🔒 Sign In
Basic Fundamental Screen Simple

Screens stocks using hard filters on profitability (Return on Equity), financial health (Debt-to-Equity ratio), and growth (Revenue Growth). Ranks passing stocks by a composite score.

This strategy applies simple pass/fail filters to screen the universe of stocks down to quality candidates. It evaluates three core fundamentals: 1. Return on Equity (ROE): Ensures the company generates adequate returns on shareholder capital 2. Debt-to-Equity Ratio: Ensures the …
Best for: Beginners seeking a systematic approach to finding quality stocks. Works best as a first filter to narrow down a large universe before deeper analysis. Suitable …
Techniques Used
Rule-based filters Static ranking
Sign in to access this strategy
Sign In
🔒 Sign In
Multi-Factor Screening Moderate

Scores stocks across multiple fundamental factors (growth, profitability, leverage, valuation) and ranks them within their sector to ensure fair comparisons. Includes historical backtesting to validate factor effectiveness.

This strategy builds a comprehensive scoring system using multiple fundamental factors: 1. For each factor category (growth, profitability, etc.), individual metrics are calculated 2. Each metric is converted to a percentile score (0-100) based on where the stock ranks 3. …
Best for: Intermediate investors who want a more sophisticated approach than simple screening. Ideal for building diversified portfolios that balance multiple attributes. Works well for patient investors …
Techniques Used
Multi-factor scoring Sector-neutral ranking Backtesting
Sign in to access this strategy
Sign In
🔒 Sign In
ML-Powered Fundamental Screen Advanced

Uses machine learning (LightGBM or XGBoost gradient boosting algorithms) to predict which stocks will outperform based on fundamental data. Includes explainability features (SHAP values) and adapts to different market regimes.

This advanced strategy uses machine learning to identify stocks likely to outperform: 1. Feature Engineering: Creates hundreds of fundamental features from income statement, balance sheet, and cash flow data (growth rates, ratios, trends, sector-relative metrics) 2. Target Variable: Forward 3-month …
Best for: Quantitative investors with data science experience who can monitor and maintain ML models. Best suited for systematic funds with proper backtesting infrastructure. Requires ongoing model …
Techniques Used
XGBoost/LightGBM SHAP values Regime detection Anomaly detection
Sign in to access this strategy
Sign In
← Back to Catalog