> For the complete documentation index, see [llms.txt](https://docs.sportradar.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.sportradar.com/mts/features/automatic-ccf-adjustments.md).

# Automatic CCF Adjustments

Customer Confidence Factor (CCF) is a numerical factor representing the level at which the customers overall account liability limit has been set (regular, restricted, VIP), affecting the bet acceptance process. It is generally configured by the team of risk analysts in relation to the betting activity and staking patterns that take place on the account.

MTS uses AI model to generate suggested CCF. The idea behind the model is to use machine learning techniques to mimic the logic and mechanics applied by risk analysts. It runs daily and checks all accounts that have been active the previous day. For those, several features are generated, representing customer's betting behaviour. The model attempts to use tickets that the customer wanted to place, not only the tickets which MTS accepted. The features can be divided in following groups:

* account statistics (e.g. profitability, turnover, average stake),
* account sport activity statistics (proportions of turnover customer placed on a sport),
* account categories activity statistics (proportions of turnover customer placed on a category),
* account market activity statistics (proportions of turnover customer placed on a market),
* account to match performance statistics (comparing customer tickets to all tickets with the same matches),
* account to market performance statistics (comparing customer tickets to all tickets with the same sport, category and market),
* significance of account's profit/loss (checking the probability that the player does not have an edge compared to MTS, based on Monte Carlo simulations with the same ticket probabilities, odds and stakes of his last 1000 tickets).

Automated CCF is an option to enable automatic adjustment of CCF based on the model suggested CCF. The goal of this feature is to automate customer profiling with the use of AI model. Risk analysts still have an option to manually adjust CCF but with the use of Automated CCF the proportion of profiled accounts greatly increases. It can be enabled/disabled on a bookmaker/sub-bookmaker level or on individual customer level. It is configurable with these parameters:

* input range (an account must have the current CCF inside this range to be eligible for an automatic adjustment),
* output range (determines how far the CCF value can go with automatic adjustment),
* % difference (represents proportion of difference between CCF and model suggested CCF that can be applied in one step, making auto adjustments more gradual)
* delay for next auto adjustment


---

# 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:

```
GET https://docs.sportradar.com/mts/features/automatic-ccf-adjustments.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.