The primary role of the AI Backtesting Assistant is to help users find strategies quickly without having to iterate through various conditions, tickers, and timeframes on TradingView. Instead, we can simply ask the AI to look for the strategy that would best match our criterias.

The AI Backtesting Assistant has access to approximately 1000 different strategies, half using our S&O toolkit and the other half using our PAC toolkit.

This AI tool’s backtesting data & analytics are for informational purposes only and do not constitute financial advice or recommendations to buy or sell any financial product, including but not limited to securities, derivatives, cryptocurrencies, or other investment instruments.

This tool may contain errors, and past performance is not indicative of future results. Always conduct your own research and consult with a professional financial advisor.

LuxAlgo is not liable for any decisions made based on any information given. Read our full disclaimer.

Strategies Configuration

Strategies accessible by the AI backtesting assistant are backtested using an initial capital of 10000$, without commissions/slippage, and using default toolkits settings (except for the PAC which use’s a different invalidation behavior).

Unit position sizing is used across al tickers except forex pairs who use a standard lot (100 000 units).

The strategies the AI can access don’t make use of all the features within our toolkits, see the section below to learn more about the supported tickers, timeframes, and backtesting conditions.

Any strategy with 0 closed trades will not be accessible by the AI.

Strategies do note make use of stop losses or take profits.

Supported Tickers

The following tickers are supported:

Supported Timeframes

The 5m, 15m, and 60m timeframes are supported.

S&O Conditions

Strategies constructed from our S&O toolkit use a single condition or a combination of two conditions for the long and short entry conditions.

Only the following conditions are considered:

It is possible for a long/short entry condition to contain both bullish and bearish conditions

S&O Exits

Strategies making use of Confirmation or Reversal Zones based conditions can make use of the following exit conditions:

  • Confirmation Builtin Exits
  • Contrarian Builtin Exits
  • Price Cross R1/S1 Average

PAC Conditions

Strategies based on the PAC can use a maximum of three steps and invalidate entry conditions on any repeated step.

PAC strategies do not make use of exit conditions.

How To Fetch Strategies

Interacting with the AI Backtesting Assistant is straightforward. All users need to do is enter a prompt in the input prompt located at the bottom of the chat.

Here are examples of prompts that will trigger the AI Assistant strategy retrieval ability:

  • What is the best performing strategy across all crypto tickers on the 5-minute timeframe?
  • Get three strategies using fair value gaps that have a winrate above 80%
  • Find a strategy with above average net profit but under average drawdown

Users can also click on one of the suggested prompts in the search group located above the input prompt.

The AI can access the following strategy backtesting results:

  • Net Profit
  • Executed Trades
  • Percentage Winrate
  • Max Drawdown Percent
  • Profit Factor
  • Average Trade
  • Average Winning Trade
  • Average Loosing Trade

These results will be returned in a table, if multiple strategies are returned, they will be all located within that table. Sometimes the AI can fetch strategies in the middle of a response; this will return another table containing the strategies fetched.

A maximum of five strategies can be returned in a table, while a maximum of three strategies can be returned from a single fetching operations.

If the AI needs to fetch more than 3 strategies it will fetch strategies in parallel.

The AI has also access to the following information from a strategy:

  • Strategy start time, that is when the strategy starts being evaluated
  • Strategy current position (long, short, or none)
  • Best signal sensitivity for a strategy using confirmation or contrarian signals

Fetch Statistics Across The Strategy Population

The AI can also get general statistics and data across the population of strategies being backtested.

Example of prompts doing this are:

  • What is the total net profit of bitcoin strategies?
  • On BTCUSD, are strategies using normal signal better than the ones using strong signals overall?
  • What is total net profit of profitable strategies across stocks?

This can be useful to get big picture information about strategies.

Add a Strategy to Your Chart

Once you get a strategy you like from the AI, you might want to add it to your chart.

To do so, follow these steps:

1

Add The Backtester To The Chart

Go to your TradingView chart, then open the indicator menu, locate the Backtester of the toolkit related to the strategy you want to add.

2

Adjust Backtesting Starting Time

Go in the backtester settings, then select “Date” in the “Backtest Window” setting, then adjust “Window Start” with the strategy start time provided by AI.

3

Select The Conditions

Adjust the long and short entry conditions in the backtester based on the conditions returned by the AI.

Strategies the AI has access to have a defined starting point. Users might not be able to reproduce exact strategy results due to the limitation on how much data certain users can access.

Saving Strategies

Users can export strategies within a table as a csv using the download icon located under it.

Prompting Tips

The AI can make mistakes when fetching strategies, as this is a very complex process depending on the user query.

We expect to improve the backtesting AI assistant over time; however, the following tips can help you get the most from our AI.

Make Detailed Queries

Make sure to detail every aspect of the strategy you want to fetch if you have a precise one in mind, for example:

OriginalImproved
Fetch a strategy that only makes use of confirmation signalsFetch a strategy that only uses confirmation signals and no other conditions
I want a PAC strategy that goes long on a new FVG, and CHoCHI want a PAC strategy that goes long when:

- Step 1: a new bullish FVG occur
- Step 2: a bullish CHoCH occur
I want the best strategyI want the strategy with the highest net profit

Context and details will help the AI avoid making guesses about your query.

Encourage the AI to Improve

The AI Backtesting Assistant can be fairly self-aware if a fetched strategy doesn’t meet a user criteria, and will then retry.

But if the AI response is clearly mistaken, then it can be good to let him know using a prompt encouraging re-evaluation of the fetching process:

The strategy your returned is not the one I want. Correct the issue in your fetching process and retry to fetch the strategy in accordance with my query.

Split Complex Queries Into Multiple Tasks

The AI will be more prone to mistakes if the query is complex, as such, it can be best to make use of follow-ups to ask about details over a strategy rather than asking the AI to give those alongside other information.

For example:

Return a good strategy on BTCUSDT, alongside the average net profit of all strategies on BTCUSDT that use Confirmation signals, then tell me what is the highest winrate strategy using the same conditions as the first one

The AI Backtesting assistant might provide more relevant answers if we let context accumulate by splitting and re-ordering our initial query into multiple ones:

1

First Query

Return a good strategy on BTCUSDT

2

Second Query

Find the strategy with the highest winrate that use the same exact entry conditions returned previously

3

Third Query

Return the average net profit of all strategies on BTCUSDT that use Confirmation signals