Forecasting the stock market is particularly challenging due to the presence of a variety of inter-related economic and political factors. In recent years, the application of Machine Learning algorithms in quantitative stock trading systems has become established, as it enables a data-driven approach to investing in the financial markets. However, most professional traders still look for an explanation of automatically generated signals to verify their adherence to technical and fundamental rules. This paper presents an explainable approach to stock trading. It investigates the use of classification rules, which represent reliable associations between a set of discrete indicator values and the target class, to address next-day stock price prediction. Adopting associative classifiers in short-term stock trading not only provides reliable signals but also allows domain experts to understand the rationale behind signal generation. The backtesting of a state-of-the-art associative classifier, relying on a lazy pruning strategy, has shown promising performance in terms of equity appreciation and robustness of the trading system to market drawdowns.
{"title":"Leveraging the explainability of associative classifiers to support quantitative stock trading","authors":"Giuseppe Attanasio, Luca Cagliero, Elena Baralis","doi":"10.1145/3401832.3402679","DOIUrl":"https://doi.org/10.1145/3401832.3402679","url":null,"abstract":"Forecasting the stock market is particularly challenging due to the presence of a variety of inter-related economic and political factors. In recent years, the application of Machine Learning algorithms in quantitative stock trading systems has become established, as it enables a data-driven approach to investing in the financial markets. However, most professional traders still look for an explanation of automatically generated signals to verify their adherence to technical and fundamental rules. This paper presents an explainable approach to stock trading. It investigates the use of classification rules, which represent reliable associations between a set of discrete indicator values and the target class, to address next-day stock price prediction. Adopting associative classifiers in short-term stock trading not only provides reliable signals but also allows domain experts to understand the rationale behind signal generation. The backtesting of a state-of-the-art associative classifier, relying on a lazy pruning strategy, has shown promising performance in terms of equity appreciation and robustness of the trading system to market drawdowns.","PeriodicalId":336159,"journal":{"name":"Proceedings of the Sixth International Workshop on Data Science for Macro-Modeling","volume":"98 12","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114126393","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
D. Lembo, Yunyao Li, Lucian Popa, Federico Maria Scafoglieri
Information extraction (IE) refers to the task of turning text documents into a structured form, in order to make the information contained therein automatically processable. Ontology Mediated Information Extraction (OMIE) is a new paradigm for IE that seeks to exploit the semantic knowledge expressed in ontologies to improve query answering over unstructured data (properly raw text). In this paper we present Mastro System-T, an OMIE tool born from a joint collaboration between the University of Rome "La Sapienza" and IBM Research Almaden and its first application in a financial domain, namely to facilitate the access to and the sharing of data extracted from the EDGAR system.
信息抽取(Information extraction, IE)是指将文本文档转化为结构化形式，使其中所包含的信息能够自动处理的任务。本体中介信息提取(OMIE)是IE的一种新范式，它寻求利用本体中表达的语义知识来改进对非结构化数据(适当的原始文本)的查询回答。在本文中，我们介绍了master system - t，这是一种OMIE工具，诞生于罗马大学“La Sapienza”和IBM阿尔马登研究所之间的联合合作，并首次在金融领域应用，即促进从EDGAR系统中提取的数据的访问和共享。
{"title":"Ontology mediated information extraction in financial domain with Mastro System-T","authors":"D. Lembo, Yunyao Li, Lucian Popa, Federico Maria Scafoglieri","doi":"10.1145/3401832.3402681","DOIUrl":"https://doi.org/10.1145/3401832.3402681","url":null,"abstract":"Information extraction (IE) refers to the task of turning text documents into a structured form, in order to make the information contained therein automatically processable. Ontology Mediated Information Extraction (OMIE) is a new paradigm for IE that seeks to exploit the semantic knowledge expressed in ontologies to improve query answering over unstructured data (properly raw text). In this paper we present Mastro System-T, an OMIE tool born from a joint collaboration between the University of Rome \"La Sapienza\" and IBM Research Almaden and its first application in a financial domain, namely to facilitate the access to and the sharing of data extracted from the EDGAR system.","PeriodicalId":336159,"journal":{"name":"Proceedings of the Sixth International Workshop on Data Science for Macro-Modeling","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127178906","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Planning buy-and-hold strategies for stock trading is a challenging financial task. It entails building a portfolio of stocks maximizing the expected return in the medium- or long-term while minimizing investments' risk. Diversification is the most common strategy to manage risk in financial investments. It entails spreading bets across multiple assets, typically by picking stocks from different financial sectors. This paper presents a time series clustering-based strategy to improve the effectiveness of stock diversification across sectors. It analyzes the cross-correlation among price series in order to identify groups of stocks belonging to different sectors that unexpectedly show similar trends as well as dissimilarities among stocks of the same sector. The diversification strategy has been integrated into a state-of-the-art itemset-based approach to stock portfolio generation. The performance achieved on the U.S. stock market show relevant improvements in portfolio returns and drawdown control.
{"title":"Price series cross-correlation analysis to enhance the diversification of itemset-based stock portfolios","authors":"Jacopo Fior, Luca Cagliero, P. Garza","doi":"10.1145/3401832.3402680","DOIUrl":"https://doi.org/10.1145/3401832.3402680","url":null,"abstract":"Planning buy-and-hold strategies for stock trading is a challenging financial task. It entails building a portfolio of stocks maximizing the expected return in the medium- or long-term while minimizing investments' risk. Diversification is the most common strategy to manage risk in financial investments. It entails spreading bets across multiple assets, typically by picking stocks from different financial sectors. This paper presents a time series clustering-based strategy to improve the effectiveness of stock diversification across sectors. It analyzes the cross-correlation among price series in order to identify groups of stocks belonging to different sectors that unexpectedly show similar trends as well as dissimilarities among stocks of the same sector. The diversification strategy has been integrated into a state-of-the-art itemset-based approach to stock portfolio generation. The performance achieved on the U.S. stock market show relevant improvements in portfolio returns and drawdown control.","PeriodicalId":336159,"journal":{"name":"Proceedings of the Sixth International Workshop on Data Science for Macro-Modeling","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129387276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Proceedings of the Sixth International Workshop on Data Science for Macro-Modeling","authors":"","doi":"10.1145/3401832","DOIUrl":"https://doi.org/10.1145/3401832","url":null,"abstract":"","PeriodicalId":336159,"journal":{"name":"Proceedings of the Sixth International Workshop on Data Science for Macro-Modeling","volume":"139 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124381403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：