Adriano Soares Koshiyama, Nikan B. Firoozye, P. Treleaven
Derivative traders are usually required to scan through hundreds, even thousands of possible trades on a daily basis. Up to now, not a single solution is available to aid in their job. Hence, this work aims to develop a trading recommendation system, and apply this system to the so-called Mid-Curve Calendar Spread (MCCS). To suggest that such approach is feasible, we used a list of 35 different types of MCCS; a total of 11 predictive models; and 4 benchmark models. Our results suggest that linear regression with lasso regularisation compared favourably to other approaches from a predictive and interpretability perspective.
{"title":"A Derivatives Trading Recommendation System: the Mid-Curve Calendar Spread Case","authors":"Adriano Soares Koshiyama, Nikan B. Firoozye, P. Treleaven","doi":"10.2139/ssrn.3269496","DOIUrl":"https://doi.org/10.2139/ssrn.3269496","url":null,"abstract":"Derivative traders are usually required to scan through hundreds, even thousands of possible trades on a daily basis. Up to now, not a single solution is available to aid in their job. Hence, this work aims to develop a trading recommendation system, and apply this system to the so-called Mid-Curve Calendar Spread (MCCS). To suggest that such approach is feasible, we used a list of 35 different types of MCCS; a total of 11 predictive models; and 4 benchmark models. Our results suggest that linear regression with lasso regularisation compared favourably to other approaches from a predictive and interpretability perspective.","PeriodicalId":406435,"journal":{"name":"CompSciRN: Other Machine Learning (Topic)","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128705121","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}
Numerous applications of machine learning have gained acceptance in the field of strategy and management research only during the last few years. Established uses span such diverse problems as strategic foreign investments, strategic resource allocation, systemic risk analysis, and customer relationship management. This survey article covers natural language processing methods focused on text analytics and machine learning methods with their applications to management research and strategic practice. The methods are presented accessibly, with directly applicable examples, supplemented by a rich set of references crossing multiple subfields of management science. The intended audience is the strategy and management researcher with an interest in understanding the concepts, the recently established applications, and the trends of machine learning for strategy research.
{"title":"Machine Learning Methods for Strategy Research","authors":"Mike H. M. Teodorescu","doi":"10.2139/ssrn.3012524","DOIUrl":"https://doi.org/10.2139/ssrn.3012524","url":null,"abstract":"Numerous applications of machine learning have gained acceptance in the field of strategy and management research only during the last few years. Established uses span such diverse problems as strategic foreign investments, strategic resource allocation, systemic risk analysis, and customer relationship management. This survey article covers natural language processing methods focused on text analytics and machine learning methods with their applications to management research and strategic practice. The methods are presented accessibly, with directly applicable examples, supplemented by a rich set of references crossing multiple subfields of management science. The intended audience is the strategy and management researcher with an interest in understanding the concepts, the recently established applications, and the trends of machine learning for strategy research.","PeriodicalId":406435,"journal":{"name":"CompSciRN: Other Machine Learning (Topic)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133583011","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}
We present a forecasting algorithm based on support vector regression emphasizing thepractical benefits of wavelets for financial time series. We utilize an e ective de-noising algorithmbased on wavelets feasible under the assumption that the data is generated by a systematic pattern plusrandom noise. The learning algorithm focuses solely on the time frequency components, instead ofthe full time series, leading to a more general approach. Our findings propose how machine learningcan be useful for data science applications in combination with signal processing methods. The timefrequencydecomposition enables the learning algorithm to solely focus on periodical components thatare beneficial to the forecasting power as we drop features with low explanatory power. The proposedintegration of feature selection and parameter optimization in a single optimization step enable theproposed algorithm to be scaled for a variety of applications. Applying the algorithm to real lifefinancial data shows wavelet decompositions based on the Daubechie and Coiflet basis functions todeliver the best results for the classification task.
{"title":"A Hybrid Forecasting Algorithm Based on SVR and Wavelet Decomposition","authors":"Timotheos Paraskevopoulos, Peter N. Posch","doi":"10.2139/ssrn.3199925","DOIUrl":"https://doi.org/10.2139/ssrn.3199925","url":null,"abstract":"We present a forecasting algorithm based on support vector regression emphasizing thepractical benefits of wavelets for financial time series. We utilize an e ective de-noising algorithmbased on wavelets feasible under the assumption that the data is generated by a systematic pattern plusrandom noise. The learning algorithm focuses solely on the time frequency components, instead ofthe full time series, leading to a more general approach. Our findings propose how machine learningcan be useful for data science applications in combination with signal processing methods. The timefrequencydecomposition enables the learning algorithm to solely focus on periodical components thatare beneficial to the forecasting power as we drop features with low explanatory power. The proposedintegration of feature selection and parameter optimization in a single optimization step enable theproposed algorithm to be scaled for a variety of applications. Applying the algorithm to real lifefinancial data shows wavelet decompositions based on the Daubechie and Coiflet basis functions todeliver the best results for the classification task.","PeriodicalId":406435,"journal":{"name":"CompSciRN: Other Machine Learning (Topic)","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116177828","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：