2023-04-12

The article discusses a trading strategy to turn $100 into $10,000 quickly by using an AI-based trading view indicator called “Machine Learning.” The strategy includes three free trading view tools, namely, the Machine Learning K-Nearest Neighbor (KNN), Exponential Moving Averages (EMA) Ribbon, and Relative Strength Index (RSI). The KNN strategy works by analyzing historical market data and predicting the direction of future price movements based on patterns in the data. The EMA ribbon is used to identify the direction and strength of a trend in the market, while the RSI is used to measure the strength of a securities price action. The strategy requires the price to be closed above the 200 EMA and the ribbon to be above the 200 EMA and be green. The price must pull back into the ribbon without closing below the long-term EMA. The machine learning strategy must print a blue label, and the RSI must be oversold before the buy signal. Once these conditions are met, the trader can open a long trade, set the stop loss below the recent swing low, and target two times the risk. The stop loss should be adjusted to the break-even price once a quarter of the profit has been made. The strategy has been tested on Ethereum's price on a three-minute time frame.

I recently asked chat GPT to give me a trading strategy to turn $100 into $10,000 quickly.

It gave me the typical tips like “focus on highly volatile assets”  and “use technical analysis”. 

Things we all know already...nothing specific. I decided to be more specific with my question.

I asked it to create the best strategy using an AI based trading view indicator called “machine learning”. This indicator is all the rage these days. I also mentioned that the strategy's goal is to turn $100 ito $10,000  in the shortest amount of time possible. This time it provided me with a detailed strategy. It wasn't really perfect so I had to make some tweaks of my own.

The Final Setup 

To check if the strategy actually works I will test it 100 times for that I will use the price of Ethereum on a three minute time frame.Before I do that however, let's actually open the charts and add the indicators. The strategy includes three free trading view tools. I will explain how each indicator works as we add them one by one.

Indicator #1  Machine Learning K-Nearest Neighbor (KNN)

Let's add the machine learning KNN based strategy. This indicator was created by Capissimo (https://www.tradingview.com/u/capissimo/). This machine learning strategy works by analyzing historical market data and predicting the direction of future price movements based on patterns in the data. KNN is a classification algorithm that determines the class of a data point based on its nearest neighbors in a feature space. In the context of trading KNN can be used to classify whether a stock price is likely to go up or down based on its historical data. To use KNN for trading, historical price data is first collected and transformed into a Feature Vector. The Feature Vector can include technical indicators such as Moving Averages,  Relative Strength Index (RSI), and Momentum Indicators. The KNN algorithm is then applied to the Feature Vectors to classify whether the stock price is likely to increase or decrease. This indicator is not repainting however you do have to wait for the candle bar to close before you can consider a signal to be valid. It’s also very simple to read because the indicator prints blue and pink labels which are buy and sell signals.

Indicator #2  Exponential Moving Averages (EMA) 

Depending on the strength of the signals, the labels may have lower or higher opacity. Obviously we can’t use this indicator on its own as this will lead to a lot of false signals. For this reason we must add the next indicator which is called the EMA ribbon by Domenico Silletti (https://www.tradingview.com/u/domenicosilletti/). The Exponential Moving Averages ribbon is a trading indicator that consists of multiple Exponential Moving Averages (EMA) plotted on a price chart. This tool is used to identify the direction and strength of a trend in the market. The EMA ribbon is created by plotting several EMAs with different time periods. The moving averages are then stacked on top of each other creating a ribbon-like appearance on the chart. When the ribbon is sloping upwards it indicates that the market is an uptrend. When the ribbon is sloping downwards it indicates that the market is in a downtrend. The EMA ribbon will help us identify potential buy or sell signals based on the direction of the trend and the location of the price relative to the moving averages. As we can see this EMA ribbon indicator comes with buy and sell signals. Since we already have a buy and sell indicator on the chart which is the “Machine Learning”, let's go ahead and disable those EMA ribbon signals.

Indicator #3  Relative Strength Index (RSI) 

If we take a look at the chart we can see that this indicator does filter out a lot of fake signals but there are still some left. That's why chatGPT suggested using their Relative Strength Index as secondary confirmation. As you probably know the RSI is used in trading to measure the strength of a Securities price action. It is displayed as a line on a chart that ranges from 0 to 100. When the RSI is above 70 it is generally considered overbought and when it is below 30 it is generally considered oversold. As part of our strategy we will make the RSI more sensitive in order to get more valid trade entries. Open the style of the indicator and change the RSI upper band to 60 and the RSI lower band to 40. 

The Entry Conditions

Now that the setup is complete, let's move on to the entry conditions. For a long trade the following must be met first:

• the price must be closed above the 200 EMA 
• the ribbon must also be above the 200 EMA
• in addition it must be green 

Secondly,  the price must pull back into the ribbon without closing below the long-term EMA. The machine learning strategy must then print a blue label. Lastly the RSI must be oversold prior to the Buy Signal. As soon as these conditions are met you can open a long trade.

Set the stop loss below the recent swing low. Target two times the risk. Once you have made a quarter of the profit, adjust the stop loss to the break-even price. For example, you risk 5% of your account per trade in order to make 10%. The price moves in your direction and the unrealized profit is running at 2.5% which is a quarter of your target. As soon as that happen, adjust the stop loss and secure the trade.

Here's one more example just so you fully understand the strategy. We can see that the price is in a clear up trend. The RSI became oversold which signals that we can purchase the security at a discounted price. Then the machine learning prints a buy label. We follow the rules and execute the trade. Do the opposite for short trades. First wait until the price and the ribbon fall below the 200 EMA. The ribbon must become red. The price must pull back into the ribbon without closing above the 200 EMA. The RSI must become overbought during the pullback. After that wait for machine learning to give a final confirmation.

There is one more important note I forgot to mention. Do not enter the trade if the RSI turns oversold. At a time the cell signal was issued open a short trade only. 

if all the rules are in place. Set the stop loss above the recent swing high and target 2X the risk.

Move the stop loss to the break even once a quarter of the profit is made.

Testing The Results

Ok now once we know the rules, let's move on to the back testing results. So the starting account balance was set at $100 and after 100 trades the strategy increased it to $19,527. I find it funny that the strategies one ratio isn't even the highest out of all the strategies I've tested so far. The truth is this particular strategy involves a bit higher risk than the usual strategy you might find on my channel. You've probably noticed by now that the risk per trade was set at 5% instead of 2%. It's no secret that such risk involves higher drawdowns but it also gives you a higher reward. By no means am I saying that you should risk 5% of your account per trade (especially if you have a bigger account). However, if your goal is to grow a small account quickly, this risk per trade may be acceptable. So give the strategy a try but don't skip the forward testing phase on a paper account. I can't stress enough how important it is.

Parker Renjiro is a renowned online entrepreneur, digital marketer, and business coach who has helped thousands of people worldwide achieve financial freedom through his proven methods and strategies. With over a decade of experience in the online business world, Parker has built multiple successful online ventures from scratch and has generated millions of dollars in revenue.