# Weight Optimization

`Tutorials` are the best documentation — [<mark style="color:blue;">`Weight Optimization Tutorial`</mark>](https://colab.research.google.com/github/sovai-research/sovai-public/blob/main/notebooks/studies/Weight%20Optimization.ipynb)

### Key Features

* Multiple optimization strategies
* Comprehensive performance analysis
* Risk-adjusted return metrics
* Portfolio composition visualization
* Drawdown and contribution analysis
* Correlation and clustering analysis
* Daily weight tracking

### Usage

To use the Weight Optimization module, you first need to prepare your dataset. Here's an example of how to set up and run the optimization:

<pre class="language-python"><code class="lang-python">import sovai as sov

# Authenticate
sov.token_auth(token="your_authentication_token")

# Prepare your data
df_price = sov.data("market/closeadj")
df_mega = df_price.select_stocks("mega").date_range("2000-01-01")
df_returns = df_mega.calculate_returns().dropna(axis=1, how="any")

# Select the most uncorrelated stocks
feature_importance = df_returns.importance()
df_select = df_returns[feature_importance["feature"].head(25)]

# Run weight optimization
<a data-footnote-ref href="#user-content-fn-1">portfolio</a> = df_select.weight_optimization()
</code></pre>

## Overall Portfolio Analysis

### **Sharpe Ratio Distribution**

Shows the distribution of Sharpe ratios across different strategies, helping to understand the consistency of risk-adjusted returns.

<pre class="language-python"><code class="lang-python"><a data-footnote-ref href="#user-content-fn-1">portfolio</a>.sharpe_plot
</code></pre>

<figure><img src="/files/AVzlWsDpHS6bj6hn7VJY" alt=""><figcaption></figcaption></figure>

### **Cumulative Returns Plot**

Displays the cumulative returns of all portfolio strategies over time, allowing for easy comparison of overall performance.

<pre class="language-python"><code class="lang-python"><a data-footnote-ref href="#user-content-fn-1">portfolio</a>.return_plot
</code></pre>

<figure><img src="/files/zEn5pgkGLPVgN1fkNER1" alt=""><figcaption></figcaption></figure>

### **Overall Composition Plot**

Illustrates the asset allocation of all strategies, allowing for a comparison of how different models allocate capital.

<pre class="language-python"><code class="lang-python"><a data-footnote-ref href="#user-content-fn-1">portfolio</a>.composition_plot
</code></pre>

<figure><img src="/files/SyqWH87L4Nl16WcwXLFJ" alt=""><figcaption></figcaption></figure>

### **Best Performing Model**

Identifies the strategy that performed best according to the Sharpe ratio.

<pre class="language-python"><code class="lang-python"><a data-footnote-ref href="#user-content-fn-1">portfolio</a>.best_model
</code></pre>

```
'NCO'
```

### **Performance Summary**

Provides a comprehensive summary of key performance metrics for all strategies, including returns, volatility, Sharpe ratio, and more.

<pre class="language-python"><code class="lang-python"><a data-footnote-ref href="#user-content-fn-1">portfolio</a>.performance_report
</code></pre>

<figure><img src="/files/8d3arZwf6pFsaAlwfqUi" alt=""><figcaption></figcaption></figure>

## Model-Specific Analysis

For model-specific analysis, replace "model\_name" with the actual model name (e.g., HRP, HERC, NCO, or EQUAL).

### **Cumulative Returns**

<pre class="language-python"><code class="lang-python"><a data-footnote-ref href="#user-content-fn-1">portfolio</a>["model_name"].backtest_plot
</code></pre>

<figure><img src="/files/XeaxKWzL0lPfaC3Xin9q" alt=""><figcaption></figcaption></figure>

Displays the cumulative returns of the specific model over the backtesting period.

### **Backtest Report**

Detailed performance statistics from the backtesting period for the specific model.

<pre class="language-python"><code class="lang-python"><a data-footnote-ref href="#user-content-fn-1">portfolio</a>["model_name"].backtest_report
</code></pre>

<figure><img src="/files/BSQSFqASZHq9u0KmPVhX" alt=""><figcaption></figcaption></figure>

### **Rolling Sharpe Ratio**

Visualizes how the Sharpe ratio of the model changes over time, indicating consistency of performance.

<pre class="language-python"><code class="lang-python"><a data-footnote-ref href="#user-content-fn-1">portfolio</a>["model_name"].sharpe_rolling_plot
</code></pre>

<figure><img src="/files/5EH4ZFt4PSd8ceuAHC1A" alt=""><figcaption></figcaption></figure>

### **Model Composition**

Illustrates the asset allocation for the specific model.

<pre class="language-python"><code class="lang-python"><a data-footnote-ref href="#user-content-fn-1">portfolio</a>["model_name"].composition_plot
</code></pre>

<figure><img src="/files/Bcs8tyHccdOWFQ3yBiEg" alt=""><figcaption></figcaption></figure>

### **Drawdown Contribution**

Shows which assets contribute most to the portfolio's drawdowns, helping identify risk sources.

<pre class="language-python"><code class="lang-python"><a data-footnote-ref href="#user-content-fn-1">portfolio</a>["model_name"].drawdown_contribution_plot
</code></pre>

<figure><img src="/files/DzqhJmiaKdTzKiiLxe1r" alt=""><figcaption></figcaption></figure>

### **Sharpe Ratio Contribution**

Indicates which assets contribute most to the portfolio's Sharpe ratio, highlighting return drivers.

<pre class="language-python"><code class="lang-python"><a data-footnote-ref href="#user-content-fn-1">portfolio</a>["model_name"].sharpe_contribution_plot
</code></pre>

<figure><img src="/files/744RwC5gNufmu2FzJmvD" alt=""><figcaption></figcaption></figure>

### **Correlation Heatmap**

Displays the correlation structure of assets used in the model (not available for EQUAL).

<pre class="language-python"><code class="lang-python"><a data-footnote-ref href="#user-content-fn-1">portfolio</a>["model_name"].heatmap_plot
</code></pre>

<figure><img src="/files/f11sSY84UcvE8nWPFYJ7" alt=""><figcaption></figcaption></figure>

### **Clustering Dendrogram**

Visualizes the hierarchical clustering of assets used in the model (not available for EQUAL).

<pre class="language-python"><code class="lang-python"><a data-footnote-ref href="#user-content-fn-1">portfolio</a>["model_name"].cluster_plot
</code></pre>

<figure><img src="/files/i3NI4U6ASrzetKFVBcmD" alt=""><figcaption></figcaption></figure>

### **Current Recommended Allocation**

Provides the model's most recent recommended asset allocation.

<pre class="language-python"><code class="lang-python"><a data-footnote-ref href="#user-content-fn-1">portfolio</a>["model_name"].recommended_allocation
</code></pre>

<figure><img src="/files/CvguDYlaJsLBB6vMMD4x" alt=""><figcaption></figcaption></figure>

### **Sharpe Ratio Distribution**

Shows the distribution of Sharpe ratio helping to understand the consistency of risk-adjusted returns.

<pre class="language-python"><code class="lang-python"><a data-footnote-ref href="#user-content-fn-1">portfolio</a>["model_name"].recommended_allocation
</code></pre>

<figure><img src="/files/SOp32Hp8xg5Dd8O7XtEK" alt=""><figcaption></figcaption></figure>

### **Daily Weights**

Shows how the model's asset allocation changes day-by-day over the backtesting period.

<pre class="language-python"><code class="lang-python"><a data-footnote-ref href="#user-content-fn-1">portfolio</a>["model_name"].daily_weights
</code></pre>

<figure><img src="/files/wSD4hmJb2FgsmZJcaAFV" alt=""><figcaption></figcaption></figure>

[^1]: class module


---

# 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.sov.ai/asset-managment/weight-optimization.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.