Supervised Machine Learning Classification for Short Straddles on the S&P500
In this paper, we apply machine learning models to execute certain short-option strategies on the S&P500. In particular, we formulate and focus on a supervised classification task which decides if a plain short straddle on the S&P500 should be executed or not on a daily basis. We describe ou...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Risks |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9091/10/12/235 |
| _version_ | 1827637054521999360 |
|---|---|
| author | Alexander Brunhuemer Lukas Larcher Philipp Seidl Sascha Desmettre Johannes Kofler Gerhard Larcher |
| author_facet | Alexander Brunhuemer Lukas Larcher Philipp Seidl Sascha Desmettre Johannes Kofler Gerhard Larcher |
| author_sort | Alexander Brunhuemer |
| collection | DOAJ |
| description | In this paper, we apply machine learning models to execute certain short-option strategies on the S&P500. In particular, we formulate and focus on a supervised classification task which decides if a plain short straddle on the S&P500 should be executed or not on a daily basis. We describe our used framework and present an overview of our evaluation metrics for different classification models. Using standard machine learning techniques and systematic hyperparameter search, we find statistically significant advantages if the gradient tree boosting algorithm is used, compared to a simple “trade always” strategy. On the basis of this work, we have laid the foundations for the application of supervised classification methods to more general derivative trading strategies. |
| first_indexed | 2024-03-09T15:54:00Z |
| format | Article |
| id | doaj.art-e7886146e540445aa9c3fc5dde40232a |
| institution | Directory Open Access Journal |
| issn | 2227-9091 |
| language | English |
| last_indexed | 2024-03-09T15:54:00Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Risks |
| spelling | doaj.art-e7886146e540445aa9c3fc5dde40232a2023-11-24T17:50:04ZengMDPI AGRisks2227-90912022-12-01101223510.3390/risks10120235Supervised Machine Learning Classification for Short Straddles on the S&P500Alexander Brunhuemer0Lukas Larcher1Philipp Seidl2Sascha Desmettre3Johannes Kofler4Gerhard Larcher5Institute for Financial Mathematics and Applied Number Theory, Johannes Kepler University Linz, AT-4040 Linz, AustriaInstitute for Financial Mathematics and Applied Number Theory, Johannes Kepler University Linz, AT-4040 Linz, AustriaInstitute for Machine Learning, Johannes Kepler University Linz, AT-4040 Linz, AustriaInstitute for Financial Mathematics and Applied Number Theory, Johannes Kepler University Linz, AT-4040 Linz, AustriaInstitute for Machine Learning, Johannes Kepler University Linz, AT-4040 Linz, AustriaInstitute for Financial Mathematics and Applied Number Theory, Johannes Kepler University Linz, AT-4040 Linz, AustriaIn this paper, we apply machine learning models to execute certain short-option strategies on the S&P500. In particular, we formulate and focus on a supervised classification task which decides if a plain short straddle on the S&P500 should be executed or not on a daily basis. We describe our used framework and present an overview of our evaluation metrics for different classification models. Using standard machine learning techniques and systematic hyperparameter search, we find statistically significant advantages if the gradient tree boosting algorithm is used, compared to a simple “trade always” strategy. On the basis of this work, we have laid the foundations for the application of supervised classification methods to more general derivative trading strategies.https://www.mdpi.com/2227-9091/10/12/235machine learningsupervised classificationgradient tree boostingoption trading strategiesshort straddlesS&P500 |
| spellingShingle | Alexander Brunhuemer Lukas Larcher Philipp Seidl Sascha Desmettre Johannes Kofler Gerhard Larcher Supervised Machine Learning Classification for Short Straddles on the S&P500 Risks machine learning supervised classification gradient tree boosting option trading strategies short straddles S&P500 |
| title | Supervised Machine Learning Classification for Short Straddles on the S&P500 |
| title_full | Supervised Machine Learning Classification for Short Straddles on the S&P500 |
| title_fullStr | Supervised Machine Learning Classification for Short Straddles on the S&P500 |
| title_full_unstemmed | Supervised Machine Learning Classification for Short Straddles on the S&P500 |
| title_short | Supervised Machine Learning Classification for Short Straddles on the S&P500 |
| title_sort | supervised machine learning classification for short straddles on the s p500 |
| topic | machine learning supervised classification gradient tree boosting option trading strategies short straddles S&P500 |
| url | https://www.mdpi.com/2227-9091/10/12/235 |
| work_keys_str_mv | AT alexanderbrunhuemer supervisedmachinelearningclassificationforshortstraddlesonthesp500 AT lukaslarcher supervisedmachinelearningclassificationforshortstraddlesonthesp500 AT philippseidl supervisedmachinelearningclassificationforshortstraddlesonthesp500 AT saschadesmettre supervisedmachinelearningclassificationforshortstraddlesonthesp500 AT johanneskofler supervisedmachinelearningclassificationforshortstraddlesonthesp500 AT gerhardlarcher supervisedmachinelearningclassificationforshortstraddlesonthesp500 |