Performance evaluation metric for statistical learning trading strategies
We analyze how the sentiment of financial news can be used to predict stock returns and build profitable trading strategies. Combining the textual analysis of financial news headlines and statistical methods, we build multi-class classification models to predict the stock return. The main contributi...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2024-12-01
|
| Series: | Data Science in Finance and Economics |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/DSFE.2024024 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590312027979776 |
|---|---|
| author | Jiawei He Roman N. Makarov Jake Tuero Zilin Wang |
| author_facet | Jiawei He Roman N. Makarov Jake Tuero Zilin Wang |
| author_sort | Jiawei He |
| collection | DOAJ |
| description | We analyze how the sentiment of financial news can be used to predict stock returns and build profitable trading strategies. Combining the textual analysis of financial news headlines and statistical methods, we build multi-class classification models to predict the stock return. The main contribution of this paper is twofold. Firstly, we develop a performance evaluation metric to compare multi-class classification methods, taking into account the precision and accuracy of the models and methods. By maximizing the metric, we find optimal combinations of models and methods and select the best approach for prediction and decision-making. Secondly, this metric enables us to construct profitable option trading strategies, which can also be used as an assessment tool to analyze models' prediction power. We apply our methodology to historical data from Apple stock and financial news headlines from Reuters from January 1, 2012 to May 31, 2019. During validation (May 31, 2018, to May 31, 2019), our models consistently outperformed the market, with two-class one-stage models yielding returns between 30% and 45%, compared to the S & P500 index's 1.73% return over the same period. |
| format | Article |
| id | doaj-art-217a8fb6ab2a413981599fadf114d3fa |
| institution | Kabale University |
| issn | 2769-2140 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | Data Science in Finance and Economics |
| spelling | doaj-art-217a8fb6ab2a413981599fadf114d3fa2025-01-24T01:03:03ZengAIMS PressData Science in Finance and Economics2769-21402024-12-014457060010.3934/DSFE.2024024Performance evaluation metric for statistical learning trading strategiesJiawei He0Roman N. Makarov1Jake Tuero2Zilin Wang3Department of Mathematics & Statistics, 50 Stone Road East, University of Guelph, Guelph, CanadaDepartment of Mathematics, Wilfird Laurier University, 75 University Avenue West, Waterloo, CanadaDepartment of Computer Science, University of Alberta, 116 Street and 85 Avenue, Edmonton, CanadaDepartment of Mathematics, Wilfird Laurier University, 75 University Avenue West, Waterloo, CanadaWe analyze how the sentiment of financial news can be used to predict stock returns and build profitable trading strategies. Combining the textual analysis of financial news headlines and statistical methods, we build multi-class classification models to predict the stock return. The main contribution of this paper is twofold. Firstly, we develop a performance evaluation metric to compare multi-class classification methods, taking into account the precision and accuracy of the models and methods. By maximizing the metric, we find optimal combinations of models and methods and select the best approach for prediction and decision-making. Secondly, this metric enables us to construct profitable option trading strategies, which can also be used as an assessment tool to analyze models' prediction power. We apply our methodology to historical data from Apple stock and financial news headlines from Reuters from January 1, 2012 to May 31, 2019. During validation (May 31, 2018, to May 31, 2019), our models consistently outperformed the market, with two-class one-stage models yielding returns between 30% and 45%, compared to the S & P500 index's 1.73% return over the same period.https://www.aimspress.com/article/doi/10.3934/DSFE.2024024statistical learninglogistic regressionsentiment analysis of financial newsmulti-class classification metricsoption trading strategies |
| spellingShingle | Jiawei He Roman N. Makarov Jake Tuero Zilin Wang Performance evaluation metric for statistical learning trading strategies Data Science in Finance and Economics statistical learning logistic regression sentiment analysis of financial news multi-class classification metrics option trading strategies |
| title | Performance evaluation metric for statistical learning trading strategies |
| title_full | Performance evaluation metric for statistical learning trading strategies |
| title_fullStr | Performance evaluation metric for statistical learning trading strategies |
| title_full_unstemmed | Performance evaluation metric for statistical learning trading strategies |
| title_short | Performance evaluation metric for statistical learning trading strategies |
| title_sort | performance evaluation metric for statistical learning trading strategies |
| topic | statistical learning logistic regression sentiment analysis of financial news multi-class classification metrics option trading strategies |
| url | https://www.aimspress.com/article/doi/10.3934/DSFE.2024024 |
| work_keys_str_mv | AT jiaweihe performanceevaluationmetricforstatisticallearningtradingstrategies AT romannmakarov performanceevaluationmetricforstatisticallearningtradingstrategies AT jaketuero performanceevaluationmetricforstatisticallearningtradingstrategies AT zilinwang performanceevaluationmetricforstatisticallearningtradingstrategies |