基于深度学习的论文个性化推荐算法

该文基于学术搜索和数据挖掘平台Aminer向用户进行个性化推荐,提出了结合协同过滤推荐和基于内容推荐的混合模型,实验表明该算法可以有效解决新物品的推荐问题,即冷启动问题。其中在基于内容推荐的模型中,融合深度学习的方法,引进了词向量模型,将用户和论文映射到用词向量空间, 并使用WMD(Word Mover Distance)计算相似度。实验表明,与其他基线模型相比该文提出的推荐模型在准确率上显著提高了4%。     

协同过滤推荐系统综述

随着互联网和信息计算的飞速发展,衍生了海量数据,我们已经进入信息爆炸的时代。网络中各种信息量的指数型增长导致用户想要从大量信息中找到自己需要的信息变得越来越困难,信息过载问题日益突出。推荐系统在缓解信息过载问题中起着非常重要的作用,该方法通过研究用户的兴趣偏好进行个性化计算,由系统发现用户兴趣进而引导用户发现自己的信息需求。目前,推荐系统已经成为产业界和学术界关注、研究的热点问题,应用领域十分广泛。在电子商务、会话推荐、文章推荐、智慧医疗等多个领域都有所应用。传统的推荐算法主要包括基于内容的推荐、协同过滤推荐以及混合推荐。其中,协同过滤推荐是推荐系统中应用最广泛最成功的技术之一。该方法利用用户或物品间的相似度以及历史行为数据对目标用户进行推荐,因此存在用户冷启动和项目冷启动问题。此外,随着信息量的急剧增长,传统协同过滤推荐系统面对数据的快速增长会遇到严重的数据稀疏性问题以及可扩展性问题。为了缓解甚至解决这些问题,推荐系统研究人员进行了大量的工作。近年来,为了提高推荐效果、提升用户满意度,学者们开始关注推荐系统的多样性问题以及可解释性等问题。由于深度学习方法可以通过发现数据中用户和项目之间的非线性关系从而学习一个有效的特征表示,因此越来越受到推荐系统研究人员的关注。目前的工作主要是利用评分数据、社交网络信息以及其他领域信息等辅助信息,结合深度学习、数据挖掘等技术提高推荐效果、提升用户满意度。对此,本文首先对推荐系统以及传统推荐算法进行概述,然后重点介绍协同过滤推荐算法的相关工作。包括协同过滤推荐算法的任务、评价指标、常用数据集以及学者们在解决协同过滤算法存在的问题时所做的工作以及努力。最后提出未来的几个可研究方向。     

基于Jaccard相似度和位置行为的协同过滤推荐算法

协同过滤是现今推荐系统中应用最为成功且最广泛的推荐方法之一,其中概率矩阵分解算法作为一类重要的协同过滤方式,能够通过学习低维的近似矩阵进行推荐。然而,传统的协同过滤推荐算法在推荐过程中只利用用户-项目评分信息,忽略了用户(项目)间的潜在影响力,影响了推荐精度。针对上述问题,首先利用Jaccard相似度对用户(项目)做预处理,而后通过用户(项目)间的位置信息挖掘出其间的潜在影响力,成功找到最近邻居集合;最后将该邻居集合融合到基于概率矩阵分解的协同过滤推荐算法中。实验证明该算法较传统的协同过滤推荐算法能够更有效地预测用户的实际评分,提高了推荐效果。     

A time-based approach to effective recommender systems using implicit feedback

Recommender systems provide personalized recommendations on products or services to customers. Collaborative filtering is a widely used method of providing recommendations using explicit ratings on items from users. In some e-commerce environments, however, it is difficult to collect explicit feedback data; only implicit feedback is available.

In this paper, we present a method of building an effective collaborative filtering-based recommender system for an e-commerce environment without explicit feedback data. Our method constructs pseudo rating data from the implicit feedback data. When building the pseudo rating matrix, we incorporate temporal information such as the user’s purchase time and the item’s launch time in order to increase recommendation accuracy.

Based on this method, we built both user-based and item-based collaborative filtering-based recommender systems for character images (wallpaper) in a mobile e-commerce environment and conducted a variety of experiments. Empirical results show our time-incorporated recommender system is significantly more accurate than a pure collaborative filtering system.     

基于项目属性的用户聚类协同过滤推荐算法

协同过滤推荐算法是个性化推荐服务系统的关键技术,由于项目空间上用户评分数据的极端稀疏性,传统推荐系统中的用户相似度量算法开销较大并且无法保证项目推荐精度.通过对共同感兴趣的项目属性的相似用户进行聚类,构建了不同项目评价的用户相似性,设计了一种优化的协同过滤推荐算法.实验结果表明,该算法能够有效避免由于数据稀疏性带来的弊端,提高了系统的推荐质量.     

Probabilistic memory-based collaborative filtering

Memory-based collaborative filtering (CF) has been studied extensively in the literature and has proven to be successful in various types of personalized recommender systems. In this paper, we develop a probabilistic framework for memory-based CF (PMCF). While this framework has clear links with classical memory-based CF, it allows us to find principled solutions to known problems of CF-based recommender systems. In particular, we show that a probabilistic active learning method can be used to actively query the user, thereby solving the "new user problem." Furthermore, the probabilistic framework allows us to reduce the computational cost of memory-based CF by working on a carefully selected subset of user profiles, while retaining high accuracy. We report experimental results based on two real-world data sets, which demonstrate that our proposed PMCF framework allows an accurate and efficient prediction of user preferences.     

基于时序行为的协同过滤推荐算法

协同过滤直接根据用户的行为记录去预测其可能喜欢的产品,是现今最为成功、应用最广泛的推荐方法.概率矩阵分解算法是一类重要的协同过滤方式.它通过学习低维的近似矩阵进行推荐,能够有效处理海量数据.然而,传统的概率矩阵分解方法往往忽略了用户(产品)之间的结构关系,影响推荐算法的效果.通过衡量用户(产品)之间的关系寻找相似的邻居用户(产品),可以更准确地识别用户的个人兴趣,从而有效提高协同过滤推荐精度.为此,提出一种对用户(产品)间的时序行为建模的方法.基于该方法,可以发现对当前用户(产品)影响最大的邻居集合.进一步地,将该邻居集合成功融合到基于概率矩阵分解的协同过滤推荐算法中.在两个真实数据集上的验证结果表明,所提出的SequentialMF 推荐算法与传统的使用社交网络信息与标签信息的推荐算法相比,能够更有效地预测用户实际评分,提升推荐精度.     

融合关系挖掘与协同过滤的物品冷启动推荐算法

针对新物品缺乏(非完全冷启动)或没有(完全冷启动)评分信息,协同过滤无法为新物品进行个性化推荐的问题,文中提出融合关系挖掘与协同过滤的推荐算法.首先,利用关系挖掘提取物品关系特征,根据属性之间的多种二元关系构建关系属性,丰富可用属性信息.然后,提出基于关系挖掘的近邻选取方法,增加邻近物品的多样性.最后,融合协同过滤方法,同时解决完全和非完全新物品冷启动问题,实现新物品的个性化推荐.在两个真实数据集上的实验表明,文中方法可以系统解决推荐系统中新物品的冷启动问题.     

Product recommendation with temporal dynamics

In many E-commerce recommender systems, a special class of recommendation involves recommending items to users in a life cycle. For example, customers who have babies will shop on Diapers.com within a relatively long period, and purchase different products for babies within different growth stages. Traditional recommendation algorithms produce recommendation lists similar to items that the target user has accessed before (content filtering), or compute recommendation by analyzing the items purchased by the users who are similar to the target user (collaborative filtering). Such recommendation paradigms cannot effectively resolve the situation with a life cycle, i.e., the need of customers within different stages might vary significantly. In this paper, we model users’ behavior with life cycles by employing hand-crafted item taxonomies, of which the background knowledge can be tailored for the computation of personalized recommendation. In particular, our method first formalizes a user’s long-term behavior using the item taxonomy, and then identifies the exact stage of the user. By incorporating collaborative filtering into recommendation, we can easily provide a personalized item list to the user through other similar users within the same stage. An empirical evaluation conducted on a purchasing data collection obtained from Diapers.com demonstrates the efficacy of our proposed method.     

A hybrid collaborative filtering method for multiple-interests and multiple-content recommendation in E-Commerce

Recommender systems apply knowledge discovery techniques to the problem of making personalized recommendations for products or services during a live interaction. These systems, especially collaborative filtering based on user, are achieving widespread success on the Web. The tremendous growth in the amount of available information and the kinds of commodity to Web sites in recent years poses some key challenges for recommender systems. One of these challenges is ability of recommender systems to be adaptive to environment where users have many completely different interests or items have completely different content (We called it as Multiple interests and Multiple-content problem). Unfortunately, the traditional collaborative filtering systems can not make accurate recommendation for the two cases because the predicted item for active user is not consist with the common interests of his neighbor users. To address this issue we have explored a hybrid collaborative filtering method, collaborative filtering based on item and user techniques, by combining collaborative filtering based on item and collaborative filtering based on user together. Collaborative filtering based on item and user analyze the user-item matrix to identify similarity of target item to other items, generate similar items of target item, and determine neighbor users of active user for target item according to similarity of other users to active user based on similar items of target item.In this paper we firstly analyze limitation of collaborative filtering based on user and collaborative filtering based on item algorithms respectively and emphatically make explain why collaborative filtering based on user is not adaptive to Multiple-interests and Multiple-content recommendation. Based on analysis, we present collaborative filtering based on item and user for Multiple-interests and Multiple-content recommendation. Finally, we experimentally evaluate the results and compare them with collaborative filtering based on user and collaborative filtering based on item, respectively. The experiments suggest that collaborative filtering based on item and user provide better recommendation quality than collaborative filtering based on user and collaborative filtering based on item dramatically.     

用于鲁棒协同推荐的元信息增强变分贝叶斯矩阵分解模型

托攻击是协同过滤推荐系统面临的重大安全威胁. 研究可抵御托攻击的鲁棒协同推荐技术已成为目前的重要课题. 本文在引入用户嫌疑性评估策略的基础上, 通过将用户嫌疑性及项类属等元信息与贝叶斯概率矩阵分解模型相融合, 提出了用于鲁棒协同推荐的元信息增强变分贝叶斯矩阵分解模型(Metadata-enhanced variational Bayesian matrix factorization, MVBMF), 并设计了相应的模型增量学习策略. 实验表明, 与现有推荐模型相比, 这种模型具备更强的攻击耐受力, 能够有效提高推荐系统的鲁棒性.     

Detection of the customer time-variant pattern for improving recommender systems

Due to the explosion of e-commerce, recommender systems are rapidly becoming a core tool to accelerate cross-selling and strengthen customer loyalty. There are two prevalent approaches for building recommender systems—content-based recommending and collaborative filtering. So far, collaborative filtering recommender systems have been very successful in both information filtering and e-commerce domains. However, the current research on recommendation has paid little attention to the use of time-related data in the recommendation process. Up to now there has not been any study on collaborative filtering to reflect changes in user interest.This paper suggests a methodology for detecting a user's time-variant pattern in order to improve the performance of collaborative filtering recommendations. The methodology consists of three phases of profiling, detecting changes, and recommendations. The proposed methodology detects changes in customer behavior using the customer data at different periods of time and improves the performance of recommendations using information on changes.     

基于用户声誉的鲁棒协同推荐算法

随着推荐系统在电子商务界的快速发展以及取得的巨大经济收益, 有目的性的托攻击是目前协同过滤系统面临的重大安全威胁, 研究一种可抵御攻击的鲁棒推荐技术已成为目前推荐系统领域的重要课题.本文利用历史记录得到用户声誉, 建立声誉推荐系统, 并结合协同过滤推荐领域内的隐语义模型, 提出基于用户声誉的隐语义模型鲁棒协同算法.本文提出的算法从人为攻击和自然噪声两个方面对系统的鲁棒性进行了改善.在真实的数据集 Movielens 1M 上的实验表明, 与现有的鲁棒性推荐算法相比, 这种算法具有形式简单、可解释性强、稳定的特点, 且在精度得到一定提升的情况下大大增强了系统抵御攻击的能力.     

一种基于用户兴趣局部相似性的推荐算法

协作过滤算法作为至今最成功的个性化推荐技术之一,被广泛应用于电子商务、个性化节目推荐等系统中。但传统的基于协作过滤的推荐系统一直受到系统的稀疏性、推荐精确度低等问题的困扰。提出了一种基于用户兴趣局部相似性的改进的协作推荐算法（CFUPS）,针对协作过滤算法中用户近邻的计算和项目评分的预测两关键步骤,基于用户间潜在的局部相似的兴趣,并结合项目资源属性和项目评分矩阵来预测项目评分,进而给用户推荐感兴趣的个性化资源,理论上在提高推荐精度、克服稀疏性问题上均有改善。同时实验表明,在极具稀疏性的数据集上,该算法的推荐精度较以往的协作过滤算法有明显提高。     

Recommendation agent impact on consumer online shopping: The Movie Magic case study

A simulated online shopping environment with a recommender system based on collaborative filtering data has been developed to empirically test the impact of recommendation agents in an online retail environment. The report provides some background for the most widely used types of recommender system based on collaborative filtering. The Movie Magic system developed for this study is described, as well as the experiment assessing the impact of such an agent on product promotion effectiveness, customer satisfaction with the website, and customer loyalty to the website. Finally, the report discusses the implications of the results for system developers and managers interested in using Intelligent Agent technology for enhancing e-commerce. By corroborating the proposed relationships between the use of the recommender agent and improved product promotion, customer satisfaction and loyalty, the results should aid online businesses in further understanding the benefits and limitations of using a recommender agent to support e-commerce.     

Collaborative user modeling for enhanced content filtering in recommender systems

Recommender systems, which have emerged in response to the problem of information overload, provide users with recommendations of content suited to their needs. To provide proper recommendations to users, personalized recommender systems require accurate user models of characteristics, preferences and needs. In this study, we propose a collaborative approach to user modeling for enhancing personalized recommendations to users. Our approach first discovers useful and meaningful user patterns, and then enriches the personal model with collaboration from other similar users. In order to evaluate the performance of our approach, we compare experimental results with those of a probabilistic learning model, a user model based on collaborative filtering approaches, and a vector space model. We present experimental results that show how our model performs better than existing alternatives.     

A personalized recommendation procedure for Internet shopping support

The rapid growth of e-commerce has caused product overload where the customer is no longer able to effectively choose the products he/she is exposed to. To overcome the product overload of Internet shoppers, several recommender systems have been developed. Recommendation systems track past actions of a group of customers to make a recommendation to individual members of the group. We introduce a personalized recommendation procedure by which we can get further recommendation effectiveness when applied to Internet shopping malls. The suggested procedure is based on Web usage mining, product taxonomy, association rule mining, and decision tree induction. We applied the procedure to a leading Internet shopping mall in Korea for performance evaluation, and some experimental results are provided. The experimental results show that choosing the right level of product taxonomy and the right customers increases the quality of recommendations.     

融合用户信任模型的协同过滤推荐算法

协同过滤推荐是电子商务系统中最为重要的技术之一.随着电子商务系统中用户数目和商品数目的增加,用户-项目评分数据稀疏性问题日益显著.传统的相似度度量方法是基于用户共同评分项目计算的,而过于稀疏的评分使得不能准确预测用户偏好,导致推荐质量急剧下降.针对上述问题,本文考虑用户评分相似性和用户之间信任关系对推荐结果的影响,利用层次分析法实现用户信任模型的构建,提出一种融合用户信任模型的协同过滤推荐算法.实验结果表明： 该算法能够有效反映用户认知变化,缓解评分数据稀疏性对协同过滤推荐算法的影响,提高推荐结果的准确度.     

基于Web日志挖掘和相关性度量的电子商务推荐系统

基于Web日志挖掘的个性化推荐技术已在电子商务网站中广泛应用,针对现有推荐系统的准确性不高等问题,提出一种基于Web日志挖掘和相关性度量的个性化推荐系统. 首先,提取用户的访问日志,并对其进行预处理,以获得精简的结构化数据. 然后,对日志进行分析,提取出特征序列. 再后,根据特征的出现频率和页面停留时间,计算出页面与交易文本文档的相关性. 最终,利用夹角余弦公式计算出用户与页面的相关性,并以此形成推荐列表. 实验结果表明,该方案能够根据用户偏好精确的给出个性化推荐.     

联邦推荐系统的协同过滤冷启动解决方法

基于联邦学习的推荐系统可以在保护用户隐私的情况下,联合多方数据,提升推荐系统的性能,已经成为推荐领域的研究热点之一.联邦协同过滤是联邦推荐系统中最经典及最常用的算法之一.然而,针对联邦协同过滤系统的冷启动问题的研究工作相对较少.针对这一问题,本文提出了一种基于安全内积协议的解决方案.具体地,在系统中添加新用户或新物品时...