Skip to content

Implement Enhanced Indexing as a Portfolio Optimizer#280

Merged
you-n-g merged 32 commits intomicrosoft:mainfrom
yongzhengqi:main
Mar 17, 2021
Merged

Implement Enhanced Indexing as a Portfolio Optimizer#280
you-n-g merged 32 commits intomicrosoft:mainfrom
yongzhengqi:main

Conversation

@yongzhengqi
Copy link
Contributor

@yongzhengqi yongzhengqi commented Feb 22, 2021 •
edited
Loading

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:

pipeline_test

2. Your own tests:
  • Add test_structured_cov_estimator.py to qlib/tests/

image

image

Types of changes

  • Fix bugs
  • Add new feature
  • Update documentation
Charles Young and others added 15 commits February 9, 2021 20:28
Add Structured Covariance Estimator to riskmodel.py
988b42e
Add an implementation of Enhanced Indexing to optimizer.py
7b01c5c
Add an implementation of Enhanced Indexing to optimizer.py
9c2653f
Separate specific implementation of Portfolio Optimizer to folder.
4000518
Applied slight modification to follow PEP 8.
b2e2142
Fix minor mismatches of type hints.
2cc057e
Add a abstract class as the base class for all optimization related p…
9448a6e 
…ortfolio constructions.
Reformat code to follow PEP 8.
42f8825
Merge optimization related portfolio construction back to portfolio/o…
f7d3e56 
…ptimizer.
Reformat code to follow PEP 8.
58f74cf
Add scikit-learn to dependencies.
164687d
Reformat code to follow PEP 8.
b8647c1
Reformat code with black.
2f9d45e
@yongzhengqi
Format code with the latest version of black.
3787138
@Derek-Wds
Black format
dc4aa67
@Derek-Wds Derek-Wds requested review from evanzd and you-n-g February 22, 2021 03:46
evanzd
evanzd reviewed Feb 22, 2021
View reviewed changes
evanzd
evanzd reviewed Feb 22, 2021
View reviewed changes
@Derek-Wds Derek-Wds added the enhancement New feature or request label Feb 22, 2021
evanzd
evanzd reviewed Mar 8, 2021
View reviewed changes
evanzd
evanzd reviewed Mar 8, 2021
View reviewed changes
evanzd
evanzd reviewed Mar 8, 2021
View reviewed changes
evanzd
evanzd reviewed Mar 8, 2021
View reviewed changes
evanzd
evanzd reviewed Mar 8, 2021
View reviewed changes
evanzd
evanzd reviewed Mar 8, 2021
View reviewed changes
evanzd
evanzd reviewed Mar 8, 2021
View reviewed changes
evanzd
evanzd reviewed Mar 8, 2021
View reviewed changes
evanzd
evanzd reviewed Mar 8, 2021
View reviewed changes
evanzd
evanzd reviewed Mar 8, 2021
View reviewed changes
evanzd
evanzd suggested changes Mar 8, 2021
View reviewed changes
Copy link
Contributor

@evanzd evanzd left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Comments have been added. Please update your commits accordingly.
Charles Young added 11 commits March 8, 2021 17:09
Pass nan_option to structured covariance estimator.
79c1142
Resolve https://github.com/microsoft/qlib/pull/280\#discussion_r58916…
4d5a30b 
…7776
Update test to cover changes in structured_cov_estimator
81b86f8
Resolve https://github.com/microsoft/qlib/pull/280\#discussion_r58916…
351d598 
…5409
Resolve https://github.com/microsoft/qlib/pull/280\#discussion_r58916…
c6675be 
…6143
Resolve https://github.com/microsoft/qlib/pull/280\#discussion_r58916…
fc89fec 
…8764
Resolve https://github.com/microsoft/qlib/pull/280\#discussion_r58916…
2f9af1a 
…9769
Resolve https://github.com/microsoft/qlib/pull/280\#discussion_r58916…
7022675 
…9489
Resolve https://github.com/microsoft/qlib/pull/280\#discussion_r58916…
6a305c7 
…6529
Reformat with black.
8b9065c
Reformat with black.
53cf89d
@yongzhengqi yongzhengqi marked this pull request as ready for review March 8, 2021 12:48
@yongzhengqi
Copy link
Contributor Author

yongzhengqi commented Mar 8, 2021

Comments have been added. Please update your commits accordingly.

All done.
@you-n-g you-n-g merged commit 023c1fe into microsoft:main Mar 17, 2021
@evanzd evanzd mentioned this pull request Dec 19, 2021
Merged
1 task
you-n-g pushed a commit to you-n-g/qlib that referenced this pull request Aug 16, 2025
@xisen-w @WinstonLiyt
feat: Feature selection v3 to support all actions (microsoft#280)
0047641 
* Update feedback.py to support all actions

Feedback.py is updated to support all actions.

* Update prompts.yaml to support all actions

* Revised for CI

* CI

* fix a ci bug

* fix a ci bug

---------

Co-authored-by: WinstonLiye <1957922024@qq.com>
gaogen123 pushed a commit to gaogen123/qlib that referenced this pull request Sep 13, 2025
@you-n-g
Merge pull request microsoft#280 from yongzhengqi/main
4994faf 
Implement Enhanced Indexing as a Portfolio Optimizer
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request

4 participants

@yongzhengqi @evanzd @you-n-g @Derek-Wds