The primary role of the AI Backtesting Assistant is to help users find strategies quickly without having to manually iterate through various conditions, tickers, and timeframes on TradingView charts. Instead, users can simply ask the AI to look for the strategy that would best match the criteria they want. The AI Backtesting Assistant has access to millions of unique strategies, each made using a wide variety of conditions.
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 are evaluated using at least the most recent 20.000 bars, with an initial capital of 10.000 base currency, without commissions/slippage, and using default settings for all toolkits features. Unit position sizing is used across all tickers. When a strategy enters a trade, any previous trade is closed. As such, it is not possible for two positions to be open at the same time.
Strategies do not make use of stop losses or take profits.
See the section below to learn more about the supported tickers, timeframes, and backtesting conditions.

Supported Tickers

The following tickers are supported:
US equities (Stocks and ETFs) use regular trading hours and are based on the Cboe BZX exchange.Futures are based on continuous contracts and use electronic trading hours.

Supported Timeframes

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

Strategy Entry and Exits Constructions

Strategy entry conditions can make use of multiple conditions from different toolkits together. We classify conditions as triggers and filters:
  • Triggers: Triggers determine the initial conditions used by a strategy. These tend to be less persistent events on a chart, occurring for a single bar.
  • Filters: Filters add precision to a strategy, potentially filtering out bad trades that would have been taken by simply using triggers. Filters tend to be more persistent, lasting for multiple bars on a chart.
Entry conditions contain a single trigger, and can contain up to two filters.
It is possible for a long/short entry condition to contain both bullish and bearish conditions
Long and short entry conditions mirror each other, that is, if the long entry condition uses a bullish condition, the short entry condition will use the same condition but bearish. Example:
  • long: Confirmation Any Bullish and Bullish Smart Trail and Bearish Trend Tracer
  • short: Confirmation Any Bearish and Bearish Smart Trail and Bullish Trend Tracer
Finally, it is possible that some strategies using conditions from the Signals & Overlays® toolkit use exits condition to close trades.

Signals & Overlays® Conditions


Triggers

Filters

Exits

Strategies using the Signals & Overlays® toolkit can make exit trades which are outlined below:

Price Action Concepts® Conditions


Currently only triggers are supported for the Price Action Concepts® toolkit.

Triggers

Oscillator Matrix® Conditions


Triggers

Filters

How To Fetch Strategies

Interacting with the AI Backtesting Assistant is straightforward. All users need to do is type a prompt in the chat box located at the bottom of their screen. Here are examples of prompts that will trigger the AI Backtesting Assistant to retrieve a trading strategy:
  • What is the best performing strategy across all crypto tickers on the 5-minute timeframe?
  • Give me three strategies using fair value gaps that have a winrate above 80%.
  • Find a strategy with above average net profit but below 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 backtesting results for strategies:
  • Net Profit
  • Max Net Profit
  • Closed Trades
  • Winning Trades
  • Losing Trades
  • Winrate
  • Gross Profit
  • Gross Loss
  • Profit Factor
  • Max Drawdown
  • Max Drawdown Percent
  • Average Trade
  • Average Winning Trade
  • Average Losing Trade
Due to calculations sensitive to data differences, our Drawdowns calculations are based on realized profits/losses, which is not the case on TradingView, this can explain why certain differences can be observed.
These results will be returned in a component in the chat. Strategy Results If multiple strategies are returned, they will all be located within a table.
A maximum of 3 strategies can be returned in a table at once, while a maximum of three strategies can be returned from a single fetching operation.If the AI needs to fetch more than 3 strategies it will fetch strategies sequentially.
The AI can also access to the following information from a strategy:
  • Strategy begins at: When the strategy started being evaluated
  • Strategy current position: Long, short, or flat if no positions are currently open

Fetch Statistics Across The Entire Strategy Population

The AI can get general statistics and data across the whole population of strategies it has access to. Example of prompts doing this are:
  • What is the total net profit of all bitcoin strategies you have?
  • On BTCUSD, are strategies using normal Confirmation signals better than the ones using strong Confirmation signals overall?
  • What is total net profit of profitable strategies across stocks?
This can be useful to get big picture information about strategies.
Do note that such prompts can lead to high wait time for the results.

Reproducing a Strategy on TradingView

Once you get a strategy you like, you may be inclined to add it to your chart to visualize it and further optimize its results on TradingView. To do so, simply click on the TradingView logo located near the ticker symbol for the single strategy component, and to the right of a hovered row on a table containing strategies. This will open a dialog box containing all the steps required to get the strategy on TradingView, as well as the scripted strategy which you must copy and paste to the relevant backtester.
A strategy using multiple conditions from at least two toolkits will require using LUCID connectors, learn more about LUCID connectors here.
We compute strategies using data that might different from the one on TradingView, which can limit the reproducibility of strategies returned by the AI.Some users might not be able to reproduce exact strategy results due to the limitation on how much data certain users can access.

Saving Strategies

Strategies can be saved in the sidebar by clicking on the star icon located near the ticker symbol for the single strategy component, and to the right of a hovered row on a table containing strategies. Additionally, strategies returned in a table can be exported as a CSV file.

Prompting Tips

The AI can make mistakes when fetching strategies, as this is a very complex process depending on the user query. We will always aim to improve the AI Backtesting 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 uses 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 on BTCUSD 5 minute
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 it 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 is best to do follow-up messages asking about the details of a strategy rather than asking the AI to give those alongside other information. For example:
Return a good strategy on BTCUSD, alongside the average net profit of all strategies on BTCUSD that use Confirmation signals, then tell me what the highest winrate strategy is, 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 BTCUSD
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 BTCUSD that use Confirmation Signals.