国立国会図書館サーチRSS - 検索

Research on Recommendation Models for One-class Collaborative Filtering / 张, 茜

Fri, 29 May 2026 19:11:51 +0900

张, 茜. Research on Recommendation Models for One-class Collaborative Filtering. 2022-03-23

On the Evaluation of Intraday Market Quality in the Limit-Order Book Markets : A Collaborative Filtering Approach / Hayashi, Takakiほか

Tue, 08 Oct 2024 11:15:46 +0900

Hayashi, Takaki; Takahashi, Makoto. On the Evaluation of Intraday Market Quality in the Limit-Order Book Markets : A Collaborative Filtering Approach. 法政大学イノベーション・マネジメント研究センター, 2021-06-08

協調フィルタリングに基づく授業推薦システム (Webと教育支援,ライフログ活用技術,オフィスインフォメーションシステム,ライフインテリジェンス,一般) / 蒋, 再興ほか

Wed, 30 Jun 2021 12:12:38 +0900

蒋, 再興; 江村, 裕介; 檜垣, 泰彦. 協調フィルタリングに基づく授業推薦システム (Webと教育支援,ライフログ活用技術,オフィスインフォメーションシステム,ライフインテリジェンス,一般). 電子情報通信学会, 2011-03

協調フィルタリングに基づく改良版授業推薦システムの構築と評価 (推薦システム,グループウェアとネットワーク,ライフログ活用技術,オフィス情報システム,セキュリティ心理学とトラスト,一般) / 蒋, 再興ほか

Wed, 30 Jun 2021 12:12:38 +0900

蒋, 再興; 檜垣, 泰彦; 荒井, 幸代. 協調フィルタリングに基づく改良版授業推薦システムの構築と評価 (推薦システム,グループウェアとネットワーク,ライフログ活用技術,オフィス情報システム,セキュリティ心理学とトラスト,一般). 電子情報通信学会, 2012-05

スペクトル観点から効果的かつ効率的な個人推薦に向けて / ポン, シャオウェン

Sat, 07 Mar 2026 14:38:03 +0900

ポン, シャオウェン. スペクトル観点から効果的かつ効率的な個人推薦に向けて. Kyoto University, 2024-03-25. DOI:10.14989/doctor.k25430; 10.14989/doctor.k25430

Research on Recommendation Models for One-class Collaborative Filtering / 张, 茜

Sat, 06 Jun 2026 13:57:53 +0900

张, 茜. Research on Recommendation Models for One-class Collaborative Filtering. 2022-03-23
Recommender systems have become an indispensable tool for real-world applications. One-class collaborative filtering has attracted much attention in recommendation communities because the “one-class” is more suitable to describe data of many applications. Many recommendation methods have been proposed for realizing personalized ranking with one-class feedback (implicit feedback). Pairwise ranking methods with relative preference assumptions are widely used for dealing with the one-class problem due to their high performance. Bayesian Personalized Ranking (BPR) is one of the most popular pairwise methods, assuming users prefer the observed item to the unobserved item.BPR assumes the equal importance of each user’s unobserved items. However, existing some items that users have not seen yet. It is not appropriate to treat each user’s all unobserved items equally. Additionally, the parameters in BPR are learned by the stochastic gradient descent (SGD) optimization algorithm. The previous work has shown that the vanishing gradient problem exists in the learning process when the user’s preference difference between the observed item and the unobserved item is very large.In order to alleviate the problems of the previous model, three recommendation models are studied for one-class collaborative filtering in this thesis, including PBPR (Prior-based Bayesian Pairwise Ranking), PBPR* (Improving PBPR) and DBPL (Double Bayesian Pairwise Learning). All three recommendation models consider users’ preference differences between their unobserved items and can be realized without any additional social information. In addition, the users’ potential preference scores on their unobserved items are calculated based on users’ historical interactions for further distinguishing the relative preference of each user’s any two unobserved items. The key contributions in this thesis are summarized as below:(1) Motivated by the discovery that the user may be interested in items that their like-minded users have observed, users’ potential preference scores on their unobserved items could be calculated by the similarities between users and the similarities between items. The similarities between users and the similarities between items are measured at the item level and the entity level considering that the user might like the item or entity. Experiments on the real-world dataset demonstrate the results of the UIIU (user-based item similarity and item-based user similarity) method are the best in most cases. The potential preference scores calculated by the UIIU method are used for further studying.(2) With the observation that each user has his/her own chosen intention on different service systems and most people’s chosen intention about items have continuity and do not change suddenly, the Latent Dirichlet Allocation (LDA) model is used to realize this observation. The user’s chosen intention is considered as the hidden variable, and two distributions (user-chosen intention distribution and item-chosen intention distribution) are updated during the learning process of the model. The users’ potential preference scores can be obtained by the inner product of two distributions. Experimental results of the LDA-based method are better than BPR across all evaluation metrics on three datasets.(3) For alleviating the assumption in BPR that equal importance of the huge unobserved items, the novel model PBPR is proposed. It relaxes the simple pairwise preference assumption in BPR by further considering the pairwise preference between any two unobserved items. PBPR considers the situation of existing fine-grained preference difference between any two unobserved items of a user. It assumes the user prefers an unobserved item with a higher potential preference score over another unobserved item. PBPR* is proposed to enhance the performance of PBPR by conducting several strategies to overcome shortcomings in PBPR, for more accurate recommendation results.(4) With the consideration that the user’s preference difference between the observed item and the unobserved item can be reduced by fusing a relatively smaller preference difference between another pair of items, DBPL is proposed by taking two pairwise preferences into the previous pairwise learning model. DBPL also takes into account each user’s fine-grained preference differences between unobserved items. For each user, the unobserved item, which has a higher potential preference score, is assumed to have a smaller preference difference with the observed item of the user. Theoretically, DBPL could alleviate the vanishing gradient problem in the previous algorithm’s learning procedure and obtain more accurate recommendations.(5) A series of experiments over three real-world datasets are conducted to validate three recommendation models. Experimental results show the effectiveness of recommendation models for solving the one-class collaborative filtering problem. The experimental results of PBPR, PBPR* and DBPL are better than BPR, showing the effectiveness of assumptions proposed for recommendation models. Experimental results of the PBPR*-based method are better than the PBPR-based method in most cases. Experimental results of the DBPL-based recommendation method outperform other recommendation methods across all evaluation metrics on all datasets.

特異性を考慮したオントロジー生成によるウェブサービスクラスタリング及びレコメンデーションの改善 / ルパシンハアラチチラゲ, ヒルニマドゥーシャルパシンハほか

Sat, 06 Jun 2026 13:51:15 +0900

ルパシンハアラチチラゲ, ヒルニマドゥーシャルパシンハ; RUPASINGHA ARACHCHILAGE, Hiruni Madhusha Rupasingha. 特異性を考慮したオントロジー生成によるウェブサービスクラスタリング及びレコメンデーションの改善. 2019-03-20. DOI:10.15016/00000155; 10.15016/00000155

複数の基準に基づく推薦システムのモデル化のための新しい機械学習方法 / ハッサン, モハメドほか

Sat, 06 Jun 2026 13:52:14 +0900

ハッサン, モハメド; HASSAN, Mohammed. 複数の基準に基づく推薦システムのモデル化のための新しい機械学習方法. 2018-03-20. DOI:10.15016/00000143; 10.15016/00000143

被覆に基づくラフ集合を用いた推薦システムに関する研究 / 張, 志鵬

Thu, 30 Oct 2025 19:46:30 +0900

張, 志鵬. 被覆に基づくラフ集合を用いた推薦システムに関する研究. 2017-09-25. DOI:10.15118/00009628; 10.15118/00009628
With the rapid development of Internet, the human race has entered the information society and the network era. Internet could provide people with more and more information and services; however, people have to face enormous data and useless information when they enjoy the convenience brought by Internet. Recommender system (RS) has emerged in response to this challenge, which can advise users when making decisions and help users discover items they might not find by themselves. Collaborative filtering (CF) approach is popularly used in RSs owing to its satisfactory performance. Generally speaking, user-based collaborative filtering (UBCF) and item-based collaborative filtering (IBCF) are two significant approaches in CF, they have been successfully applied to many commercial RSs. However, with various kinds of data and complicated application environment, CF approaches are facing many challenges. For instance, UBCF cannot provide recommendations for an active user with satisfactory accuracy and diversity simultaneously. Personalized recommendations cannot be provided by UBCF for a new user which often has insufficient information. In addition, items that make a more significant contribution cannot have high weighting in IBCF. In view of the above key issues, this dissertation launched a study of the following aspects: (1) Aiming to provide personalized recommendations for an active user, we apply covering-based rough sets to improve UBCF, and propose a new covering-based collaborative filtering (CBCF) approach. CBCF inserts a user reduction procedure into UBCF, covering reduction in covering-based rough sets is utilized to remove redundant users from all users. Then, k-nearest neighbors are selected from candidate neighbors comprised by the reduct-users. Our experiment results suggest that, for the sparse datasets that often occur in real RSs, CBCF outperforms than the UBCF, and can provide satisfactory accuracy and coverage for an active user at the same time. (2) In order to provide personalized recommendations for a new user, through a detailed analysis of the characteristic of new users, we reconstruct a decision class to improve the previous CBCF. Unlike the previous CBCF, the decision class in improved CBCF can be extracted easily from the user-item rating matrix. Furthermore, the improved CBCF could provide personalized recommendations without needing special additional information. Our experiment results suggest that the improved CBCF significantly outperforms those of existing work and can provide personalized recommendations for a new user with satisfactory accuracy and diversity simultaneously. (3) The traditional IBCF approach treats all items as the same weighting; however, because some items may have more important impact when computing the similarity and predictions, item-variance weighting should also be considered. In this paper, we present the time-based correlation degree and covering degree, and apply them to the traditional IBCF approach to rearrange the item weighting. Our experimental results suggest that, our proposed approach can produce recommendations superior to the traditional IBCF and other existing work.; インターネットの高速な発展に従って、人類は情報社会とネットワークの時代に入った。人々はインターネットから多くの情報と便利なサービスが得られる一方で、膨大なデータ及び無駄な情報にも接することになる。推薦システム（RS）はこの問題に呼応して出現した。RSはユーザーの決定と自身によって見つけられないアイテムの発見を助けることができる。協調フィルタリング（CF）は良好な性能のため、RSに広く応用されている。一般的に言えば、ユーザベース協調フィルタリング（UBCF）とアイテムベース協調フィルタリング（IBCF）の二つはCFにおいて重要なアプローチであり、多くの商業RSに適用されている。しかし、様々なデータ及び複雑なアプリケーション環境の影響で、CFは多くの問題に直面している。例えば、UBCFはアクティブユーザーに対する推薦で高い推薦精度と推薦の多様性を両立させることができない。また、UBCFは十分な情報を持っていない新しいユーザーに個人化した推薦を提供することができない。さらに、IBCFではアイテムの重要性によって、重みに差を付けることができない。上記の問題点を考慮して、この論文では以下の研究を行った：（１）アクティブユーザーに個人化した推薦を提供するために、被覆に基づくラフ集合を用いた新しいカバーベース協調フィルタリング（CBCF）を提案した。CBCFでは被覆に基づくラフ集合における被覆縮約をUBCFに導入し、すべてのユーザーから冗長なユーザーを削除する。そして、ｋ―最近傍ユーザーは縮約したユーザーから選択される。実験結果によって、現実の推薦システムでよく現れる疎なデータについて、CBCFはUBCFより性能が良く、アクティブユーザーに対する推薦で高い推薦精度と推薦の多様性を両立できることが示された。（２）新しいユーザーに個人化した推薦を提供するために、新しいユーザーの特徴の詳細な分析を通じて、決定クラスを再定義することで、CBCFを改良した。元のCBCFと異なり、改良されたCBCFの決定クラスはユーザーアイテム評価行列から容易に抽出される。さらに、改良されたCBCFは特別な追加の情報を必要とせずに、個人化した推薦を提供することができる。実験結果によって、改良されたCBCFは既存の関連研究より良く、新しいユーザーに対する推薦で高い推薦精度と推薦の多様性を両立できることが示された。（３）伝統的なIBCFはすべてのアイテムに同じ重みを与える。しかし、類似度と予測値を計算する時に、いくつかのアイテムがより重要な影響を持つ可能性がある。アイテムの分散重み付けもまた考慮されるべきである。この論文では、アイテムの重みを付け直すために、時間ベース協調度と被覆度を提案して、伝統的なIBCFに適用した。実験結果によって、提案したIBCFは伝統的なIBCFと他の関連研究に比べて、良い推薦結果を提供することが確認された。

国立国会図書館サーチRSS - 検索

Research on Recommendation Models for One-class Collaborative Filtering / 张, 茜

On the Evaluation of Intraday Market Quality in the Limit-Order Book Markets : A Collaborative Filtering Approach / Hayashi, Takakiほか

協調フィルタリングに基づく授業推薦システム (Webと教育支援,ライフログ活用技術,オフィスインフォメーションシステム,ライフインテリジェンス,一般) / 蒋, 再興ほか

協調フィルタリングに基づく改良版授業推薦システムの構築と評価 (推薦システム,グループウェアとネットワーク,ライフログ活用技術,オフィス情報システム,セキュリティ心理学とトラスト,一般) / 蒋, 再興ほか

スペクトル観点から効果的かつ効率的な個人推薦に向けて / ポン, シャオウェン

Research on Recommendation Models for One-class Collaborative Filtering / 张, 茜

特異性を考慮したオントロジー生成によるウェブサービスクラスタリング及びレコメンデーションの改善 / ルパシンハ アラチチラゲ, ヒルニ マドゥーシャ ルパシンハほか

複数の基準に基づく推薦システムのモデル化のための新しい機械学習方法 / ハッサン, モハメドほか

被覆に基づくラフ集合を用いた推薦システムに関する研究 / 張, 志鵬

特異性を考慮したオントロジー生成によるウェブサービスクラスタリング及びレコメンデーションの改善 / ルパシンハアラチチラゲ, ヒルニマドゥーシャルパシンハほか