scoring-engine

Quantitative composite scoring evaluates financial assets by integrating fundamental, technical, and sentiment analyses to produce a 0-100 score. The system applies regime-based weighting and risk adjustment filters to generate data-driven investment decisions.

You can screen stocks by running a command like `trading screen --market NYSE --min-score 70 --top 20`. This quickly filters the market to identify top-performing assets based on a quantitative composite score.

Yes, financial asset scoring requires a Python execution environment with access to financial data APIs and analytical libraries. These dependencies are necessary to calculate financial metrics like Z-Score and M-Score for safety filters.

The scoring system implements hard gates using Z-Score and M-Score as safety and risk adjustment filters. These metrics ensure the reliability of the 0-100 composite score by filtering out high-risk financial assets.

Yes, the system leverages parallel execution of specialized Team Agents for fundamental, technical, and sentiment analysis. This multi-agent approach ensures comprehensive evaluation of financial assets across three distinct analytical dimensions.

Regime-based weighting in investment scoring relies heavily on accurate financial data APIs and analytical libraries. Limitations arise if the Python execution environment lacks access to real-time market data, affecting the reliability of the 0-100 composite score.