strategy-pivot-designer

Backtest stagnation occurs when iteration scores plateau or show overfitting. This Skill analyzes your backtest history JSON to identify performance plateaus and generates new strategy architectures using techniques like assumption inversion and archetype switching to improve trading performance.

Redesigning plateaued machine learning strategies requires analyzing iteration history to detect overfitting. This Skill processes your backtest history to propose strategy pivots, applying objective reframing and archetype switching techniques to generate new architectures that bypass performance stagnation.

Yes, detecting backtest overfitting and stagnation requires Python 3.9 or higher. You also need pandas, numpy, scikit-learn, scipy, and PyYAML installed, along with a valid iteration history JSON file containing your backtest records for analysis.

Yes, assumption inversion and archetype switching are core techniques used to propose new algorithmic trading architectures. The Skill applies these methods to your backtest history data, generating pivot proposals that reframe objectives and invert underlying assumptions to overcome performance plateaus.

Automating strategy pivot proposals depends entirely on the quality and structure of your iteration history JSON file. The Skill cannot generate meaningful stagnation detection or architecture recommendations without a properly formatted backtest history capturing sufficient iteration data.

Backtest iteration history often shows overfitting when strategies become too refined for historical data. The Skill detects these stagnation points by analyzing your iteration history JSON, then proposes new architectures using objective reframing to break free from overfitted performance plateaus.