feat: optuna

[Satvik-Singh192]

Description

This PR integrates Optuna hyperparameter optimization with pruning support into the quantitative research framework. The implementation automates hyperparameter search for factor-based strategies, enabling efficient optimization of trading strategy parameters.

Key Changes

• New tuning/optuna_runner.py module: Core Optuna integration with support for:

  • Automated hyperparameter search with pruning
  • Early stopping of bad trials (MedianPruner, PercentilePruner)
  • Optional RDB storage for distributed tuning runs (SQLite, PostgreSQL, MySQL)
  • Customizable objective functions for backtest-based optimization
  • Trial history tracking and result persistence

• New CLI command autotune: Command-line interface for hyperparameter tuning with:

  • YAML configuration file support
  • Command-line options for all parameters
  • Integration with existing backtest infrastructure
  • Support for optimizing momentum, volatility, and other factors

• Example YAML configuration: examples/autotune_config.yaml demonstrating all configuration options

• Dependencies: Added optuna>=3.0.0 and pyyaml>=6.0 to project dependencies

• Documentation: Updated README with comprehensive autotune documentation and usage examples

Testing

• pytest passes locally
• Linting passes (ruff, black)

Semver Changes

• Patch (bug fix, no new features)
• Minor (new features, no breaking changes)
• Major (breaking changes)

Issues

Closes #95 - autotune: integrate Optuna hyperparameter optimization + pruning

Checklist

• I have read the Contributing Guidelines.

[netlify]

✅ Deploy Preview for strong-duckanoo-898b2c ready!

Name	Link
🔨 Latest commit	4a3dda8
🔍 Latest deploy log	https://app.netlify.com/projects/strong-duckanoo-898b2c/deploys/6915fef93bb7d70008b48e69
😎 Deploy Preview	https://deploy-preview-121--strong-duckanoo-898b2c.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.

[netlify]

✅ Deploy Preview for qrsopcode canceled.

Name	Link
🔨 Latest commit	8f2cbe7
🔍 Latest deploy log	https://app.netlify.com/projects/qrsopcode/deploys/6914488dddb7ae0008ef490d

[Copilot]

Pull Request Overview

This PR integrates Optuna hyperparameter optimization into the quantitative research framework, enabling automated hyperparameter tuning for factor-based trading strategies with support for early stopping via pruning and distributed optimization via RDB storage.

Key changes:

• Added Optuna integration with pruning strategies (MedianPruner, PercentilePruner) for efficient hyperparameter search
• Implemented new autotune CLI command with YAML configuration support for optimizing momentum, volatility, and other factors
• Added dependencies for optuna>=3.0.0 and pyyaml>=6.0 to support the new functionality

Reviewed Changes

Copilot reviewed 6 out of 6 changed files in this pull request and generated 7 comments.

Show a summary per file

File	Description
src/quant_research_starter/tuning/optuna_runner.py	Core Optuna integration implementing OptunaRunner class, backtest objective function factory, and hyperparameter suggestion utilities
src/quant_research_starter/tuning/init.py	Module initialization exporting OptunaRunner
src/quant_research_starter/cli.py	Added autotune CLI command with options for data file, factor type, trials, metrics, storage, and pruning configuration
pyproject.toml	Added optuna and pyyaml dependencies
examples/autotune_config.yaml	Example YAML configuration demonstrating all tuning options
README.md	Documentation for hyperparameter tuning feature with usage examples

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.