A general framework for portfolio construction based on generative models of asset returns
In this paper, we present an integrated approach to portfolio construction and optimization, leveraging high-performance computing capabilities. We first explore diverse pairings of generative model forecasts and objective functions used for portfolio optimization, which are evaluated using performa...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2023-11-01
|
| Series: | Journal of Finance and Data Science |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405918823000296 |
| _version_ | 1797383779069722624 |
|---|---|
| author | Tuoyuan Cheng Kan Chen |
| author_facet | Tuoyuan Cheng Kan Chen |
| author_sort | Tuoyuan Cheng |
| collection | DOAJ |
| description | In this paper, we present an integrated approach to portfolio construction and optimization, leveraging high-performance computing capabilities. We first explore diverse pairings of generative model forecasts and objective functions used for portfolio optimization, which are evaluated using performance-attribution models based on least absolute shrinkage and selection operator (LASSO). We illustrate our approach using extensive simulations of crypto-currency portfolios, and we show that the portfolios constructed using the vine-copula generative model and the Sharpe-ratio objective function consistently outperform. To accommodate a wide array of investment strategies, we further investigate portfolio blending and propose a general framework for evaluating and combining investment strategies. We employ an extension of the multi-armed bandit framework and use value models and policy models to construct eclectic blended portfolios based on past performance. We consider similarity and optimality measures for value models and employ probability-matching (“blending”) and a greedy algorithm (“switching”) for policy models. The eclectic portfolios are also evaluated using LASSO models. We show that the value model utilizing cosine similarity and logit optimality consistently delivers robust superior performances. The extent of outperformance by eclectic portfolios over their benchmarks significantly surpasses that achieved by individual generative model-based portfolios over their respective benchmarks. |
| first_indexed | 2024-03-08T21:25:53Z |
| format | Article |
| id | doaj.art-1957f7ef716b43d6ac51bc95f3ad764a |
| institution | Directory Open Access Journal |
| issn | 2405-9188 |
| language | English |
| last_indexed | 2024-03-08T21:25:53Z |
| publishDate | 2023-11-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Journal of Finance and Data Science |
| spelling | doaj.art-1957f7ef716b43d6ac51bc95f3ad764a2023-12-21T07:36:14ZengKeAi Communications Co., Ltd.Journal of Finance and Data Science2405-91882023-11-019100113A general framework for portfolio construction based on generative models of asset returnsTuoyuan Cheng0Kan Chen1Risk Management Institute, National University of Singapore, 04-03 Heng Mui Keng Terrace, I3 Building, Singapore, 119613, Singapore; Corresponding author.Risk Management Institute, National University of Singapore, 04-03 Heng Mui Keng Terrace, I3 Building, Singapore, 119613, Singapore; Department of Mathematics, National University of Singapore, Level 4, Block S17, 10 Lower Kent Ridge Road, Singapore, 119076, SingaporeIn this paper, we present an integrated approach to portfolio construction and optimization, leveraging high-performance computing capabilities. We first explore diverse pairings of generative model forecasts and objective functions used for portfolio optimization, which are evaluated using performance-attribution models based on least absolute shrinkage and selection operator (LASSO). We illustrate our approach using extensive simulations of crypto-currency portfolios, and we show that the portfolios constructed using the vine-copula generative model and the Sharpe-ratio objective function consistently outperform. To accommodate a wide array of investment strategies, we further investigate portfolio blending and propose a general framework for evaluating and combining investment strategies. We employ an extension of the multi-armed bandit framework and use value models and policy models to construct eclectic blended portfolios based on past performance. We consider similarity and optimality measures for value models and employ probability-matching (“blending”) and a greedy algorithm (“switching”) for policy models. The eclectic portfolios are also evaluated using LASSO models. We show that the value model utilizing cosine similarity and logit optimality consistently delivers robust superior performances. The extent of outperformance by eclectic portfolios over their benchmarks significantly surpasses that achieved by individual generative model-based portfolios over their respective benchmarks.http://www.sciencedirect.com/science/article/pii/S2405918823000296Portfolio constructionGenerative modelMulti-armed banditPortfolio blendingCryptocurrency |
| spellingShingle | Tuoyuan Cheng Kan Chen A general framework for portfolio construction based on generative models of asset returns Journal of Finance and Data Science Portfolio construction Generative model Multi-armed bandit Portfolio blending Cryptocurrency |
| title | A general framework for portfolio construction based on generative models of asset returns |
| title_full | A general framework for portfolio construction based on generative models of asset returns |
| title_fullStr | A general framework for portfolio construction based on generative models of asset returns |
| title_full_unstemmed | A general framework for portfolio construction based on generative models of asset returns |
| title_short | A general framework for portfolio construction based on generative models of asset returns |
| title_sort | general framework for portfolio construction based on generative models of asset returns |
| topic | Portfolio construction Generative model Multi-armed bandit Portfolio blending Cryptocurrency |
| url | http://www.sciencedirect.com/science/article/pii/S2405918823000296 |
| work_keys_str_mv | AT tuoyuancheng ageneralframeworkforportfolioconstructionbasedongenerativemodelsofassetreturns AT kanchen ageneralframeworkforportfolioconstructionbasedongenerativemodelsofassetreturns AT tuoyuancheng generalframeworkforportfolioconstructionbasedongenerativemodelsofassetreturns AT kanchen generalframeworkforportfolioconstructionbasedongenerativemodelsofassetreturns |