signal if a signal has not already been generated and the conditions are met
if trendUp and crossover(stoch, oversold) and not buySignal
buySignal := true
// Generate sell signal if a signal has not already been generated and the conditions are met
if trendDown and crossunder(stoch, overbought) and not sellSignal
sellSignal := true
// Plot signals on chart
plotshape(buySignal, style=shape.arrowup, location=location.belowbar, color=color.green, size=size.small, text="Buy")
plotshape(sellSignal, style=shape.arrowdown, location=location.abovebar, color=color.red, size=size.small, text="Sell")
// Reset buy and sell signals if a new trend develops
if trendUp and sellSignal
sellSignal := false
if trendDown and buySignal
buySignal := false
// Plot moving averages on chart
plot(ma1, color=color.blue)
plot(ma2, color=color.orange)
🔸Once I inputted the code provided I started to get a signal for every candle which is not what we wanted.
So I advised GPT of the issue.
It then attempted to solve the issue but instead it modified the code to only generate a buy signal or sell signal if the moving averages and the stochastic conditions where met all AT THE SAME TIME, Resulting in little to no signals.
//version=4
study(title="Moving Average and Stochastic RSI Indicator", shorttitle="MA+Stoch RSI", overlay=true)
// Input variables
ma1_length = input(title="MA1 Length", type=input.integer, defval=20, minval=1)
ma2_length = input(title="MA2 Length", type=input.integer, defval=50, minval=1)
stoch_length = input(title="Stochastic RSI Length", type=input.integer, defval=14, minval=1)
overbought = input(title="Overbought Level", type=input.integer, defval=80)
oversold = input(title="Oversold Level", type=input.integer, defval=20)
// Calculate moving averages
ma1 = sma(close, ma1_length)
ma2 = sma(close, ma2_length)
// Calculate Stochastic RSI
rsi1 = rsi(close, stoch_length)
rsiH = highest(rsi1, stoch_length)
rsiL = lowest(rsi1, stoch_length)
stoch = (rsi1 - rsiL) / (rsiH - rsiL) * 100
// Determine trend direction based on MA crossover
trendUp = ma1 > ma2 ? true : false
trendDown = ma1 < ma2 ? true : false
// Keep track of current trend direction
var currentTrendUp = trendUp
var currentTrendDown = trendDown
// Determine buy and sell signals based on Stochastic RSI
buySignal = false
sellSignal = false
if trendUp and not currentTrendUp and crossover(stoch, oversold)
buySignal := true
currentTrendUp := true
else if trendDown and not currentTrendDown and crossunder(stoch, overbought)
sellSignal := true
currentTrendDown := true
// Reset trend direction if moving averages cross
if not trendUp and currentTrendUp or not trendDown and currentTrendDown
currentTrendUp := trendUp
currentTrendDown := trendDown
// Plot signals on chart
plotshape(buySignal, style=shape.arrowup, location=location.belowbar, color=color.green, size=size.small, text="Buy")
plotshape(sellSignal, style=shape.arrowdown, location=location.abovebar, color=color.red, size=size.small, text="Sell")
// Plot moving averages on chart
plot(ma1, color=color.blue)
plot(ma2, color=color.orange)
I advised ChatGPT of the issue once again. And was more clear in what I wanted.
This time, GPT was successful in solving the issue and the code was working exactly how I wanted it to. As you can see, one of the major challenges with using GPT to generate code is clearly articulating what you want it to do and limiting the number of iterations and changes it makes to the code. Additionally, providing feedback on what it is doing right and wrong is crucial in achieving the desired outcome.
//version=4
study(title="Moving Average and Stochastic RSI Indicator", shorttitle="MA+Stoch RSI", overlay=true)
// Input variables
ma1_length = input(title="MA1 Length", type=input.integer, defval=20, minval=1)
ma2_length = input(title="MA2 Length", type=input.integer, defval=50, minval=1)
stoch_length = input(title="Stochastic RSI Length", type=input.integer, defval=14, minval=1)
overbought = input(title="Overbought Level", type=input.integer, defval=80)
oversold = input(title="Oversold Level", type=input.integer, defval=20)
// Calculate moving averages
ma1 = sma(close, ma1_length)
ma2 = sma(close, ma2_length)
// Calculate Stochastic RSI
rsi1 = rsi(close, stoch_length)
rsiH = highest(rsi1, stoch_length)
rsiL = lowest(rsi1, stoch_length)
stoch = (rsi1 - rsiL) / (rsiH - rsiL) * 100
// Initialize trend direction and signal variables
var trendUp = ma1 > ma2 ? true : false
var trendDown = ma1 < ma2 ? true : false
var signalUp = false
var signalDown = false
// Determine trend direction based on MA crossover
if ma1 > ma2
trendUp := true
trendDown := false
else
trendUp := false
trendDown := true
// Determine buy and sell signals based on Stochastic RSI
buySignal = false
sellSignal = false
if trendUp and crossover(stoch, oversold) and not signalUp
buySignal := true
signalUp := true
signalDown := false
else if trendDown and crossunder(stoch, overbought) and not signalDown
sellSignal := true
signalUp := false
signalDown := true
// Plot signals on chart
plotshape(buySignal, style=shape.arrowup, location=location.belowbar, color=color.green, size=size.small, text="Buy")
plotshape(sellSignal, style=shape.arrowdown, location=location.abovebar, color=color.red, size=size.small, text="Sell")
// Plot moving averages on chart
plot(ma1, color=color.blue)
plot(ma2, color=color.orange)
6: With our indicator now functioning properly, we can move on to the next step of converting it into a strategy for testing on Tradingview. To accomplish this, we'll need to establish specific take profit and stop loss criteria I've decided to use the price of the slow moving average as the exit of the trades. Which will also act as a trailing stop loss
//version=4
strategy("MA+Stoch RSI Strategy", overlay=true)
// Input variables
ma1_length = input(title="MA1 Length", type=input.integer, defval=20, minval=1)
ma2_length = input(title="MA2 Length", type=input.integer, defval=50, minval=1)
stoch_length = input(title="Stochastic RSI Length", type=input.integer, defval=14, minval=1)
overbought = input(title="Overbought Level", type=input.integer, defval=80)
oversold = input(title="Oversold Level", type=input.integer, defval=20)
// Calculate moving averages
ma1 = sma(close, ma1_length)
ma2 = sma(close, ma2_length)
// Calculate Stochastic RSI
rsi1 = rsi(close, stoch_length)
rsiH = highest(rsi1, stoch_length)
rsiL = lowest(rsi1, stoch_length)
stoch = (rsi1 - rsiL) / (rsiH - rsiL) * 100
// Determine trend direction based on MA crossover
trendUp = ma1 > ma2 ? true : false
trendDown = ma1 < ma2 ? true : false
// Initialize flag variables
var hasBoughtSignal = false
var hasSoldSignal = false
// Generate signals
if trendUp and crossover(stoch, oversold) and not hasBoughtSignal
strategy.entry("Buy", strategy.long)
hasBoughtSignal := true
hasSoldSignal := false
if trendDown and crossunder(stoch, overbought) and not hasSoldSignal
strategy.entry("Sell", strategy.short)
hasBoughtSignal := false
hasSoldSignal := true
// Set stop loss and take profit levels
if strategy.position_size != 0
if strategy.position_size > 0
strategy.exit("StopLoss", "Buy", stop=ma2, qty_percent=100)
strategy.exit("TakeProfit", "Sell", limit=close - (ma2 - close), qty_percent=100)
else
strategy.exit("StopLoss", "Sell", stop=ma2, qty_percent=100)
strategy.exit("TakeProfit", "Buy", limit=close + (close - ma2), qty_percent=100)
// Plot moving averages on chart
plot(ma1, color=color.blue)
plot(ma2, color=color.orange)
And that's it! Our code is complete. The final step is to convert it to version 5
And here is the final code
//version=5
strategy('MA+Stoch RSI Strategy', overlay=true)
// Input variables
ma1_length = input.int(title='MA1 Length', defval=20, minval=1)
ma2_length = input.int(title='MA2 Length', defval=50, minval=1)
stoch_length = input.int(title='Stochastic RSI Length', defval=14, minval=1)
overbought = input(title='Overbought Level', defval=80)
oversold = input(title='Oversold Level', defval=20)
// Calculate moving averages
ma1 = ta.sma(close, ma1_length)
ma2 = ta.sma(close, ma2_length)
// Calculate Stochastic RSI
rsi1 = ta.rsi(close, stoch_length)
rsiH = ta.highest(rsi1, stoch_length)
rsiL = ta.lowest(rsi1, stoch_length)
stoch = (rsi1 - rsiL) / (rsiH - rsiL) * 100
// Determine trend direction based on MA crossover
trendUp = ma1 > ma2 ? true : false
trendDown = ma1 < ma2 ? true : false
// Initialize flag variables
var hasBoughtSignal = false
var hasSoldSignal = false
// Generate signals
if trendUp and ta.crossover(stoch, oversold) and not hasBoughtSignal
strategy.entry('Buy', strategy.long)
hasBoughtSignal := true
hasSoldSignal := false
hasSoldSignal
if trendDown and ta.crossunder(stoch, overbought) and not hasSoldSignal
strategy.entry('Sell', strategy.short)
hasBoughtSignal := false
hasSoldSignal := true
hasSoldSignal
// Set stop loss and take profit levels
if strategy.position_size != 0
if strategy.position_size > 0
strategy.exit('StopLoss', 'Buy', stop=ma2, qty_percent=100)
strategy.exit('TakeProfit', 'Sell', limit=close - (ma2 - close), qty_percent=100)
else
strategy.exit('StopLoss', 'Sell', stop=ma2, qty_percent=100)
strategy.exit('TakeProfit', 'Buy', limit=close + close - ma2, qty_percent=100)
// Plot moving averages on chart
plot(ma1, color=color.new(color.blue, 0))
plot(ma2, color=color.new(color.orange, 0))
🔸I will also publish this script along with this article for others to use. However, I want to stress that this is not a guaranteed profitable system and users should use it at their own risk. This tutorial is simply an example of how to use ChatGPT to create your own script and test it.
🔸While using ChatGPT, you may encounter some issues, such as incomplete responses due to word limits. In such cases, you can refer to the end of the code and ask ChatGPT to provide only the additional part of the response. Additionally, the longer the chat history, the more likely you may encounter issues as GPT makes more modifications to the code. Therefore, it's important to limit the number of changes and provide clear feedback to help GPT understand your desired outcome. You may sometimes need to start a new chat if having many issues.
🔸Another way to utilize GPT for more complex tasks, especially when you already have programming knowledge, is to use it to brainstorm solutions for specific issues instead of writing the code. For example, if you're working with multiple timeframes, GPT may be unable to generate the code for you, but it can help you come up with ideas and potential solutions to the problem. Here is an example below :
Note
If there are issues copying the final code to your chart this is due to the fact that the indentation of the if statements are being copied incorrectly. When you copy the if statements should look as shown below.
C Nicholas Downie
Disclaimer
The information and publications are not meant to be, and do not constitute, financial, investment, trading, or other types of advice or recommendations supplied or endorsed by TradingView. Read more in the Terms of Use.
C Nicholas Downie
Disclaimer
The information and publications are not meant to be, and do not constitute, financial, investment, trading, or other types of advice or recommendations supplied or endorsed by TradingView. Read more in the Terms of Use.