Most financial PDFs weren't designed for analysis. Tables break across pages, units shift, and formatting changes from file to file. DealSheets.ai handles that complexity automatically so you can focus on interpretation, not cleanup.
Upload one or more PDFs containing monthly financial statements through our secure interface.
For single large PDFs (like CIMs), select specific pages containing your financial tables. Perfect for extracting monthly P&Ls across multiple years — when Jan-Dec 2021 is on page 55, Jan-Dec 2022 on page 56, and Jan-Dec 2023 on page 57.
Each file is scanned and preprocessed. If your statements are scanned images, the system automatically applies OCR to make them machine-readable.
Supports:
Our engine reviews each selected page to identify financial tables with period-based columns (monthly, quarterly, or annual data).
The system detects Income Statements by identifying common line items like revenue, COGS, gross profit, and EBITDA, then classifies tables by statement type.
Each detected table is extracted using multiple parsing methods to ensure accuracy.
We combine outputs from pdfplumber and Camelot in both lattice and stream modes, then compare results and choose the highest-confidence version.
Common accounting structures are recognized automatically, including:
Financial statements often report figures in thousands or millions.
DealSheets.ai detects the declared units, rescales all values to a consistent standard, and ensures subtotals and totals align correctly.
Example:
If a Balance Sheet shows "($ in millions)," the export converts every figure accordingly.
When multiple Income Statements are selected — whether from different pages in one PDF, multiple separate files, or different time periods — the system intelligently merges them into a single horizontal view.
Line items are matched using section-aware logic that preserves legitimate duplicates (like "Business to Consumer" appearing in both revenue and COGS sections).
The result is a single consolidated Excel sheet. For multi-year monthly data, all periods appear horizontally: Jan-21, Feb-21, ..., Dec-21, Jan-22, ..., Dec-23.
Before export, the system performs consistency checks on total lines:
Results include color-coded indicators showing where PDF values match or differ from formula calculations.
Your final Excel workbook includes:
Once processing is complete, download your Excel workbook with all periods consolidated into a single view.
Every number is traceable back to the source PDF, ready for analysis, modeling, or integration into existing workflows. No manual re-typing, no copy-paste errors.
DealSheets.ai was designed by operators who have lived both sides of the table — CEOs running portfolio companies and deal teams reviewing them. The system reflects years of firsthand experience with financial data, built to eliminate the slowest manual step in the transaction process.
Upload your first PDF and see how accurate automation can be.