{"corpus_id":21813886,"paper_sha":"0eef26c7801822efa9cd5fb17471f993f2972085","doi":"10.1109/CCBD.2016.038","arxiv_id":null,"pmid":null,"pmcid":null,"mag_id":2734573782,"dblp_id":"conf/ccbd/ChenHLHCH16","acl_id":null,"title":"Decision Support System for Real-Time Trading Based on On-Line Learning and Parallel Computing Techniques","year":2016,"publication_date":null,"venue":"International Conference on Cloud Computing and Big Data","journal":{"name":"2016 7th International Conference on Cloud Computing and Big Data (CCBD)","pages":"151-156","volume":null},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle","Conference"],"pubmed_pub_types":null,"s2_fields_of_study":["Computer Science"],"reference_count":28,"citation_count":0,"influential_citation_count":0,"is_open_access":false,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":null,"s2_open_access_landing_url":null,"s2_open_access_license":null,"s2_open_access_status":null,"pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"A novel intraday algorithmic trading strategy is developed based on various machine learning techniques and paralleled computing architectures in this paper. The proposed binary classification framework can predict the price trends of Taiwan stock index futures after thirty minutes. Traditional learning-based approaches collect all samples during the training period as the learning materials. The major contribution of this paper is to collect a subset of similar historical financial data to train the real-time trading model. This goal can be achieved by an on-line learning technique which is required to calculate an accurate model with training time limitation. In addition, the proposed joint-AdaBoost algorithm is to improve the system performance based on the concept of paired feature learning and planar weak classifier design. The core execution components in this algorithm can be further accelerated with the aid of Open Computing Language (OpenCL) parallel computing platform. The experimental results show that the proposed learning algorithm can improve the prediction accuracy of final classifier from 53.8% to 61.68%. Compared to the pure CPU implementation, the OpenCL version which uses CPU and GPGPU simultaneously can reduce the calculation time around 83.02 times. The efficiency improvement can decrease the delay of investment opportunity which is a critical issue in real-time financial decision support system application. To sum up, this paper proposed a novel learning framework based on joint-AdaBoost algorithm with similar learning samples and OpenCL parallel computation. The extended financial decision support system is also proven to work effectively and efficiently in our simulation experiments to trade the Taiwan stock index futures.","claims":[{"public_id":"cl_71011bdce7679df8c7e1aa61536b8d2a","status":"active","text":"Accelerating the core execution components with OpenCL using CPU and GPGPU simultaneously reduces calculation time by around 83.02 times compared to a pure CPU implementation.","confidence":0.9,"contributors":[{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["extraction"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/claims/cl_71011bdce7679df8c7e1aa61536b8d2a"},{"public_id":"cl_85727d651dfcccd6c61e070fe868560a","status":"active","text":"The binary classification framework predicts price trends of Taiwan stock index futures thirty minutes into the future.","confidence":0.85,"contributors":[{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["extraction"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/claims/cl_85727d651dfcccd6c61e070fe868560a"},{"public_id":"cl_ff1833371a956333f031ca31fe1d9ac8","status":"active","text":"The joint-AdaBoost algorithm, which combines paired feature learning with planar weak classifier design, improves the prediction accuracy of the final classifier from 53.8% to 61.68%.","confidence":0.9,"contributors":[{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["extraction"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/claims/cl_ff1833371a956333f031ca31fe1d9ac8"},{"public_id":"cl_0f6e2727bb59b55ab9fcff8fae64aa6a","status":"active","text":"The on-line learning technique trains the real-time trading model using a subset of similar historical financial data selected to satisfy a training time limitation.","confidence":0.85,"contributors":[{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["extraction"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/claims/cl_0f6e2727bb59b55ab9fcff8fae64aa6a"}],"concepts":[{"public_id":"co_058e18946b2889a3bc225f3ed102991e","status":"active","name":"OpenCL","description":"Open Computing Language, a parallel computing platform used to accelerate the algorithm's core execution components.","types":["technology","platform"],"aliases":["Open Computing Language"],"contributors":[{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["extraction"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/concepts/co_058e18946b2889a3bc225f3ed102991e"},{"public_id":"co_244b345d80c84858e91754813201a894","status":"active","name":"Taiwan stock index futures","description":"Futures contracts based on the Taiwan stock index, used as the traded financial instrument in this study.","types":["financial instrument"],"aliases":[],"contributors":[{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["extraction"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/concepts/co_244b345d80c84858e91754813201a894"},{"public_id":"co_474a61ebcf58a3199d214fd53d1b478d","status":"active","name":"on-line learning technique","description":"A learning approach that selects a subset of similar historical data to train a model within a training time limitation.","types":["method"],"aliases":[],"contributors":[{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["extraction"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/concepts/co_474a61ebcf58a3199d214fd53d1b478d"},{"public_id":"co_4d556bb4c043091e10e4a106367beea8","status":"active","name":"real-time trading model","description":"The trading prediction model trained and applied in real time to support trading decisions.","types":["model","system"],"aliases":[],"contributors":[{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["extraction"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/concepts/co_4d556bb4c043091e10e4a106367beea8"},{"public_id":"co_5409cc41a9c923db7902ed160ee0bb88","status":"active","name":"financial decision support system","description":"The overall decision support system developed in this paper for real-time financial trading.","types":["system"],"aliases":[],"contributors":[{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["extraction"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/concepts/co_5409cc41a9c923db7902ed160ee0bb88"},{"public_id":"co_5c306203c63dd5cfe1b6fc9cac68b05a","status":"active","name":"joint-AdaBoost algorithm","description":"A boosting algorithm proposed in this paper that combines paired feature learning with planar weak classifier design.","types":["method","algorithm"],"aliases":[],"contributors":[{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["extraction"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/concepts/co_5c306203c63dd5cfe1b6fc9cac68b05a"},{"public_id":"co_96fe784c73147769e770257af0cc682f","status":"active","name":"paired feature learning","description":"A feature learning concept in which pairs of features are jointly considered to build weak classifiers.","types":["method"],"aliases":[],"contributors":[{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["extraction"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/concepts/co_96fe784c73147769e770257af0cc682f"},{"public_id":"co_af28ff2fae1b1acccc8f6275e7e25bc4","status":"active","name":"intraday algorithmic trading strategy","description":"A trading strategy that uses machine learning algorithms to make trading decisions within a single trading day.","types":["method"],"aliases":[],"contributors":[{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["extraction"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/concepts/co_af28ff2fae1b1acccc8f6275e7e25bc4"},{"public_id":"co_c00a12aaf8048a7a3114833f0f20512b","status":"active","name":"planar weak classifier","description":"A weak classifier design that partitions the feature space using a planar decision boundary.","types":["method","component"],"aliases":[],"contributors":[{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["extraction"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/concepts/co_c00a12aaf8048a7a3114833f0f20512b"},{"public_id":"co_c6041c770a5d5011e1d6511f4af60a7f","status":"active","name":"binary classification framework","description":"A predictive framework that classifies future price movements into two outcome categories.","types":["method"],"aliases":[],"contributors":[{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["extraction"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/concepts/co_c6041c770a5d5011e1d6511f4af60a7f"},{"public_id":"co_c83c3772d474ed0a38b754df8548ea4a","status":"active","name":"GPGPU","description":"General-purpose computing on graphics processing units, used together with the CPU to accelerate calculations.","types":["hardware","technology"],"aliases":[],"contributors":[{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["extraction"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":2,"public_id":"4715169a40","public_label":"AK (4715169a40)","roles":["review"],"url":"https://sah.borca.ai/u/4715169a40"},{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["review"],"url":"https://sah.borca.ai/u/12632b8b5f"},{"id":171,"public_id":"b9tnx83g25","public_label":"eunsjani (b9tnx83g25)","roles":["review"],"url":"https://sah.borca.ai/u/b9tnx83g25"}],"url":"https://sah.borca.ai/concepts/co_c83c3772d474ed0a38b754df8548ea4a"}],"external_ids":{"DOI":"10.1109/CCBD.2016.038","ArXiv":null,"PubMed":null,"PubMedCentral":null,"MAG":2734573782,"DBLP":"conf/ccbd/ChenHLHCH16","ACL":null},"open_access":{"is_open_access":false,"pdf_url":null,"landing_url":"https://sah.borca.ai/papers/21813886","source":null,"pdf_url_source":null,"license":null,"reason":"pdf_url_not_indexed"},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":631307,"paper_uid":"1fd7a9fd-a225-40e1-83ad-e7427c3755d7","canonical_identity":{"paper_id":631307,"paper_uid":"1fd7a9fd-a225-40e1-83ad-e7427c3755d7","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/21813886"}