# AI / ML Core

At the heart of Selen AI lies a sophisticated artificial intelligence engine that drives decision-making across all features. This core comprises:

* **Time-Series Transformers**: Analyze historical token price movements and liquidity inflows to anticipate short-term trends and market reactions.
* **Gradient-Boosted Decision Trees (GBDTs)**: Evaluate structured data such as token metadata, pool statistics, and developer behavior for predictive scoring.
* **Graph Neural Networks (GNNs)**: Model relationships between wallets, token contracts, and liquidity pools to detect hidden risk vectors and identify influential actors.

These models work together to generate real-time scores for:

* **Pool Quality**
* **Liquidity Shock Impact**
* **Trader Skill-Level & Alpha Potential**

![](https://lh7-rt.googleusercontent.com/docsz/AD_4nXcHU-Oq8BsNrDE8OaHn40UnsszqPdla-BcOxzqZsIAuG4RoBNMr2e6zTyp8kDR6rIk4w54WKz5KSaICEOsb_Oiekfo05Wm_NpQP0dV_mUggU4NqYHHT_QuI4Av6jdI5aRv7Us8AVQ?key=pLJLFHzbL-FOIiOqLBYN8lsL)


---

# Agent Instructions: 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://selen-ai.gitbook.io/selen-ai/selen-ai-architecture/ai-ml-core.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.