apps/website/src/app/docs/content/auto-categorization.mdx
Every transaction that flows into Midday is automatically categorized using AI. This saves hours of manual work and keeps your books organized for accounting.
When a new transaction arrives, Midday's AI:
The AI learns from your corrections. The more you use Midday, the more accurate it becomes for your specific business.
Midday uses a two-level category system designed for business accounting:
Each parent category contains specific subcategories. For example, Technology includes:
See all categories and subcategories →
Some categories are "excluded" from burn rate calculations to prevent double-counting:
| Category | Why it's excluded |
|---|---|
| Credit Card Payment | The purchases on your card already count; the payment would be double-counting |
| Internal Transfer | Moving money between accounts isn't spending |
This happens automatically. Your burn rate and runway calculations stay accurate.
Learn more about how categories affect metrics →
If the AI gets it wrong:
For multiple similar transactions:
This is useful for:
The AI builds patterns based on merchant names:
When you correct a category:
The AI learns from your entire team's categorization choices, building a model specific to your business.
How you categorize transactions directly affects your reports:
| Metric | Affected by |
|---|---|
| Revenue | Transactions in Revenue categories |
| Burn Rate | All expense categories except excluded ones |
| Profit | Revenue minus expenses |
| Cash Flow | All income and expense categories |
Accurate categorization means accurate metrics.
When you export transactions, categories are included. Your accountant can map them to their chart of accounts.
If you connect Xero, QuickBooks, or Fortnox:
Categories are intentionally broad (for accounting). Use tags for additional detail:
Some merchants (like Amazon) could be many categories:
Correct these carefully. The AI will learn that Amazon transactions from your account might be different from another business.
Midday uses a standard category set that maps to accounting charts of accounts. This ensures consistency for exports and integrations. Use tags for custom groupings.
Choose the primary purpose. For example:
If a personal transaction accidentally appears:
Common reasons:
Correct it once, and the AI will learn.