Machine learning portfolio allocation
We find economically and statistically significant gains when using machine learning for portfolio allocation between the market index and risk-free asset. Optimal portfolio rules for time-varying expected returns and volatility are implemented with two Random Forest models. One model is employed in...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2022-11-01
|
| Series: | Journal of Finance and Data Science |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405918821000155 |
| _version_ | 1797903406170374144 |
|---|---|
| author | Michael Pinelis David Ruppert |
| author_facet | Michael Pinelis David Ruppert |
| author_sort | Michael Pinelis |
| collection | DOAJ |
| description | We find economically and statistically significant gains when using machine learning for portfolio allocation between the market index and risk-free asset. Optimal portfolio rules for time-varying expected returns and volatility are implemented with two Random Forest models. One model is employed in forecasting monthly excess returns with macroeconomic factors including payout yields. The second is used to estimate the prevailing volatility. Reward-risk timing with machine learning provides substantial improvements over the buy-and-hold in utility, risk-adjusted returns, and maximum drawdowns. This paper presents a unifying framework for machine learning applied to both return- and volatility-timing. |
| first_indexed | 2024-04-10T09:32:22Z |
| format | Article |
| id | doaj.art-ce89550663b5468daaf99796264690c2 |
| institution | Directory Open Access Journal |
| issn | 2405-9188 |
| language | English |
| last_indexed | 2024-04-10T09:32:22Z |
| publishDate | 2022-11-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Journal of Finance and Data Science |
| spelling | doaj.art-ce89550663b5468daaf99796264690c22023-02-19T04:26:21ZengKeAi Communications Co., Ltd.Journal of Finance and Data Science2405-91882022-11-0183554Machine learning portfolio allocationMichael Pinelis0David Ruppert1Department of Economics, Cornell University, 404 Uris Hall, Ithaca, NY 14853, USA; Corresponding author. 222 East 39th Street, New York, NY 10016, USA.Department of Statistics & Data Science, Cornell University, 1170 Comstock Hall Cornell University, Ithaca, NY 14853, USA; School of Operations Research and Information Engineering, Cornell University, 238 Rhodes Hall Cornell University Ithaca, NY 14853, USAWe find economically and statistically significant gains when using machine learning for portfolio allocation between the market index and risk-free asset. Optimal portfolio rules for time-varying expected returns and volatility are implemented with two Random Forest models. One model is employed in forecasting monthly excess returns with macroeconomic factors including payout yields. The second is used to estimate the prevailing volatility. Reward-risk timing with machine learning provides substantial improvements over the buy-and-hold in utility, risk-adjusted returns, and maximum drawdowns. This paper presents a unifying framework for machine learning applied to both return- and volatility-timing.http://www.sciencedirect.com/science/article/pii/S2405918821000155Portfolio allocationFinanceMachine learningRandom forestMarket timingReward-risk timing |
| spellingShingle | Michael Pinelis David Ruppert Machine learning portfolio allocation Journal of Finance and Data Science Portfolio allocation Finance Machine learning Random forest Market timing Reward-risk timing |
| title | Machine learning portfolio allocation |
| title_full | Machine learning portfolio allocation |
| title_fullStr | Machine learning portfolio allocation |
| title_full_unstemmed | Machine learning portfolio allocation |
| title_short | Machine learning portfolio allocation |
| title_sort | machine learning portfolio allocation |
| topic | Portfolio allocation Finance Machine learning Random forest Market timing Reward-risk timing |
| url | http://www.sciencedirect.com/science/article/pii/S2405918821000155 |
| work_keys_str_mv | AT michaelpinelis machinelearningportfolioallocation AT davidruppert machinelearningportfolioallocation |