ログイン
言語:

WEKO3

  • トップ
  • コミュニティ
  • ランキング
AND
To
lat lon distance
To

Field does not validate



インデックスリンク

インデックスツリー

メールアドレスを入力してください。

WEKO

One fine body…

WEKO

One fine body…

アイテム

{"_buckets": {"deposit": "cf4484ee-a773-4210-b226-8e29617780d9"}, "_deposit": {"id": "7886", "owners": [], "pid": {"revision_id": 0, "type": "depid", "value": "7886"}, "status": "published"}, "_oai": {"id": "oai:kitami-it.repo.nii.ac.jp:00007886", "sets": ["1:86"]}, "author_link": ["40682", "40683", "40684", "40685", "40678", "273", "40680", "40681"], "item_1646810750418": {"attribute_name": "\u51fa\u7248\u30bf\u30a4\u30d7", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_970fb48d4fbd8a85", "subitem_version_type": "VoR"}]}, "item_3_alternative_title_198": {"attribute_name": "\u305d\u306e\u4ed6\u306e\u30bf\u30a4\u30c8\u30eb", "attribute_value_mlt": [{"subitem_alternative_title": "Variable Order Transition Probability Markov Decision Process for the Recommendation System"}]}, "item_3_biblio_info_186": {"attribute_name": "\u66f8\u8a8c\u60c5\u5831", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2013-03", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "1", "bibliographicPageEnd": "30", "bibliographicPageStart": "20", "bibliographicVolumeNumber": "6", "bibliographic_titles": [{"bibliographic_title": "\u60c5\u5831\u51e6\u7406\u5b66\u4f1a\u8ad6\u6587\u8a8c\u6570\u7406\u30e2\u30c7\u30eb\u5316\u3068\u5fdc\u7528\uff08TOM\uff09", "bibliographic_titleLang": "ja"}]}]}, "item_3_description_184": {"attribute_name": "\u6284\u9332", "attribute_value_mlt": [{"subitem_description": "\u63a8\u85a6\u554f\u984c\u3092\u6271\u3046\u305f\u3081\u306e\u3088\u308a\u4e00\u822c\u5316\u3055\u308c\u305f\u30de\u30eb\u30b3\u30d5\u6c7a\u5b9a\u904e\u7a0b\u30e2\u30c7\u30eb\u306b\u5bfe\u3057\u3066\uff0c\u30d9\u30a4\u30ba\u57fa\u6e96\u306e\u3082\u3068\u3067\u6700\u9069\u306a\u63a8\u85a6\u30eb\u30fc\u30eb\u3092\u5c65\u6b74\u30c7\u30fc\u30bf\u304b\u3089\u6c42\u3081\u308b\u65b9\u6cd5\u3092\u63d0\u6848\u3059\u308b\uff0e\u63a8\u85a6\u554f\u984c\u306b\u95a2\u3059\u308b\u7814\u7a76\u306b\u304a\u3044\u3066\uff0c\u3053\u308c\u307e\u3067\uff0c\u3042\u308b\u5546\u54c1\u3092\u63a8\u85a6\u3057\u305f\u7d50\u679c\u3069\u306e\u5546\u54c1\u304c\u8cb7\u308f\u308c\u305f\u306e\u304b\uff08\u63a8\u85a6\u7d50\u679c\uff09\u3084\uff0c\u3055\u3089\u306b\u306f\uff0c\u4e00\u5b9a\u671f\u9593\u5185\u306b\u884c\u3063\u305f\u8907\u6570\u306e\u63a8\u85a6\u7d50\u679c\u304c\u8003\u616e\u3055\u308c\u308b\u3053\u3068\u306f\u307b\u3068\u3093\u3069\u306a\u304b\u3063\u305f\uff0e\u3053\u308c\u306b\u5bfe\u3057\u3066\uff0c\u30de\u30eb\u30b3\u30d5\u6c7a\u5b9a\u904e\u7a0b\u30e2\u30c7\u30eb\u3092\u7528\u3044\u308b\u3053\u3068\u3067\u4e0a\u8a182\u70b9\u3092\u521d\u3081\u3066\u8003\u616e\u3057\u305f\u624b\u6cd5\u304c\u63d0\u6848\u3055\u308c\u3066\u3044\u308b\uff0e\u63d0\u6848\u6cd5\u306f\uff0c\u305d\u306e\u5f93\u6765\u7814\u7a76\u306e\u30e2\u30c7\u30eb\u3092\u4e00\u822c\u5316\u3057\u305f\u70b9\u306b\u65b0\u898f\u6027\u304c\u3042\u308b\uff0e\u307e\u305f\uff0c\u3082\u30461\u3064\u306e\u65b0\u898f\u6027\u3068\u3057\u3066\uff0c\u63a8\u85a6\u30eb\u30fc\u30eb\u3092\u6c42\u3081\u308b\u305f\u3081\u306e\u30d7\u30ed\u30bb\u30b9\u3092\u7d71\u8a08\u7684\u6c7a\u5b9a\u554f\u984c\u3068\u3057\u3066\u53b3\u5bc6\u306b\u5b9a\u5f0f\u5316\u3057\u305f\u70b9\u304c\u3042\u308b\uff0e\u5f93\u6765\u306e\u30e2\u30c7\u30eb\u3092\u4e00\u822c\u5316\u3059\u308b\u3053\u3068\u3067\uff0c\u30de\u30eb\u30b3\u30d5\u6c7a\u5b9a\u904e\u7a0b\u30e2\u30c7\u30eb\u3092\u7528\u3044\u305f\u63a8\u85a6\u624b\u6cd5\u306e\u9069\u7528\u9818\u57df\u304c\u62e1\u5927\u3055\u308c\uff0c\u304b\u3064\uff0c\u63a8\u85a6\u3059\u308b\u76ee\u7684\u306b\u5bfe\u3057\u3066\u6700\u9069\u306a\u63a8\u85a6\u304c\u884c\u3048\u308b\u3088\u3046\u306b\u306a\u3063\u305f\uff0e\u4eba\u5de5\u30c7\u30fc\u30bf\u3092\u7528\u3044\u305f\u8a55\u4fa1\u5b9f\u9a13\u306b\u3088\u308a\uff0c\u63d0\u6848\u3059\u308b\u63a8\u85a6\u624b\u6cd5\u306e\u6709\u52b9\u6027\u3092\u78ba\u8a8d\u3057\u305f\uff0eIn this paper, we propose a general markov decision process model for the recommendation system. Furthermore, by using historical data, we derive the optimal recommendation lists from the proposed model based on bayesian decision theory. In the recommendation research area, there were little studies that considered both the purchased items and the past recommended items within a given period. In these circumstances, markov decision process based recommend method that can take these two things into account has been proposed. Our method also uses both things as with the previous method. Here, the unique thing about this paper is not only that we generalize the existing model, but also that we formulate the process to get the recommendation lists as the statistical decision problem. As a result, we can obtain the most suitable recommendation lists with respect to the purpose of the recommendation for a wide variety of recommendation scene. By using artificial data, we show the experimental results that our method can obtain more rewards than the conventional method gets.", "subitem_description_type": "Abstract"}]}, "item_3_full_name_183": {"attribute_name": "\u8457\u8005\u5225\u540d", "attribute_value_mlt": [{"nameIdentifiers": [{"nameIdentifier": "40682", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "Kuwata, Shuhei", "nameLang": "en"}]}, {"nameIdentifiers": [{"nameIdentifier": "40683", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "Maeda, Yasunari", "nameLang": "en"}]}, {"nameIdentifiers": [{"nameIdentifier": "40684", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "Matsushima, Toshiyasu", "nameLang": "en"}]}, {"nameIdentifiers": [{"nameIdentifier": "40685", "nameIdentifierScheme": "WEKO"}], "names": [{"name": "Hirasawa, Shigeichi", "nameLang": "en"}]}]}, "item_3_publisher_212": {"attribute_name": "\u51fa\u7248\u8005", "attribute_value_mlt": [{"subitem_publisher": "\u4e00\u822c\u793e\u56e3\u6cd5\u4eba\u3000\u60c5\u5831\u51e6\u7406\u5b66\u4f1a"}]}, "item_3_select_195": {"attribute_name": "\u8457\u8005\u7248\u30d5\u30e9\u30b0", "attribute_value_mlt": [{"subitem_select_item": "publisher"}]}, "item_3_subject_196": {"attribute_name": "\u65e5\u672c\u5341\u9032\u5206\u985e\u6cd5", "attribute_value_mlt": [{"subitem_subject": "417", "subitem_subject_scheme": "NDC"}]}, "item_access_right": {"attribute_name": "\u30a2\u30af\u30bb\u30b9\u6a29", "attribute_value_mlt": [{"subitem_access_right": "open access", "subitem_access_right_uri": "http://purl.org/coar/access_right/c_abf2"}]}, "item_creator": {"attribute_name": "\u8457\u8005", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "\u6851\u7530, \u4fee\u5e73", "creatorNameLang": "ja"}], "nameIdentifiers": [{"nameIdentifier": "40678", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "\u524d\u7530, \u5eb7\u6210", "creatorNameLang": "ja"}], "nameIdentifiers": [{"nameIdentifier": "273", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "30422033", "nameIdentifierScheme": "KAKEN - \u7814\u7a76\u8005\u691c\u7d22", "nameIdentifierURI": "https://nrid.nii.ac.jp/ja/nrid/1000030422033/"}]}, {"creatorNames": [{"creatorName": "\u677e\u5d8b, \u654f\u6cf0", "creatorNameLang": "ja"}], "nameIdentifiers": [{"nameIdentifier": "40680", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "\u5e73\u6fa4, \u8302\u4e00", "creatorNameLang": "ja"}], "nameIdentifiers": [{"nameIdentifier": "40681", "nameIdentifierScheme": "WEKO"}]}]}, "item_files": {"attribute_name": "\u30d5\u30a1\u30a4\u30eb\u60c5\u5831", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2016-11-22"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "No194.pdf", "filesize": [{"value": "512.2 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_note", "mimetype": "application/pdf", "size": 512200.00000000006, "url": {"label": "No194.pdf", "url": "https://kitami-it.repo.nii.ac.jp/record/7886/files/No194.pdf"}, "version_id": "52797f1d-f758-4555-ade3-3cd61423bd29"}]}, "item_keyword": {"attribute_name": "\u30ad\u30fc\u30ef\u30fc\u30c9", "attribute_value_mlt": [{"subitem_subject": "\u63a8\u85a6\u554f\u984c", "subitem_subject_scheme": "Other"}, {"subitem_subject": "\u30de\u30eb\u30b3\u30d5\u6c7a\u5b9a\u904e\u7a0b", "subitem_subject_scheme": "Other"}, {"subitem_subject": "\u30d9\u30a4\u30ba\u6c7a\u5b9a\u7406\u8ad6", "subitem_subject_scheme": "Other"}, {"subitem_subject": "\u5f37\u5316\u5b66\u7fd2", "subitem_subject_scheme": "Other"}, {"subitem_subject": "recommendation", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Markov decision process", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Bayesian decision theory", "subitem_subject_scheme": "Other"}, {"subitem_subject": "reinforcement learning", "subitem_subject_scheme": "Other"}]}, "item_language": {"attribute_name": "\u8a00\u8a9e", "attribute_value_mlt": [{"subitem_language": "jpn"}]}, "item_resource_type": {"attribute_name": "\u8cc7\u6e90\u30bf\u30a4\u30d7", "attribute_value_mlt": [{"resourcetype": "journal article", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "\u63a8\u85a6\u30b7\u30b9\u30c6\u30e0\u306e\u305f\u3081\u306e\u72b6\u614b\u9077\u79fb\u78ba\u7387\u306e\u69cb\u9020\u3092\u672a\u77e5\u3068\u3057\u305f\u30de\u30eb\u30b3\u30d5\u6c7a\u5b9a\u904e\u7a0b", "item_titles": {"attribute_name": "\u30bf\u30a4\u30c8\u30eb", "attribute_value_mlt": [{"subitem_title": "\u63a8\u85a6\u30b7\u30b9\u30c6\u30e0\u306e\u305f\u3081\u306e\u72b6\u614b\u9077\u79fb\u78ba\u7387\u306e\u69cb\u9020\u3092\u672a\u77e5\u3068\u3057\u305f\u30de\u30eb\u30b3\u30d5\u6c7a\u5b9a\u904e\u7a0b", "subitem_title_language": "ja"}, {"subitem_title": "Variable Order Transition Probability Markov Decision Process for the Recommendation System", "subitem_title_language": "en"}]}, "item_type_id": "3", "owner": "1", "path": ["1/86"], "permalink_uri": "https://kitami-it.repo.nii.ac.jp/records/7886", "pubdate": {"attribute_name": "PubDate", "attribute_value": "2015-08-17"}, "publish_date": "2015-08-17", "publish_status": "0", "recid": "7886", "relation": {}, "relation_version_is_last": true, "title": ["\u63a8\u85a6\u30b7\u30b9\u30c6\u30e0\u306e\u305f\u3081\u306e\u72b6\u614b\u9077\u79fb\u78ba\u7387\u306e\u69cb\u9020\u3092\u672a\u77e5\u3068\u3057\u305f\u30de\u30eb\u30b3\u30d5\u6c7a\u5b9a\u904e\u7a0b"], "weko_shared_id": -1}
  1. 学術雑誌掲載済論文
  2. 和雑誌

推薦システムのための状態遷移確率の構造を未知としたマルコフ決定過程

https://kitami-it.repo.nii.ac.jp/records/7886
22460990-dd1a-481c-890f-9430e180a1a2
名前 / ファイル ライセンス アクション
No194.pdf No194.pdf (512.2 kB)
Item type 学術雑誌論文 / Journal Article(1)
公開日 2015-08-17
タイトル
言語 ja
タイトル 推薦システムのための状態遷移確率の構造を未知としたマルコフ決定過程
タイトル
言語 en
タイトル Variable Order Transition Probability Markov Decision Process for the Recommendation System
言語
言語 jpn
キーワード
主題Scheme Other
主題 推薦問題
キーワード
主題Scheme Other
主題 マルコフ決定過程
キーワード
主題Scheme Other
主題 ベイズ決定理論
キーワード
主題Scheme Other
主題 強化学習
キーワード
主題Scheme Other
主題 recommendation
キーワード
主題Scheme Other
主題 Markov decision process
キーワード
主題Scheme Other
主題 Bayesian decision theory
キーワード
主題Scheme Other
主題 reinforcement learning
資源タイプ
資源 http://purl.org/coar/resource_type/c_6501
タイプ journal article
アクセス権
アクセス権 open access
アクセス権URI http://purl.org/coar/access_right/c_abf2
その他のタイトル
その他のタイトル Variable Order Transition Probability Markov Decision Process for the Recommendation System
著者 桑田, 修平

× 桑田, 修平

WEKO 40678

ja 桑田, 修平

Search repository
前田, 康成

× 前田, 康成

WEKO 273
KAKEN - 研究者検索 30422033

ja 前田, 康成

Search repository
松嶋, 敏泰

× 松嶋, 敏泰

WEKO 40680

ja 松嶋, 敏泰

Search repository
平澤, 茂一

× 平澤, 茂一

WEKO 40681

ja 平澤, 茂一

Search repository
著者別名
姓名
姓名 Kuwata, Shuhei
言語 en
著者別名
姓名
姓名 Maeda, Yasunari
言語 en
著者別名
姓名
姓名 Matsushima, Toshiyasu
言語 en
著者別名
姓名
姓名 Hirasawa, Shigeichi
言語 en
抄録
内容記述タイプ Abstract
内容記述 推薦問題を扱うためのより一般化されたマルコフ決定過程モデルに対して,ベイズ基準のもとで最適な推薦ルールを履歴データから求める方法を提案する.推薦問題に関する研究において,これまで,ある商品を推薦した結果どの商品が買われたのか(推薦結果)や,さらには,一定期間内に行った複数の推薦結果が考慮されることはほとんどなかった.これに対して,マルコフ決定過程モデルを用いることで上記2点を初めて考慮した手法が提案されている.提案法は,その従来研究のモデルを一般化した点に新規性がある.また,もう1つの新規性として,推薦ルールを求めるためのプロセスを統計的決定問題として厳密に定式化した点がある.従来のモデルを一般化することで,マルコフ決定過程モデルを用いた推薦手法の適用領域が拡大され,かつ,推薦する目的に対して最適な推薦が行えるようになった.人工データを用いた評価実験により,提案する推薦手法の有効性を確認した.In this paper, we propose a general markov decision process model for the recommendation system. Furthermore, by using historical data, we derive the optimal recommendation lists from the proposed model based on bayesian decision theory. In the recommendation research area, there were little studies that considered both the purchased items and the past recommended items within a given period. In these circumstances, markov decision process based recommend method that can take these two things into account has been proposed. Our method also uses both things as with the previous method. Here, the unique thing about this paper is not only that we generalize the existing model, but also that we formulate the process to get the recommendation lists as the statistical decision problem. As a result, we can obtain the most suitable recommendation lists with respect to the purpose of the recommendation for a wide variety of recommendation scene. By using artificial data, we show the experimental results that our method can obtain more rewards than the conventional method gets.
書誌情報 ja : 情報処理学会論文誌数理モデル化と応用(TOM)

巻 6, 号 1, p. 20-30, 発行日 2013-03
出版者
出版者 一般社団法人 情報処理学会
著者版フラグ
値 publisher
出版タイプ
出版タイプ VoR
出版タイプResource http://purl.org/coar/version/c_970fb48d4fbd8a85
戻る
0
views
See details
Views

Versions

Ver.1 2021-03-01 06:11:06.286207
Show All versions

Share

Mendeley CiteULike Twitter Facebook Print Addthis

Cite as

Export

OAI-PMH
  • OAI-PMH JPCOAR
  • OAI-PMH DublinCore
  • OAI-PMH DDI
Other Formats
  • JSON
  • BIBTEX

Confirm


Powered by CERN Data Centre & Invenio


Powered by CERN Data Centre & Invenio