> For the complete documentation index, see [llms.txt](https://guide.xs2a.com/xs2a/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://guide.xs2a.com/xs2a/integration-cs/additional-guides/the-facts-system/the-categorisation-engine.md).

# The Categorization Engine

A very common question is: how does your categorization engine work?

The details are rather complicated but we can outline the overall process as follows:

1. Certain situations are algorithmically "hardwired". For instance, will some return debit notes be generated by the bank systems according to specific rules that are catched in this first step.
2. The categorization engine executes a rule system that uses all kinds of available information, i.e. the account holder name, the turnover amounts and purposes, the counterparty names, IBANs and types and even turnover-spanning information like "this counterparty appears as being the employer of the account holder".
3. If several different categories are possible/likely, we employ an approach to select the most likely alternative of the possible alternatives.

In the future, we will add additional components to get better estimations for categories that are extremely difficult by nature (e.g. money transfer from one private person to another with a purpose of "dance, the king is in the mood").


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://guide.xs2a.com/xs2a/integration-cs/additional-guides/the-facts-system/the-categorisation-engine.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.