# Mozaic AI Paper: Beyond Traditional Models

This document explores the innovative application of machine learning techniques within a portfolio optimization framework, surpassing traditional methods like mean-variance optimization. The paper introduces the use of machine learning models to predict returns, yields, and volatilities for GMX pools, integrating these predictions seamlessly into the portfolio construction process.

**Key highlights include:**

* **Machine Learning for Prediction:** Utilizing historical data and various influencing factors, machine learning models generate accurate predictions for GMX pool behavior.
* **Integration into Optimization:** The predicted returns and covariances are integrated into the portfolio optimization framework, accounting for the unique risk-return profile of GMX pools.
* **Results and Significance:** The findings demonstrate significant improvements in portfolio performance, with higher cumulative returns and superior Sharpe Ratios compared to benchmark portfolios.

This paper provides valuable insights into the effectiveness of machine learning-driven approaches for enhancing investment strategies in the dynamic cryptocurrency market.

[<mark style="color:yellow;">View the PDF</mark>](https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-MiihhDZYtNvGU8rJ3vI%2Fuploads%2FoIyoQozAjsu3LZz7jCT2%2FMozaic%20AI%20Paper%20-%20Beyond%20Traditional%20Models.pdf?alt=media\&token=1783af7d-4f40-40ba-bdd6-6496c0585249)


---

# 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.mozaic.finance/archimedes/ai-fi/mozaic-ai-paper-beyond-traditional-models.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.