How we score.
How we rank.
BigEarnings combines SEC-filed earnings data with a proprietary scoring model to surface the stocks most likely to move after earnings. Here's exactly how it works.
Data collection
Where the data comes from
All earnings data originates from SEC filings and verified market data providers. We ingest quarterly EPS and revenue figures — estimates and actuals — for 6,200+ U.S.-listed companies. Data is reconciled across multiple sources and cross-validated before entering our system. Price data is sourced from exchange feeds with second-level granularity for post-earnings tracking.
Post-earnings tracking
Measuring what happens after the call
Most platforms stop at beat or miss. We measure four distinct price windows after every earnings report: 1 day, 1 week, 1 month, and ER to ER (next earnings date). Each window measures the percentage change from the closing price on the day before earnings to the closing price at the specified interval.
This gives you a complete picture of post-earnings drift — the well-documented tendency for stock prices to continue moving in the direction of an earnings surprise for weeks or months after the report.
Scoring model
Growth Trajectory Score (0–100)
Every company receives a composite Growth Trajectory Score from 0 to 100, updated quarterly. The score combines three weighted dimensions:
Fundamental Growth
Revenue growth rate, EPS growth rate, margin expansion, and market cap relative to sector. Measured over a trailing 18-month window to capture sustained trends, not one-time spikes.
Beat Quality
EPS beat rate, beat consistency across quarters, and magnitude of surprises. Companies that consistently beat by a small amount score differently than those with volatile results.
Price Momentum
Post-earnings price performance across all four time windows (1D, 1W, 1M, ER-to-ER). Rewards stocks that consistently move up after beating earnings — the signal that matters most.
AI layer
How AI analysis works
After each earnings report is filed, our AI engine generates a structured analysis covering the key takeaways: revenue and EPS performance vs. estimates, management guidance changes, notable commentary, and sector-relative positioning. These notes are designed to give you the essential context in 30 seconds instead of reading through an entire earnings transcript.
AI-generated content is clearly labeled and should be treated as a starting point for further research, not as financial advice.
Data quality
How we keep data accurate
Multi-source validation
Earnings data is cross-referenced across multiple providers to catch discrepancies before they reach the platform.
Automated anomaly detection
Statistical checks flag unusual EPS surprises, price spikes, or missing data that require manual review.
Historical consistency
Beat rates and performance metrics are retroactively corrected if underlying data is revised by the SEC or reporting companies.
Real-time monitoring
System health checks run continuously. If a data pipeline fails, affected pages are flagged and data is held until validated.
See it in action
The methodology is the product. Explore the data yourself.