strategy-generate

Backtesting a quantitative trading strategy involves parsing your requirements into a config.json file specifying instruments, dates, and intervals, then coding signal_engine.py to run and evaluate the logic on a built-in engine.

A signal engine in quantitative trading is a coded module, such as signal_engine.py, that generates entry and exit signals. Its output must align with input data indices and stay within a normalized range of -1.0 to 1.0.

Yes, this strategy generation workflow supports multi-market quantitative trading. You can configure data sources and apply tailored signals across both equities and crypto instruments through the unified config.json.

You configure dates and instrument codes for backtesting by defining them within a config.json file. This file governs all critical parameters including codes, date ranges, data intervals, and any extra fields required for the signal engine.

Your signal engine output returns a validation error because it fails to meet the hard-gate criteria. The signal_engine.py output must precisely align with input data indices and remain bounded within the -1.0 to 1.0 range.

The best way to implement a dual-moving-average crossover strategy is to draft a config.json for your chosen instruments, code the entry and exit rules in signal_engine.py, and iterate on the backtest artifacts until metrics pass hard-gate criteria.