Skip to main content

​
Source Data

All source data originates from the U.S. Alcohol and Tobacco Tax and Trade Bureau (TTB), a bureau of the U.S. Department of the Treasury.
  • Primary source: TTB COLA Public Registry — the federal database of approved alcohol product labels
  • Supplementary sources: TTB permit holder records, TTB production statistics
  • Reuse: Public access is not a blanket license to every submitted label image or brand asset. TTB’s copyright notice distinguishes government work from copyrighted material. COLA Cloud delivery and reuse rights are governed by the applicable service or data-license terms.
Customers are free to access the TTB’s public data directly. COLA Cloud’s value is in the collection, structuring, enrichment, and ongoing maintenance of this data at scale.

​
Coverage

Millions of COLAs

Label approval records dating back to 2005

Label Images

Submitted label images, when available

Extracted Barcodes

Extracted from label images for product matching

Daily Collection

New records added from TTB on a daily basis
The web app and self-service API cover records from 2005 onward, using approval date, then application date, then latest-update date when the preceding date fields are absent. Warehouse and delivery counts can differ from the application database; counts of approvals, images, barcodes, and distinct products are not interchangeable. A label approval does not establish a unique product, retail launch, current availability, or sales. The registry does not cover every alcohol product or reveal the status of private pending applications. See TTB label approval basics for COLA requirements and exceptions.

​
Dated App Coverage

As of October 1, 2026, the export feeding the web app and self-service API contains: This snapshot counts current export records with available label imagery and excludes physical-form submissions. Related images and barcodes inherit the same record scope. The date boundary uses the fallback dates described above. Counts change as collection and enrichment continue. Barcode values are not normalized GTINs or unique-product counts: UPC/EAN formats can represent the same identifier differently, and a value can appear on multiple approvals. Use these values to find and evaluate possible product matches alongside the label evidence. Permit holder records are updated from TTB filings.

​
Collection

COLA Cloud collects new and updated records from the TTB on a daily basis, including label images and all associated structured fields — brand name, product type, origin, alcohol content, approval dates, applicant information, and more. Raw source materials are retained in durable storage for auditability and reprocessing.

​
Enrichments

The enrichment pipeline can produce the following additional fields. Availability varies by record, source imagery, and processing outcome:

​
Text Extraction

Label images are processed with optical character recognition to extract visible text from the label artwork. This captures information printed on the label that isn’t part of the TTB’s structured data — tasting notes, marketing copy, ABV declarations, volume statements, and more.

​
Barcode Identification

Label images are scanned for standard barcode formats. When found, the decoded value, barcode type, and position on the label are recorded.
Barcode coverage varies with the submitted images and extraction results. A missing barcode does not mean the product has no barcode; a decoded barcode is a matching clue and should be checked against the approval and label image.

​
AI-Powered Feature Extraction

Automated models extract structured fields from available label evidence that would otherwise require manual review:

​
Address Normalization

Applicant addresses from TTB records are parsed and normalized into structured components for consistent matching and geocoding.

​
Data Freshness

​
Known Limitations

We believe in transparency about what automated enrichment can and cannot do:
  1. Source data quality — The TTB registry occasionally contains errors, omissions, or delays. COLA Cloud reflects what the TTB publishes.
  2. Text extraction accuracy — Extraction from label images is automated and imperfect. Stylized fonts, low-resolution images, and overlapping text can reduce accuracy. Field-level accuracy is not guaranteed.
  3. AI classification — Product categorization and feature extraction are probabilistic. Submitted imagery, OCR text, and source-time COLA metadata provide complementary evidence, but products may still be misclassified when the label is ambiguous or incomplete.
  4. Barcode coverage — Some submissions have no visible or decodable barcode, and extraction can miss or misread one. Coverage is not complete, and the same barcode can appear on multiple approval records.
  5. Methodology evolution — COLA Cloud continuously improves its enrichment methods. This may cause field values to change between updates as accuracy improves.
Category classifications can stop at a non-leaf node when a more specific placement is not supported. See the category taxonomy guide for the field contract and Taxonomy 2.0 transition behavior.

​
Data Delivery

Licensed data is available through multiple channels:
  • Snowflake Data Share — Direct access in your Snowflake account, updated weekly (learn more)
  • S3 Export — Parquet or CSV files delivered to your S3 bucket
  • REST API — Programmatic access with structured queries and filtering (quickstart)
  • MCP Server — AI-native access for LLM-powered applications (learn more)

​
Questions?

Contact help@colacloud.us or explore the COLA API reference for full schema details.