AI Strategies

AI strategies are strategies that are evaluated by AI, produce AI events, and that trade on behalf of the user.

An AI strategy has the following properties:

• Nickname (a descriptive name for the strategy, chosen by the user at strategy creation time - only used for display purposes)

• Markets (markets that the strategy covers - any market not in this list will not be considered by the strategy - the more markets selected, the more AI credits the strategy consumes)

• Quantity (USD quantity of the orders that the strategy submits - selected by the user at strategy creation time - users are recommended to start out with a low Quantity and scale up as they refine their prompts and become more confident in their AI)

• Timeframe (the timeframe which the strategy operates on - can be anywhere from 20 seconds to 1 week - lower timeframes query the AI more often and consume more AI credits)

• Min. confidence (minimum confidence required by the strategy in order to submit orders - traders are recommend to start out with a minimum confidence of 90% and fine-tune as needed)

• Status (status of the strategy, can be either "ACTIVE" or "PAUSED" - "PAUSED" strategies do not trade and do not consume AI credits)

• Creation time (strategy creation time - time at which the user created the strategy)

The most important properties to understand are Timeframe and Min. Confidence.

Timeframe governs the rate at which the strategy queries the AI, the timeframe that the AI considers in its decision process, and the timeframe/horizon of the data that is sent to the AI as part of a query. Lower timeframe strategies query the AI more often, and consume more AI credits, relative to higher timeframes.

Min. confidence is the minimum confidence level required by the AI in order to commit to a trading decision ("BUY" or "SELL"). The default minimum confidence level is 90%, requiring the AI to be reasonably certain in its decision prior to placing a trade. Traders can optionally select a lower minimum confidence level, resulting in more frequent trades and a potentially higher error/hallucination rate.