Interpretable trading pattern designed for machine learning applications
Financial markets are a source of non-stationary multidimensional time series which has been drawing attention for decades. Each financial instrument has its specific changing-over-time properties, making its analysis a complex task. Hence, improvement of understanding and development of more inform...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-03-01
|
| Series: | Machine Learning with Applications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2666827023000014 |
| _version_ | 1828012546647392256 |
|---|---|
| author | Artur Sokolovsky Luca Arnaboldi Jaume Bacardit Thomas Gross |
| author_facet | Artur Sokolovsky Luca Arnaboldi Jaume Bacardit Thomas Gross |
| author_sort | Artur Sokolovsky |
| collection | DOAJ |
| description | Financial markets are a source of non-stationary multidimensional time series which has been drawing attention for decades. Each financial instrument has its specific changing-over-time properties, making its analysis a complex task. Hence, improvement of understanding and development of more informative, generalisable market representations are essential for the successful operation in financial markets, including risk assessment, diversification, trading, and order execution.In this study, we propose a volume-price-based market representation for making financial time series more suitable for machine learning pipelines. We use a statistical approach for evaluating the representation. Through the research questions, we investigate, i) whether the proposed representation allows any improvement over the baseline (always-positive) performance; ii) whether the proposed representation leads to increased performance over the price levels market pattern; iii) whether the proposed representation performs better on the liquid markets, and iv) whether SHAP feature interactions are reliable to be used in the considered setting.Our analysis shows that the proposed volume-based method allows successful classification of the financial time series patterns, and also leads to better classification performance than the price levels-based method, excelling specifically on more liquid financial instruments. Finally, we propose an approach for obtaining feature interactions directly from tree-based models and compare the outcomes to those of the SHAP method. This results in the significant similarity between the two methods, hence we claim that SHAP feature interactions are reliable to be used in the setting of financial markets. |
| first_indexed | 2024-04-10T09:34:27Z |
| format | Article |
| id | doaj.art-94e9145a321c45c9b8b8105129464f94 |
| institution | Directory Open Access Journal |
| issn | 2666-8270 |
| language | English |
| last_indexed | 2024-04-10T09:34:27Z |
| publishDate | 2023-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Machine Learning with Applications |
| spelling | doaj.art-94e9145a321c45c9b8b8105129464f942023-02-18T04:17:42ZengElsevierMachine Learning with Applications2666-82702023-03-0111100448Interpretable trading pattern designed for machine learning applicationsArtur Sokolovsky0Luca Arnaboldi1Jaume Bacardit2Thomas Gross3Newcastle University, School of Computing, 1 Science Square, Newcastle upon, Tyne NE4 5TG, UK; Corresponding author.University of Edinburgh, School of Informatics, 10 Crichton St, Newington, Edinburgh EH8 9AB, UKNewcastle University, School of Computing, 1 Science Square, Newcastle upon, Tyne NE4 5TG, UKNewcastle University, School of Computing, 1 Science Square, Newcastle upon, Tyne NE4 5TG, UKFinancial markets are a source of non-stationary multidimensional time series which has been drawing attention for decades. Each financial instrument has its specific changing-over-time properties, making its analysis a complex task. Hence, improvement of understanding and development of more informative, generalisable market representations are essential for the successful operation in financial markets, including risk assessment, diversification, trading, and order execution.In this study, we propose a volume-price-based market representation for making financial time series more suitable for machine learning pipelines. We use a statistical approach for evaluating the representation. Through the research questions, we investigate, i) whether the proposed representation allows any improvement over the baseline (always-positive) performance; ii) whether the proposed representation leads to increased performance over the price levels market pattern; iii) whether the proposed representation performs better on the liquid markets, and iv) whether SHAP feature interactions are reliable to be used in the considered setting.Our analysis shows that the proposed volume-based method allows successful classification of the financial time series patterns, and also leads to better classification performance than the price levels-based method, excelling specifically on more liquid financial instruments. Finally, we propose an approach for obtaining feature interactions directly from tree-based models and compare the outcomes to those of the SHAP method. This results in the significant similarity between the two methods, hence we claim that SHAP feature interactions are reliable to be used in the setting of financial markets.http://www.sciencedirect.com/science/article/pii/S2666827023000014Applied MLVolume profilesBoosting treesExplainable MLComputational finance |
| spellingShingle | Artur Sokolovsky Luca Arnaboldi Jaume Bacardit Thomas Gross Interpretable trading pattern designed for machine learning applications Machine Learning with Applications Applied ML Volume profiles Boosting trees Explainable ML Computational finance |
| title | Interpretable trading pattern designed for machine learning applications |
| title_full | Interpretable trading pattern designed for machine learning applications |
| title_fullStr | Interpretable trading pattern designed for machine learning applications |
| title_full_unstemmed | Interpretable trading pattern designed for machine learning applications |
| title_short | Interpretable trading pattern designed for machine learning applications |
| title_sort | interpretable trading pattern designed for machine learning applications |
| topic | Applied ML Volume profiles Boosting trees Explainable ML Computational finance |
| url | http://www.sciencedirect.com/science/article/pii/S2666827023000014 |
| work_keys_str_mv | AT artursokolovsky interpretabletradingpatterndesignedformachinelearningapplications AT lucaarnaboldi interpretabletradingpatterndesignedformachinelearningapplications AT jaumebacardit interpretabletradingpatterndesignedformachinelearningapplications AT thomasgross interpretabletradingpatterndesignedformachinelearningapplications |