Overview
Topograph’s extract financial data automatically from company annual statements. We analyze PDF documents and extracts key financial metrics into a structured, machine-readable format.How It Works
When a financial statement document is processed:- Document Classification - The AI first determines if the document is a financial statement
- Data Extraction - If identified as a financial statement, key metrics are extracted
- Structured Output - Data is returned in the
extractedData.financialDatafield
extractedData field populated.
Data Model
The structure for extracted data covers all major components of financial statements as presented below.Top-Level Structure
Metadata Fields
Fiscal Year
Accounting Standard
"IFRS"- International Financial Reporting Standards"French GAAP"- French Generally Accepted Accounting Principles"US GAAP"- United States GAAP"Swiss GAAP"- Swiss GAAP"Lux GAAP"- Luxembourg GAAP"Other"- Other accounting standards
Statement Type
"consolidated"- Group/consolidated financial statements"simplified"- Individual/standalone statements
Income Statement
Balance Sheet
The balance sheet is organized into two main sections.Assets
Equity and Liabilities
AI Financial Analysis
In addition to extracting raw financial data, Topograph provides AI-powered analysis that includes insights, ratios, trends, and risk assessments.Analysis Structure
Ratio Explanations
| Ratio | Formula | Good | Watch | Risk |
|---|---|---|---|---|
| Current Ratio | Current Assets / Current Liabilities | > 1.5 | 1.0 - 1.5 | < 1.0 |
| Quick Ratio | (Current Assets - Inventory) / Current Liabilities | > 1.0 | 0.5 - 1.0 | < 0.5 |
| Debt to Equity | Total Liabilities / Total Equity | < 1.0 | 1.0 - 2.0 | > 2.0 |
| Net Profit Margin | Net Income / Revenue | > 10% | 5% - 10% | < 5% |
| Return on Equity | Net Income / Total Equity | > 15% | 10% - 15% | < 10% |
Health Score
The health score ranges from 1 to 10:- 8-10: Excellent financial health
- 6-7: Good, with some areas to monitor
- 4-5: Fair, requires attention
- 2-3: Weak financial position
- 1: Critical condition
Important Notes
Data Quality
- Null Values - Fields return
nullwhen data is missing, unclear, or not applicable - Numeric Values - All amounts are numeric values without currency symbols or thousand separators
- Negative Values - Losses and deficits preserve the negative sign
- Local Terms - The
localNamefield presents the exact wording used in the source document
Multi-Language Support
The extraction works across multiple languages and accounting frameworks:- Recognizes financial terms in various languages
- Maps local terminology to standardized fields
- Preserves original terms in
localNamefields
Current Limits
- Only processes PDF financial statements
- Extraction accuracy depends on document quality and structure
- Complex or non-standard formats may have reduced accuracy
- Currently focuses on core financial metrics