Using Ranker Predictions and Benchmark Returns in Backtests

Summary

This Chinese-language forum question explains two data objects that appear in AI strategy examples on the BigQuant platform. The ranker prediction object contains predictions passed to the backtesting module, and the strategy can read the data through the backtest context. It is used to retrieve the predictions corresponding to the current backtest date.

The benchmark risk object is described as holding broad market index data, from which a five-day return is calculated. The post points to code for that calculation but does not include it in the supplied text, so the precise formula and data handling cannot be reviewed. It is a narrow explanation of platform-specific backtest inputs rather than a complete account of model construction, validation, or strategy performance.

Key ideas

• Ranker predictions are made available to the backtest through its context data.
• The strategy retrieves prediction values for the current backtest date.
• The benchmark risk data represents a broad market index and its five-day return.
• The excerpt does not show the calculation code or report any model performance.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.