TPFOpt: Portfolio Optimization for Tracking Stock Indices
Overview
This repository contains a Python implementation of a portfolio optimization framework for tracking stock indices. It is designed to construct tracking portfolios, such as those underlying ETFs, that replicate the performance of a target index.
Features
- Construction of index-tracking portfolios via optimized sampling
- Performance evaluation metrics, including concentration measures, risk measures, and tracking statistics
- Sector allocation analysis
- Turnover calculation and reporting
Results
The optimized portfolio weights and performance metrics are stored in a ResultsStore object, which can be saved to a file for further analysis.
Contributing
Contributions are welcome — please open an issue or submit a pull request to improve the code or the documentation.
Acknowledgments
This code was developed in the course of the research published as Feature selection based index tracking: A two-stage approach for optimized sampling.