> For the complete documentation index, see [llms.txt](https://docs.crxtoken.xyz/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.crxtoken.xyz/page-5.-ai-credit-engine/5.3-model-families-and-analytical-tasks.md).

# 5.3 Model Families and Analytical Tasks

Different questions require different model families. The AI engine is therefore organized around a set of core analytical tasks.

For trend and stability analysis, time-series models examine trajectories of key metrics such as utilization, net discretionary income, and repayment buffers. They identify whether a user’s position is stable, improving, or deteriorating, and at what speed.

For behavioral segmentation, clustering and classification methods group users and behaviors into patterns such as “stable low-risk with predictable cash flow”, “high utilization but consistent repayment”, or “volatile income with emerging shortfalls”. These segments are not used to label individuals in a static way, but to improve the relevance of insights by comparing each user’s behavior to similar patterns observed historically.

For risk and stress detection, anomaly detection techniques monitor for unusual changes, such as rapid increases in short-term debt, repeated near-misses on repayment dates, or sudden shifts in discretionary spending. These models are tuned to minimize noise; their output is fed into downstream logic that decides which events should trigger user-facing alerts.

For opportunity identification, optimization routines and heuristic models evaluate potential actions. For example, they may estimate the benefit of changing payment timing, adjusting utilization on specific lines, or rebalancing between accounts. While Credit Express does not execute actions on behalf of the user, the engine can rank potential options by estimated impact on stability and long-term credit health.


---

# 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.crxtoken.xyz/page-5.-ai-credit-engine/5.3-model-families-and-analytical-tasks.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.