{"id":229712,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00229712","sets":["6504:11436:11438"]},"path":["11438"],"owner":"44499","recid":"229712","title":["深層強化学習による機会損失と破産確率を考慮した金融取引戦略の構築"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-02-16"},"_buckets":{"deposit":"1506191d-40d2-4232-88fc-8a5fb7af9b29"},"_deposit":{"id":"229712","pid":{"type":"depid","value":"229712","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"深層強化学習による機会損失と破産確率を考慮した金融取引戦略の構築","author_link":["617894","617895"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"深層強化学習による機会損失と破産確率を考慮した金融取引戦略の構築"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"ソフトウェア科学・工学","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2023-02-16","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京都市大"},{"subitem_text_value":"東京都市大"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/229712/files/IPSJ-Z85-4M-04.pdf","label":"IPSJ-Z85-4M-04.pdf"},"date":[{"dateType":"Available","dateValue":"2023-11-17"}],"format":"application/pdf","filename":"IPSJ-Z85-4M-04.pdf","filesize":[{"value":"371.0 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"210c6f16-251d-4150-916b-40351563af15","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"井上, 修一"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"穴田, 一"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_22_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00349328","subitem_source_identifier_type":"NCID"}]},"item_22_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"近年，機械学習の発展に伴い深層強化学習を用いた金融取引戦略を構築する研究が精力的に行われている．我々の従来研究では，取引エージェントの「買い」「売り」「様子見」といった行動に対し，相場の局面によって適応的に変化する機会損失を考慮した報酬を与えていた．しかし，取引の安全性については考慮されておらず，比較的大きな損失を出すタイミングがあった．そこで，本研究では取引エージェントの勝率，ペイオフレシオ，リスク資金比率から求められる破産確率を深層強化学習での状態変数や報酬に導入し，株式投資においてより安全に利益を上げるための最適な買いや売りのタイミングを学習するモデルを構築し，その有効性を示す．","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"370","bibliographic_titles":[{"bibliographic_title":"第85回全国大会講演論文集"}],"bibliographicPageStart":"369","bibliographicIssueDates":{"bibliographicIssueDate":"2023-02-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2023"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T11:27:00.405545+00:00","created":"2025-01-19T01:29:02.068492+00:00","links":{}}