Implement Enhanced Indexing as a Portfolio Optimizer. And implemented a structured covariance estimator to boost the optimization process.

Description

Enhanced Indexing is a popular portfolio construction strategy. It's one of the index-tracking strategies, which means the possibility of both alpha and rather tender volatility.

A structured covariance estimator assumes observations can be predicted by multiple factors X = FB + U where F can be specified by explicit risk factors or latent factors. Therefore the structured covariance can be estimated by cov(X) = F cov(B) F.T + cov(U).

Motivation and Context

This pull request makes no change to current functions. It simply adds new featrues. Enhanced Indexing is a popular portfolio construction strategy while a structured covariance estimator will boost many optimization-based portfolio construction strategies.

How Has This Been Tested?

• Pass the test by running: pytest qlib/tests/test_all_pipeline.py under the upper directory of qlib.
• If you are adding a new feature, test on your own test scripts.

Screenshots of Test Results (if appropriate):

1. Pipeline test:

• Add test_structured_cov_estimator.py to qlib/tests/

• Write another script to test Enhanced Indexing Optimizer. However, this test requires private data (history weights of an index), so I didn't add this one to qlib/tests/. You could find the test file at https://drive.google.com/file/d/1eKO6OcyPZjR2PEGZ2zyZByKUbgVyAwII/view?usp=sharing.

Types of changes

• Fix bugs
• Add new feature
• Update documentation