{"created":"2025-01-19T01:32:24.344182+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00231858","sets":["581:11492:11493"]},"path":["11493"],"owner":"44499","recid":"231858","title":["異種ドメインのユーザ・アイテムクラスタ情報を用いたペアワイズ学習に基づく購買予測手法"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-01-15"},"_buckets":{"deposit":"8dd3d58c-01ec-421b-9b16-71f9846af187"},"_deposit":{"id":"231858","pid":{"type":"depid","value":"231858","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"異種ドメインのユーザ・アイテムクラスタ情報を用いたペアワイズ学習に基づく購買予測手法","author_link":["627058","627056","627054","627060","627055","627053","627051","627050","627057","627052","627049","627059"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"異種ドメインのユーザ・アイテムクラスタ情報を用いたペアワイズ学習に基づく購買予測手法"},{"subitem_title":"Purchase Prediction Based on Pairwise Learning with User-Item Cluster Information from Heterogeneous Domains","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[一般論文（推薦論文）] レコメンドシステム，ランキング学習，ネガティブサンプリング，クロスドメイン推薦","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2024-01-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"大阪大学大学院情報科学研究科マルチメディア工学専攻"},{"subitem_text_value":"大阪大学情報科学研究科"},{"subitem_text_value":"株式会社KDDI総合研究所"},{"subitem_text_value":"株式会社KDDI総合研究所"},{"subitem_text_value":"大阪大学情報科学研究科"},{"subitem_text_value":"大阪大学情報科学研究科"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Multimedia Engineering Graduate School of Information Science and Technology, Osaka University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science and Technology, Osaka University","subitem_text_language":"en"},{"subitem_text_value":"KDDI Research, Inc.","subitem_text_language":"en"},{"subitem_text_value":"KDDI Research, Inc.","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science and Technology, Osaka University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Information Science and Technology, Osaka University","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/231858/files/IPSJ-JNL6501026.pdf","label":"IPSJ-JNL6501026.pdf"},"date":[{"dateType":"Available","dateValue":"2026-01-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL6501026.pdf","filesize":[{"value":"1.1 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"bdadefac-0a93-48a1-afec-e50b428bfd0b","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"海保, 拓真"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"原, 隆浩"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"黒川, 茂莉"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"米川, 慧"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"天方, 大地"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"前川, 卓也"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Takuma, Kaiho","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takahiro, Hara","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Mori, Kurokawa","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Kei, Yonekawa","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Daichi, Amagata","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Takuya, Maekawa","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_2_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00116647","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_2_publisher_15":{"attribute_name":"公開者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"item_2_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7764","subitem_source_identifier_type":"ISSN"}]},"item_2_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"オンラインショッピングサービス上の膨大な量のアイテムからユーザの嗜好に合うアイテムを優先して推薦するためのランキング学習は重要である．ランキング学習には，ユーザの行動情報が大量に必要となるが，実際にユーザが持つ購買履歴は非常に少ない．本論文では，広告配信サービスの閲覧履歴をクラスタリングして得られたユーザクラスタの行動特徴を利用し，購買履歴の少ないユーザへの商品推薦を可能にする購買予測手法を提案する．提案手法では，ユーザ・アイテム間の関連度予測モデルのランキング学習の際にユーザクラスタの行動特徴を利用し，推薦対象のユーザとの購買履歴がないアイテムのランキングを予測できるように学習を行う．これにより，ユーザの嗜好をとらえた商品推薦が可能となり，購買履歴の少ないユーザへの推薦精度を向上する．","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Learning to rank is important for recommending items that match user preferences from a huge amount of items on online shopping services. Although a large amount of user behavior information is required for learning the ranking, purchase history that users have are very limited. In this paper, we propose a purchase prediction method that enables item recommendation to users with little purchase history by using behavioral characteristics of user clusters obtained from the browsing history of Web ad services. The proposed method uses behavioral characteristics of user clusters when learning ranking for the user-item relevance prediction model, and learns to predict the ranking of items that have no purchase history with the user to be recommended. This enables product recommendations that capture the user's preferences and increase the accuracy of recommendations to users with little purchase history.","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"240","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicPageStart":"230","bibliographicIssueDates":{"bibliographicIssueDate":"2024-01-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"65"}]},"relation_version_is_last":true,"item_2_identifier_registration":{"attribute_name":"ID登録","attribute_value_mlt":[{"subitem_identifier_reg_text":"10.20729/00231748","subitem_identifier_reg_type":"JaLC"}]},"weko_creator_id":"44499"},"links":{},"id":231858,"updated":"2025-01-19T10:36:32.552003+00:00"}