Model Methodology

1. What the Models Use

SeekingBeta.AI models are trained on historical market data and derived indicators. Inputs include price/volume history and model features that summarize trend, momentum, and volatility behavior over time.

2. What the Models Output

Each model returns:

• A rating: Bullish, Neutral, or Bearish.
• An upside probability estimate for the selected horizon.
• A high-level driver summary to explain the rating context.

3. Time Horizons

We run multiple model horizons (for example, short-horizon and swing-horizon variants) so users can compare signals across different time windows.

4. Track Record and Benchmarking

We publish model track record metrics and compare results against the S&P 500 (SPY) for context. Displayed metrics can include return, hit rate, drawdown, Sharpe ratio, and related diagnostics.

Track record values are based on defined backtest rules and assumptions and are updated as new artifacts are refreshed.

5. What This Is Not

SeekingBeta.AI does not provide personalized investment advice. Ratings are generated by automated statistical models and may be wrong.

Market conditions change, and past performance does not guarantee future results. Always do your own research before making investment decisions.

6. Contact

Questions about methodology can be sent to support@seekingbeta.ai.