Trade Crypto With AI

Crypto + ChatGPT

Crypto + ChatGPT

Type your trading strategy in words and our AI will turn it into an algorithmic trading bot and run a backtest to show if it would have been historically profitable.

Some Guidelines:


Basic Strategy Example: "Buy AAPL when the price goes down 5 times in a row". You can use either the stock symbol or company name. And you can choose from 100+ technical indicators (see the list at the bottom of this page).

Stock Data: Daily prices from US stock exchanges (NYSE and NASDAQ).

Order Entries: Your trade is entered at the market close. In our 40+ years of stock backtesting experience (starting back when it was done without computers), we have never seen the benefit of waiting until the next day to enter a trade like most backtesting programs do. If, for example, your strategy is "buy AAPL after it goes down 4 days in a row", that streak indicator is calculated at the end of the current bar (the closing price for the day). If it then enters the trade when the market opens tomorrow (the typical method) there is a good chance the price will be significantly different from when the trade was triggered. If AAPL already went up overnight, the "4 down days in a row" indicator in your strategy would no longer be valid and you would have missed your opportunity for profits.

Instead, by entering the trade at the exact same time the indicators for your strategy are calculated, it is a more scientific test of your strategy because it eliminates the randomness of waiting until after the overnight move. One reason backtesting programs generally delay the order until the next bar (in our case, the next day), is that it is technically impossible to place the trade at the exact same time you are supposed to be calculating the indicators. But the reality is that nowadays all stock brokers give you data by the minute (or even by the second or tick. That means even though your strategy is daily, you could calculate your indicators a few seconds before the market closes and then execute the order at the close, just as our backtester does.

Order Exits: It exits at the market close once your strategy triggers it. If no exit is specified, it automatically exits the next trading day (no weekends or market holidays). You can either specify to exit after a certain number of days, or use a stop loss/take profit strategy such as "Exit the trade after it goes down 20%."

AI-Powered Trading Signals: Uses a LightGBM machine learning model to predict if the stock will go up or down. Example AI strategies include:

Buy GOOG when the AI says to buy it.

Buy AMZN when the price goes up by 1% or more, but only if AI also agrees.


Advanced Strategy Examples:

Buy MSFT when the price goes down exactly 5 times in a row, sell short MSFT when the price goes up exactly 5 times in a row.

Buy DIS on Tuesdays when you also see an Evening Doji Star.

Sell Short TSLA when both the RSI and ADX suggest it's time to do so.

Buy MCD when the RSI, ADX, and average true range combined suggest it's time to do so, and sell short MCD with the opposite logic.

Buy HD when the closing price is under the lower Bollinger Band, sell short HD when the price crosses above the upper Bollinger Band.

Buy SPY when the MACD is higher than the Signal line (histogram is positive), sell short SPY when the MACD crosses below the Signal line (histogram is negative).


Multi-Stock Backtests: Get results for a strategy on a universe of stocks all at once, like: "Buy when it goes down 3 days in a row. Test on AAPL, TSLA, DIS"

Hedged Backtest: We run your backtest as usual, but automatically hedge the trades so the strategy is market-neutral. To do this, include hedge=true in your prompt like "Buy AAPL when the price goes down 5 times in a row, hedge=true". There are 2 reasons you might want to do this. First, no matter how good your strategy is, it can easily lose money if the market moves against you. Hedging protects you from big market moves. Second, if your strategy involves mostly buy orders, it will probably show a good profit because the stock market has gone up so much during the time period of the backtest. For example, almost any strategy that involved buying AAPL in the past 10 years would have made a big profit because AAPL has consistently increased in price. With hedging, if the strategy says to buy AAPL, for that same period of time we sell short an equal amount of SPY (this is an ETF that represents the general stock market). That way if the market goes down and causes AAPL to go down, you will make money shorting SPY to offset the AAPL loss.

Pair Trading: A market-neutral strategy (meaning it does not matter if the overall market goes up or down) like "Buy PEP and sell short COKE when they diverge by a threshold of more than 1%." The concept of pair trading is that two related stocks, such as Coke and Pepsi, usually move together (their prices are highly correlated). If for some reason the prices diverge, you short the outperforming stock and go long the underperforming one, hoping the price spread will eventually revert back to the mean.

Pair Basket Basket Trading: This is like pair trading, but it picks the pair of stocks from a bigger group of stocks like "Buy the stock that went down the most yesterday, sell the stock that went up the most yesterday. The universe of stocks to use for this is AAPL, DIS, MSFT, AA, VZ, META."

Coming Soon - Algorithmic Portfolio Trading: Where you always have your money invested in something, but the strategy decides when you move in and out of various stocks and ETFs.

Coming Soon - Preprogrammed Strategies: You will be able to backtest a bunch of well-known strategies from stock investment books and newsletters, and optionally mix those with your own strategies.

Coming Soon - Crypto, FX, and Futures: We are working on adding these to the site.

Coming Soon - Paper Trading: Register for a free account and you can save your favorite strategies to forward-test them. Track the profit/loss each new day, as if you had invested in the strategy for real.

Coming Soon - AI Portfolio Investing: Where the AI recommends a group of stocks for you to buy and hold based on criteria that you specify. For example, you might ask the AI to create a stock portfolio based on your own prediction of the future economic and political environment. There is no backtesting for this, it is buy and hold so it needs to be tested with paper trading or live trading. An example would be: "I think the stock market might go down so I want to play it safe and invest in stocks that are safe. Please output a list of the top 10 safe stocks for me to buy." Another example would be "I want you to create a stock trading strategy based on the following predictions:
1. There will be hyperinflation.
2. The AI industry will grow significantly.
3. The Russia/Ukraine war will go on for years.
4. Global warming will get worse.

Available Technical Indicators:


Momentum Indicators

ADX - Average Directional Movement Index

ADXR - Average Directional Movement Index Rating

APO - Absolute Price Oscillator

AROON - Aroon

AROONOSC - Aroon Oscillator

BOP - Balance Of Power

CCI - Commodity Channel Index

CMO - Chande Momentum Oscillator

DX - Directional Movement Index

MACD - Moving Average Convergence/Divergence

MACDEXT - MACD with controllable MA type

MACDFIX - Moving Average Convergence/Divergence Fix 12/26

MFI - Money Flow Index

MINUS_DI - Minus Directional Indicator

MINUS_DM - Minus Directional Movement

MOM - Momentum

PLUS_DI - Plus Directional Indicator

PLUS_DM - Plus Directional Movement

PPO - Percentage Price Oscillator

ROC - Rate of change : ((price/prevPrice)-1)*100

ROCP - Rate of change Percentage: (price-prevPrice)/prevPrice

ROCR - Rate of change ratio: (price/prevPrice)

ROCR100 - Rate of change ratio 100 scale: (price/prevPrice)*100

RSI - Relative Strength Index

STOCH - Stochastic

STOCHF - Stochastic Fast

STOCHRSI - Stochastic Relative Strength Index

TRIX - 1-day Rate-Of-Change (ROC) of a Triple Smooth EMA

ULTOSC - Ultimate Oscillator

WILLR - Williams' %R


Overlap Studies

BBANDS - Bollinger Bands

DEMA - Double Exponential Moving Average

EMA - Exponential Moving Average

HT_TRENDLINE - Hilbert Transform - Instantaneous Trendline

KAMA - Kaufman Adaptive Moving Average

MA - Moving average

MAMA - MESA Adaptive Moving Average

MAVP - Moving average with variable period

MIDPOINT - MidPoint over period

MIDPRICE - Midpoint Price over period

SAR - Parabolic SAR

SAREXT - Parabolic SAR - Extended

SMA - Simple Moving Average

T3 - Triple Exponential Moving Average (T3)

TEMA - Triple Exponential Moving Average

TRIMA - Triangular Moving Average

WMA - Weighted Moving Average


Volume Indicators

AD Chaikin A/D Line

ADOSC Chaikin A/D Oscillator

OBV On Balance Volume


Cycle Indicators

HT_DCPERIOD - Hilbert Transform - Dominant Cycle Period

HT_DCPHASE - Hilbert Transform - Dominant Cycle Phase

HT_PHASOR - Hilbert Transform - Phasor Components

HT_SINE - Hilbert Transform - SineWave

HT_TRENDMODE - Hilbert Transform - Trend vs Cycle Mode


Price Transform

AVGPRICE - Average Price

MEDPRICE - Median Price

TYPPRICE - Typical Price

WCLPRICE - Weighted Close Price


Volatility Indicators

ATR - Average True Range

NATR - Normalized Average True Range

TRANGE - True Range


Pattern Recognition

CDL2CROWS - Two Crows

CDL3BLACKCROWS - Three Black Crows

CDL3INSIDE - Three Inside Up/Down

CDL3LINESTRIKE - Three-Line Strike

CDL3OUTSIDE - Three Outside Up/Down

CDL3STARSINSOUTH - Three Stars In The South

CDL3WHITESOLDIERS - Three Advancing White Soldiers

CDLABANDONEDBABY - Abandoned Baby

CDLADVANCEBLOCK - Advance Block

CDLBELTHOLD - Belt-hold

CDLBREAKAWAY - Breakaway

CDLCLOSINGMARUBOZU - Closing Marubozu

CDLCONCEALBABYSWALL - Concealing Baby Swallow

CDLCOUNTERATTACK - Counterattack

CDLDARKCLOUDCOVER - Dark Cloud Cover

CDLDOJI - Doji

CDLDOJISTAR - Doji Star

CDLDRAGONFLYDOJI - Dragonfly Doji

CDLENGULFING - Engulfing Pattern

CDLEVENINGDOJISTAR - Evening Doji Star

CDLEVENINGSTAR - Evening Star

CDLGAPSIDESIDEWHITE - Up/Down-gap side-by-side white lines

CDLGRAVESTONEDOJI - Gravestone Doji

CDLHAMMER - Hammer

CDLHANGINGMAN - Hanging Man

CDLHARAMI - Harami Pattern

CDLHARAMICROSS - Harami Cross Pattern

CDLHIGHWAVE - High-Wave Candle

CDLHIKKAKE - Hikkake Pattern

CDLHIKKAKEMOD - Modified Hikkake Pattern

CDLHOMINGPIGEON - Homing Pigeon

CDLIDENTICAL3CROWS - Identical Three Crows

CDLINNECK - In-Neck Pattern

CDLINVERTEDHAMMER - Inverted Hammer

CDLKICKING - Kicking

CDLKICKINGBYLENGTH - Kicking - bull/bear determined by the longer marubozu

CDLLADDERBOTTOM - Ladder Bottom

CDLLONGLEGGEDDOJI - Long Legged Doji

CDLLONGLINE - Long Line Candle

CDLMARUBOZU - Marubozu

CDLMATCHINGLOW - Matching Low

CDLMATHOLD - Mat Hold

CDLMORNINGDOJISTAR - Morning Doji Star

CDLMORNINGSTAR - Morning Star

CDLONNECK - On-Neck Pattern

CDLPIERCING - Piercing Pattern

CDLRICKSHAWMAN - Rickshaw Man

CDLRISEFALL3METHODS - Rising/Falling Three Methods

CDLSEPARATINGLINES - Separating Lines

CDLSHOOTINGSTAR - Shooting Star

CDLSHORTLINE - Short Line Candle

CDLSPINNINGTOP - Spinning Top

CDLSTALLEDPATTERN - Stalled Pattern

CDLSTICKSANDWICH - Stick Sandwich

CDLTAKURI - Takuri (Dragonfly Doji with very long lower shadow)

CDLTASUKIGAP - Tasuki Gap

CDLTHRUSTING - Thrusting Pattern

CDLTRISTAR - Tristar Pattern

CDLUNIQUE3RIVER - Unique 3 River

CDLUPSIDEGAP2CROWS - Upside Gap Two Crows

CDLXSIDEGAP3METHODS - Upside/Downside Gap Three Methods


Statistic Functions

BETA - Beta

CORREL - Pearson's Correlation Coefficient (r)

LINEARREG - Linear Regression

LINEARREG_ANGLE - Linear Regression Angle

LINEARREG_INTERCEPT - Linear Regression Intercept

LINEARREG_SLOPE - Linear Regression Slope

STDDEV - Standard Deviation

TSF - Time Series Forecast

VAR - Variance