#
Earnings
This tool is designed for pulling earnings data on specific tickers you already have in mind. For screening and discovering upcoming earnings dates, use the market screener tool found in the screener documentation.
The earnings tool provides access to comprehensive earnings data for any ticker, covering both historical confirmed results and future projected earnings. Access detailed earnings information including EPS surprises, revenue beats/misses, fiscal periods, and earnings dates to analyze company performance patterns and predict market movements.
#
How To Use
The earnings tool pulls detailed earnings data for specific companies over custom date ranges. You can filter for confirmed historical earnings or projected future earnings, and analyze performance patterns across multiple fiscal periods.
📊 Historical & Future 🎯 Specific Tickers 📈 Performance Analysis
#
Getting Started
- Specify Ticker: Provide the stock ticker you want earnings data for
- Set Date Range: Define your start and end dates for the earnings period
- Choose Data Type: Select confirmed historical earnings or projected future earnings
- Apply Filters: Optionally filter by fiscal periods, surprise percentages, or other criteria
How to trigger: Use the Earnings tool directly from the tools tab, or mention "earnings data" in your prompt along with your target ticker and date range.
#
Available Filters
#
Basic Filters
- Ticker Symbol: Target any specific stock ticker for focused earnings analysis
- Date Range: Set custom start and end dates to capture relevant earnings periods
- Data Status: Choose between confirmed historical results or projected future earnings
- Result Limit: Control the number of earnings reports returned (up to 100 companies per query)
#
Advanced Filters
- Fiscal Periods: Filter by specific quarters (Q1, Q2, Q3, Q4), half-years (H1, H2), or full fiscal years (FY)
- EPS Surprise Range: Set minimum and maximum EPS surprise percentages to find significant beats or misses
- Revenue Surprise Range: Filter by revenue surprise percentages to identify companies exceeding or missing expectations
- Fiscal Year Range: Focus on specific fiscal years for multi-year earnings analysis
#
Example Use Cases
#
Historical Performance Analysis
Analyze past earnings patterns to identify consistency trends and predict future stock movements. Pull 3-5 years of historical earnings data to spot companies with reliable earnings growth or concerning volatility patterns.
#
Earnings Health Assessment
Evaluate a company's earnings quality by examining surprise percentages, revenue growth consistency, and seasonal patterns across multiple fiscal periods.
#
Pre-Earnings Research
Before major earnings announcements, review historical earnings performance to gauge potential market reactions and set realistic expectations for upcoming results.
#
Example Queries
- "Pull AAPL earnings data for the last 2 years to analyze consistency patterns"
- "Get TSLA confirmed earnings with EPS surprises above 10% since 2022"
- "Show me projected earnings for NVDA over the next 6 months"
- "Load historical Q4 earnings data for AMZN to identify seasonal trends"
#
💡 Pro Tips
- Pattern Recognition: Use historical earnings data to analyze consistency and identify patterns in a stock's earnings performance over multiple cycles
- Batch Analysis: Pull earnings history for up to 100 stocks in one query—screen for stocks with earnings in the next week, then grab all their previous earnings performance for comparison
- Surprise Impact: Focus on EPS and revenue surprise percentages to understand which companies consistently beat or miss expectations and how markets typically react
#
⚠️ Important Notes
- Data vs Screening: This tool is for pulling detailed earnings data on specific tickers, not for screening or discovering earnings opportunities
- Date Requirements: Always specify both start and end dates—the tool requires a defined date range to function properly
- Historical Focus: Use confirmed earnings data for backtesting and pattern analysis, projected data for forward-looking research