Zero setup, zero training
No templates, no labeled data, no schema files. Drop the document in and Docusift returns clean structured data.
Brokerage Statements extraction
Extract Holdings and activity from Brokerage Statements
Pull every holdings and activity value out of any brokerage statements — including scans and multi-page variants — into clean structured JSON. Each value carries a confidence score and a citation back to its source pixel.
Pulling holdings and activity out of a brokerage statement by hand is slow, and it is exactly where a mistake slips through. A brokerage or investment statement mixes a holdings table, a transaction ledger, income and fee lines, and performance summaries into a long, provider-specific document, and reconstructing cost basis or spreading assets means pulling every holding and trade exactly.
Docusift reads the account, period, every holding with its quantity, cost basis, and market value, and each transaction, into structured tables, so cost-basis and net-worth work runs off clean data instead of a retyped statement.
Each extracted value ships with a per-field confidence score and a citation back to the exact spot on the page it was read from, so low-confidence holdings and activity route to review automatically — and the clean data pushes to Google Sheets, a webhook, QuickBooks, or Xero.
| Symbol | Qty | Cost basis | Market value |
|---|---|---|---|
| VTI | 120 | 24,800.00 | 31,440.00 |
| BND | 200 | 14,900.00 | 14,320.00 |
| Cash | — | — | 5,180.00 |
Example structured output
{
"document_type": "brokerage_statement",
"account_number_masked": "****4471",
"period": "2026-03-01 to 2026-03-31",
"holdings": [
{ "symbol": "VTI", "quantity": 120, "cost_basis": 24800.00, "market_value": 31440.00 },
{ "symbol": "BND", "quantity": 200, "cost_basis": 14900.00, "market_value": 14320.00 }
],
"total_market_value": 50940.00,
"confidence": 0.97
}Why teams choose Docusift
A confidence score on every field
Every value ships with a confidence score and a citation back to the source pixel in the original document, so low-confidence fields route to review instead of landing unchecked.
Fast turnaround
Seconds per document, not minutes. Built for production pipelines, not batch jobs.
Privacy first
Workspace-isolated processing, encrypted in transit and at rest, and one-click data deletion.
Frequently asked questions
How do I extract holdings and activity from brokerage statements?
Upload the brokerage statements to Docusift via the dashboard, the REST API, or by emailing it to your workspace inbox. Docusift returns structured JSON with every holdings and activity value, its confidence score, and a citation back to the source pixel — typically in under a second per page.
What is the best way to pull holdings and activity from brokerage statements automatically?
The best way is a tool that reads layouts visually rather than matching templates. Template tools break when a vendor changes their format; Docusift parses each brokerage statement from scratch, so it works on multi-page, multi-currency, and scanned variants without per-vendor configuration.
Does it work on scanned brokerage statements?
Yes. OCR, layout analysis, and field extraction run in a single pass, so scans, mobile photos, and native PDFs use the same endpoint and reach the same accuracy bar.
Can I push the extracted holdings and activity into my own system?
Yes. Receive structured JSON via REST, hit a webhook, or sync directly into Google Sheets, your data warehouse, or your accounting tool.
How accurate is Docusift at extracting holdings and activity?
Docusift reads each brokerage statement visually rather than matching a template, and every extracted value ships with a per-field confidence score and a citation back to the source pixel — so low-confidence holdings and activity route to human review automatically instead of landing unchecked.
Do I need to train a model first?
No. Docusift recognizes hundreds of document types out of the box. Custom fields are configured with a single sentence — no labeled training data required.
How is pricing calculated?
Pay per page processed. There is a free tier for evaluation and volume discounts for production workloads. No seat fees.
Can Docusift handle scanned or photographed documents?
Yes. The pipeline runs OCR + layout analysis + extraction in one pass, so scans, mobile photos, and native PDFs all flow through the same endpoint.
Related extractors
Start extracting holdings and activity from brokerage statements
Free tier includes 100 pages per month. No credit card required.
Start free — no credit card