Dynamic Covariance Estimation under Structural Assumptions via a Joint Optimization Approach
Dynamic covariance estimation is a problem of fundamental importance in statistics, econometrics, with important applications in finance, especially portfolio optimization. While there is a large body of work on static covariance estimation, the current literature on dynamic covariance estimation is...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
ACM|4th ACM International Conference on AI in Finance
2023
|
| Online Access: | https://hdl.handle.net/1721.1/153141 |
| _version_ | 1811087644050849792 |
|---|---|
| author | Chen, Wenyu Benbaki, Riade Zhu, Yada Mazumder, Rahul |
| author2 | Massachusetts Institute of Technology. Operations Research Center |
| author_facet | Massachusetts Institute of Technology. Operations Research Center Chen, Wenyu Benbaki, Riade Zhu, Yada Mazumder, Rahul |
| author_sort | Chen, Wenyu |
| collection | MIT |
| description | Dynamic covariance estimation is a problem of fundamental importance in statistics, econometrics, with important applications in finance, especially portfolio optimization. While there is a large body of work on static covariance estimation, the current literature on dynamic covariance estimation is somewhat limited in comparison. We propose a flexible optimization framework to simultaneously learn covariance matrices across different time periods under suitable structural assumptions on the period-specific covariance matrices and time-varying regularizers. We propose a novel efficient joint optimization algorithm to learn the covariance matrices simultaneously. Our numerical experiments demonstrate the computation improvements of our algorithm over both off-the-shelf solvers and other dynamic covariance estimation methods. We also see notable gains in terms of test MSE and downstream portfolio optimization tasks on both synthetic and real datasets. |
| first_indexed | 2024-09-23T13:49:44Z |
| format | Article |
| id | mit-1721.1/153141 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T13:49:44Z |
| publishDate | 2023 |
| publisher | ACM|4th ACM International Conference on AI in Finance |
| record_format | dspace |
| spelling | mit-1721.1/1531412024-01-11T19:43:08Z Dynamic Covariance Estimation under Structural Assumptions via a Joint Optimization Approach Chen, Wenyu Benbaki, Riade Zhu, Yada Mazumder, Rahul Massachusetts Institute of Technology. Operations Research Center MIT-IBM Watson AI Lab Dynamic covariance estimation is a problem of fundamental importance in statistics, econometrics, with important applications in finance, especially portfolio optimization. While there is a large body of work on static covariance estimation, the current literature on dynamic covariance estimation is somewhat limited in comparison. We propose a flexible optimization framework to simultaneously learn covariance matrices across different time periods under suitable structural assumptions on the period-specific covariance matrices and time-varying regularizers. We propose a novel efficient joint optimization algorithm to learn the covariance matrices simultaneously. Our numerical experiments demonstrate the computation improvements of our algorithm over both off-the-shelf solvers and other dynamic covariance estimation methods. We also see notable gains in terms of test MSE and downstream portfolio optimization tasks on both synthetic and real datasets. 2023-12-12T14:24:20Z 2023-12-12T14:24:20Z 2023-11-27 2023-12-01T08:48:17Z Article http://purl.org/eprint/type/ConferencePaper 979-8-4007-0240-2 https://hdl.handle.net/1721.1/153141 Chen, Wenyu, Benbaki, Riade, Zhu, Yada and Mazumder, Rahul. 2023. "Dynamic Covariance Estimation under Structural Assumptions via a Joint Optimization Approach." PUBLISHER_CC en https://doi.org/10.1145/3604237.3626885 Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ The author(s) application/pdf ACM|4th ACM International Conference on AI in Finance Association for Computing Machinery |
| spellingShingle | Chen, Wenyu Benbaki, Riade Zhu, Yada Mazumder, Rahul Dynamic Covariance Estimation under Structural Assumptions via a Joint Optimization Approach |
| title | Dynamic Covariance Estimation under Structural Assumptions via a Joint Optimization Approach |
| title_full | Dynamic Covariance Estimation under Structural Assumptions via a Joint Optimization Approach |
| title_fullStr | Dynamic Covariance Estimation under Structural Assumptions via a Joint Optimization Approach |
| title_full_unstemmed | Dynamic Covariance Estimation under Structural Assumptions via a Joint Optimization Approach |
| title_short | Dynamic Covariance Estimation under Structural Assumptions via a Joint Optimization Approach |
| title_sort | dynamic covariance estimation under structural assumptions via a joint optimization approach |
| url | https://hdl.handle.net/1721.1/153141 |
| work_keys_str_mv | AT chenwenyu dynamiccovarianceestimationunderstructuralassumptionsviaajointoptimizationapproach AT benbakiriade dynamiccovarianceestimationunderstructuralassumptionsviaajointoptimizationapproach AT zhuyada dynamiccovarianceestimationunderstructuralassumptionsviaajointoptimizationapproach AT mazumderrahul dynamiccovarianceestimationunderstructuralassumptionsviaajointoptimizationapproach |