# Mood

At Nuvolari, risk is the true north metric, but it's never monolithic - it’s contextual. Traditional models assign risk by weighting wallet positions and outputting fixed scores. That misses the dynamism of this industry: its velocity, cross-chain movements, shifting liquidity, and behaviour-driven exposure.

<figure><img src="/files/eephyW5Wnop54lVHzuHP" alt=""><figcaption></figcaption></figure>

We are well aware that users operate across multiple wallets, Nuvolari reconstructs the on chain behaviour over time, linking activity and historical trades to build a highly accurate map of user preferences.

* Analysing wallet history, transaction types and patterns, and the assets and chains users favour, we can identify loyalty to certain protocols - often shaped by deep personal experience, trust factors, social validation, UI/UX quirks, or just gut feeling.

This creates a compound trust factor that helps predict future wallet behaviour. We compute 50+ features—from portfolio concentration and transaction velocity to CEX interactions and behavioural consistency—then benchmark users against representative datasets. By matching individual risk assessments with opportunity-specific risk profiles, we deliver truly personalised recommendations.

> The approach is so tailored that it’s not a "risk" score anymore it’s a mood - our way of capturing both the hard numbers and the soft signals that define how a user actually lives and breathes crypto assets.

> f(recommendation) = weight1 · H(opportunity, history) + weight2 · P(opportunity, portfolio, R\_historic) + weight3 · R(opportunity, R\_historic, R\_selected)

> H = history match score \
> P = portfolio match score (discounted by historic risk) \
> R = risk alignment score \
> R\_historic = calculated from user's past behaviour \
> R\_selected = user's stated risk preference


---

# 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://docs.nuvolari.ai/ai-engine/mood.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.