基于模糊聚类的协同过滤算法

针对传统协同过滤算法普遍存在的稀疏性和扩展性问题,提出一种基于模糊聚类的协同过滤算法。利用模糊聚类的方法对项目进行聚类,通过用户-项目评分矩阵计算用户之间的相似度,从中选出与用户最相似的前k个用户,根据这k个用户对当前用户的未评分项目的打分进行预测,选出前n个推荐。实验结果证明,与基于用户的协同过滤算法相比,该算法能提高冷启动问题下的相似度计算精度。     

一种融合聚类与用户兴趣偏好的协同过滤推荐算法

协同过滤推荐算法可以根据已知用户的偏好预测其可能感兴趣的项目,是现今最为成功、应用最广泛的推荐技术。然而,传统的协同过滤推荐算法受限于数据稀疏性问题,推荐结果较差。目前的协同过滤推荐算法大多只针对用户-项目评分矩阵进行数据分析,忽视了项目属性特征及用户对项目属性特征的偏好。针对上述问题,提出了一种融合聚类和用户兴趣偏好的协同过滤推荐算法。首先根据用户评分矩阵与项目类型信息,构建用户针对项目类型的用户兴趣偏好矩阵;然后利用K-Means算法对项目集进行聚类,并基于用户兴趣偏好矩阵查找待估值项所对应的近邻用户;在此基础上,通过结合项目相似度的加权Slope One算法在每一个项目类簇中对稀疏矩阵进行填充,以缓解数据稀疏性问题;进而基于用户兴趣偏好矩阵对用户进行聚类;最后,面向填充后的评分矩阵,在每一个用户类簇中使用基于用户的协同过滤算法对项目评分进行预测。实验结果表明,所提算法能够有效缓解原始评分矩阵的稀疏性问题,提升算法的推荐质量。     

基于项目聚类的全局最近邻的协同过滤算法

用户评分数据极端稀疏的情况下,传统相似性度量方法存在弊端,导致推荐系统的推荐质量急剧下降。针对 此问题,提出了一种基于项目聚类的全局最近部的协同过滤算法。该算法根据项目之间的相似性进行聚类,使得相似 性较高的项目聚成一类,在项目聚类集的基础上,计算用户的局部相似度,使用一种新的最近部用户全局相似度作为 衡量用户间相似性的标准;其次,给出了一种利用重叠度因子来调节局部相似度的方法,以更准确地刻画用户之间的 相似性。实验结果表明,该算法可以提升预测结果的准确性,提高推荐质量,特别是在数据较为稀疏时,改善尤为明 显。     

一种优化聚类的协同过滤推荐算法

针对传统的协同过滤推荐算法存在评分数据稀疏和推荐准确率偏低的问题,提出了一种优化聚类的协同过滤推荐算法。根据用户的评分差异对原始评分矩阵进行预处理,再将得到的用户项目评分矩阵以及项目类型矩阵构造用户类别偏好矩阵,更好反映用户的兴趣偏好,缓解数据的稀疏性。在该矩阵上利用花朵授粉优化的模糊聚类算法对用户聚类,增强用户的聚类效果,并将项目偏好信息的相似度与项目评分矩阵的相似度进行加权求和,得到多个最近邻居。融合时间因素对目标用户进行项目评分预测,改善用户兴趣变化对推荐效果的影响。通过在MovieLens 100k数据集上实验结果表明,提出的算法缓解了数据的稀疏性问题,提高了推荐的准确性。     

基于多维特征交叉的深度协同过滤算法

基于深度学习的推荐算法最初以用户和物品的ID信息作为输入,但是ID无法很好地表现用户与物品的特征。在原始数据中,用户对物品的评分数据在一定程度上能表现出用户和物品的特征,但是未考虑用户的评分偏好以及物品的热门程度。在评分任务中使用隐式反馈和ID信息作为用户与物品的特征,在消除用户主观性对特征造成的噪声的同时在一定程度上缓解冷启动问题,利用单层神经网络对原始高维稀疏特征降维,使用特征交叉得到用户与物品的低阶交互,再利用神经网络捕获用户与物品的高阶交互,有效提取了特征间的高低阶交互。在四个公开数据集上的实验表明,该算法能有效提高推荐精度。     

基于聚类和用户偏好的协同过滤推荐算法

协同过滤推荐算法使用评分数据作为学习的数据源,针对协同过滤推荐算法中存在的评分数据稀疏以及算法的可拓展性问题,提出了一种基于聚类和用户偏好的协同过滤推荐算法。为了挖掘用户的偏好,该算法引入了用户对项目类型的平均评分到评分矩阵中,并加入了基于用户自身属性的相似度;同时,为了降低数据稀疏性,该算法使用Weighted Slope One算法填充评分数据中的未评分项,并通过融入密度和距离优化初始聚类中心的K-means算法聚类填充后的评分数据中的用户,缩小了相似用户的搜索空间;最后在聚类后的数据集中使用传统的协同过滤推荐算法生成目标用户的推荐结果。通过使用MovieLens100K数据集实验证明,提出的算法对推荐效果有所改善。     

融合评分矩阵和评论文本深度神经网络推荐模型

针对个性化推荐中用户评分矩阵数据集稀疏,用户和项目描述信息未充分利用的问题,提出融合评分矩阵和评论文本的深度神经网络推荐模型(deep neural network recommendation model,DeepRec)。首先将通过数据预处理得到的用户偏好特征和项目属性特征的文本集合分别输入到卷积神经网络进行训练,得到用户和项目的深层次非线性特征,同时将评分矩阵输入多层感知机得到用户偏好隐表示,并对两种模型提取的用户偏好隐表示进行融合;其次利用多层感知机建模用户和项目隐表示对用户进行个性化推荐;最后基于三组数据集以均方根误差为评估指标进行对比实验。结果表明DeepRec的预测误差更低,有效提高了推荐的精准度。     

云模型与用户聚类的个性化推荐

针对传统推荐系统数据稀疏、相似性计算方法导致共同评分用户少的问题,提出利用云模型定性概念与定量数值转换的优势,研究云模型、用户聚类的个性化推荐改进算法。用户对项目属性评价的偏好,转换为用户对加权综合云模型表示的数字特征的偏好。利用改进的聚类算法,对评分数据、原始用户属性标准化后的信息进行聚类;同时考虑用户兴趣的变化,结合用户之间项目属性评价的综合云模型的相似度、用户对项目评分的聚类、用户属性聚类这三种方法产生的邻居用户的并集进行推荐。理论分析和实验结果表明,提出的改进算法不但解决数据稀疏性带来的共同评分用户少的弊端,即使是在新用户的情况下,仍能获得较低的平均绝对误差和平均平方误差     

Exploiting interactions of review text,hidden user communities and item groups,and time for collaborative filtering

Rich side information concerning users and items are valuable for collaborative filtering (CF) algorithms for recommendation. For example, rating score is often associated with a piece of review text, which is capable of providing valuable information to reveal the reasons why a user gives a certain rating. Moreover, the underlying community and group relationship buried in users and items are potentially useful for CF. In this paper, we develop a new model to tackle the CF problem which predicts user’s ratings on previously unrated items by effectively exploiting interactions among review texts as well as the hidden user community and item group information. We call this model CMR (co-clustering collaborative filtering model with review text). Specifically, we employ the co-clustering technique to model the user community and item group, and each community–group pair corresponds to a co-cluster, which is characterized by a rating distribution in exponential family and a topic distribution. We have conducted extensive experiments on 22 real-world datasets, and our proposed model CMR outperforms the state-of-the-art latent factor models. Furthermore, both the user’s preference and item profile are drifting over time. Dynamic modeling the temporal changes in user’s preference and item profiles are desirable for improving a recommendation system. We extend CMR and propose an enhanced model called TCMR to consider time information and exploit the temporal interactions among review texts and co-clusters of user communities and item groups. In this TCMR model, each community–group co-cluster is characterized by an additional beta distribution for time modeling. To evaluate our TCMR model, we have conducted another set of experiments on 22 larger datasets with wider time span. Our proposed model TCMR performs better than CMR and the standard time-aware recommendation model on the rating score prediction tasks. We also investigate the temporal effect on the user–item co-clusters.     

一种基于特征属性的Web用户模糊聚类改进算法

为降低传统FCM算法的计算复杂性,提高Web用户聚类的效果,文中提出了一种改进的基于特征属性的Web用户模糊聚类算法。首先通过用户访问页面的次数和时间建立Web用户兴趣度矩阵,并根据商品的特征属性值将Web用户兴趣度矩阵映射为用户对特征属性的偏好矩阵,从而有效降低数据稀疏性;然后以此为数据集,对传统的FCM算法进行了改进,将聚类中心分为活动和稳定两种,忽略稳定聚类中的距离计算以降低计算复杂性。最后通过仿真实验证实了新算法的有效性和可行性。     

Rating prediction for recommendation: Constructing user profiles and item characteristics using backpropagation

Recommender systems play an important role in quickly identifying and recommending most acceptable products to the users. The latent user factors and item characteristics determine the degree of user satisfaction on an item. While many of the methods in the literature have assumed that these factors are linear, there are some other methods that treat these factors as nonlinear; but they do it in a more implicit way. In this paper, we have investigated the effect of true nature (i.e., nonlinearity) of the user factors and item characteristics, and their complex layered relationship on rating prediction. We propose a new deep feedforward network that learns both the factors and their complex relationship concurrently. The aim of our study was to automate the construction of user profiles and item characteristics without using any demographic information and then use these constructed features to predict the degree of acceptability of an item to a user. We constructed the user and item factors by using separate learner weights at the lower layers, and modeled their complex relationship in the upper layers. The construction of the user profiles and the item characteristics, solely based on rating triples (i.e., user id, item id, rating), overcomes the requirement of explicit demographic information be given to the system. We have tested our model on three real world datasets: Jester, Movielens, and Yahoo music. Our model produces better rating predictions than some of the state-of-the-art methods which use demographic information. The root mean squared error incurred by our model on these datasets are 4.0873, 0.8110, and 0.9408 respectively. The errors are smaller than current best existing models’ errors in these datasets. The results show that our system can be integrated to any web store where development of hand engineered features for recommending products is less feasible due to huge traffics and also that there is a lack of demographic information about the users and the items.     

基于用户情景的协同过滤推荐

为提高基于项目的协同推荐算法的预测效果,引入用户情景因素。首先计算用户情景因素的相异度矩阵,然后按照用户间相异度大小,采用基于等价相异度矩阵聚类算法对用户进行聚类。在聚类后的用户簇中,选取与目标项目相异度小的项目作为近邻,为用户对目标项目进行评分预测。最后,在标准的MovieLens数据集上进行实验。通过对改进的推荐算法与经典的基于项目的协同推荐算法Slope One进行比较,实验数据表明改进后算法的推荐结果有较大提高。     

Personalized recommendation based on review topics

The traditional collaborative filtering algorithm is a successful recommendation technology. The core idea of this algorithm is to calculate user or item similarity based on user ratings and then to predict ratings and recommend items based on similar users’ or similar items’ ratings. However, real applications face a problem of data sparsity because most users provide only a few ratings, such that the traditional collaborative filtering algorithm cannot produce satisfactory results. This paper proposes a new topic model-based similarity and two recommendation algorithms: user-based collaborative filtering with topic model algorithm (UCFTM, in this paper) and item-based collaborative filtering with topic model algorithm (ICFTM, in this paper). Each review is processed using the topic model to generate review topic allocations representing a user’s preference for a product’s different features. The UCFTM algorithm aggregates all topic allocations of reviews by the same user and calculates the user most valued features representing product features that the user most values. User similarity is calculated based on user most valued features, whereas ratings are predicted from similar users’ ratings. The ICFTM algorithm aggregates all topic allocations of reviews for the same product, and item most valued features representing the most valued features of the product are calculated. Item similarity is calculated based on item most valued features, whereas ratings are predicted from similar items’ ratings. Experiments on six data sets from Amazon indicate that when most users give only one review and one rating, our algorithms exhibit better prediction accuracy than other traditional collaborative filtering and state-of-the-art topic model-based recommendation algorithms.     

结合用户聚类和评分偏好的推荐算法*

针对推荐算法中用户评分矩阵维度高、计算量大的问题,为更加真实地反映用户本身评分偏好,提出一种结合用户聚类和评分偏好的推荐算法。先利用PCA降维和k-means聚类对用户评分矩阵进行预处理,在最近邻选取方法上,添加用户共同评分数量作为约束,利用用户和相似簇的相似度对相似簇内评分加权求和生成基本预测评分;再综合用户评分偏置和用户项目类型偏好,建立用户评分偏好模型;最后通过多元线性回归确定每部分的权重,生成最终的预测评分。对比实验结果表明,新算法能更真实地反映用户评分,有效减少计算量并提高推荐系统的预测准确率,更好地满足用户对于推荐系统的个性化需求。     

基于用户多样性偏好的top-N推荐算法

传统推荐算法主要关注推荐准确性,而用户对项目的不同偏好和多样性需求也影响着用户体验和满意度。针对该问题,提出了一种新的算法,在计算项目相似度时结合了用户对不同项目的评分差异,以此可以提高项目相似度计算的准确性,根据用户历史评分数据和项目类别数据得到用户-类别权重矩阵,一方面以此计算基于熵的多样性,另外根据用户对项目的兴趣计算公式,生成一个降序排列的初始推荐序列,根据用户偏好误差门限,并结合用户-类别权重矩阵实现基于用户偏好的推荐,最终生成[N]个推荐的项目,同时保证准确率和多样性的前提下,提高用户满意度。在数据集movielens的多个版本上,与多个经典算法比较,实验结果表明,提出的算法可以有效提高推荐精度和用户满意度。     

一种融合信任和项目卷积描述信息的PMF算法

针对现有概率矩阵分解(PMF)技术的个性化推荐系统在采用社交网络中信任信息时常常忽视项目相关描述文档信息的问题,提出一种融合用户信任和通过卷积网络以获取项目描述等信息的PMF模型.首先,利用用户偏好信息和行为轨迹信息构建一种新的信任网络;然后,通过卷积神经网络从项目描述文档中提取项目潜在的特征向量;最后,在概率矩阵分解过程中同时利用评分数据、信任网络中用户的信任信息和项目的描述信息,计算用户和项目的潜在特征向量以预测评分并进行个性化推荐.为验证算法的有效性,选择3种算法在4个数据集上进行对比,实验结果表明所提出的算法在推荐精确度和鲁棒性方面优于其他3种算法.     

An ensemble method for top-N recommendations from the SVD

Matrix factorization methods such as the singular value decomposition technique have become very popular in the area of recommender systems. Given a rating matrix as input, these techniques output two matrixes with lower dimensional space that represent the user and item features. The relevance of item i to user u is revealed by the score of the dot product between u vector of features and i vector of features. High scores indicate greater relevance. In order to deliver the best recommendations for a given user based on these latent features, one must obtain the list of scores of all the items for the given user and sort the resulting list. When the size of the catalogue is large, this phase consumes a large amount of computational time and cannot be done online. Another drawback with this approach is that once such a list is computed for a given user, it remains finite and it is impossible to incorporate within it new activities of the user. Hence, the use of such techniques is limited online.In this paper we propose an ensemble method for building a forest of trees offline, where each leaf in each tree is holding a unique set of item vectors. Once a user is engaged with the system, its vector is classified to one leaf in each one of the trees in the forest for conducting a dot product with the corresponding items. By using this method we compute online only a small number of dot products for a given user vector allowing us to quickly retrieve dynamic recommendations from the SVD, thereby presenting an alternative to the existing method which computes and caches all of the dot products among the items and users. The method maps the items to the leaves of multiple compact trees offline, each tree is a weak recommendation model, creating a forest of decision trees algorithm in which users that are assigned to these leaves online are likely to produce high dot product scores with the items that are already in the leaves. We demonstrate the effectiveness of the suggested ensemble method by applying it to three public datasets and comparing it to a state-of-the-art algorithm aimed at solving the problem.     

基于蜂群K-means聚类模型的协同过滤推荐算法

针对目前协同过滤推荐算法的推荐质量和推荐效率低的问题,提出了一种基于改进蜂群K-means聚类模型的协同过滤推荐算法。首先,根据用户属性信息,采用改进蜂群K-means算法对用户进行聚类,建立用户聚类模型;然后,计算目标用户与用户聚类模型中各聚类中心的距离,其中距离最近的类为目标用户的检索空间;最后,从检索空间中依据用户-项目评分矩阵通过相似度计算搜索目标用户的最近邻居,由最近邻居的信息产生推荐列表。实验结果表明,该算法降低了平均绝对误差值,缩短了运行时间,提高了推荐质量和推荐效率。     

基于聚类和项目相似性的Slope One算法优化

随着用户项目数量的增长,用户项目矩阵变得越来越稀疏,使用基于最小生成树的k-means算法对项目进行聚类并以聚类结果对用户评分矩阵进行预测填充。考虑到Slope One算法存在用户兴趣变化问题,将时间权重加入Slope One算法中进行评分预测。将改进后的算法在Movie Lens数据集上进行验证,结果表明,改进后的算法可有效解决稀疏性问题和用户兴趣变化问题,并将MAE值降低到0.015以下。     

A novel classification-based shilling attack detection approach for multi-criteria recommender systems

Recommender systems are emerging techniques guiding individuals with provided referrals by considering their past rating behaviors. By collecting multi-criteria preferences concentrating on distinguishing perspectives of the items, a new extension of traditional recommenders, multi-criteria recommender systems reveal how much a user likes an item and why user likes it; thus, they can improve predictive accuracy. However, these systems might be more vulnerable to malicious attacks than traditional ones, as they expose multiple dimensions of user opinions on items. Attackers might try to inject fake profiles into these systems to skew the recommendation results in favor of some particular items or to bring the system into discredit. Although several methods exist to defend systems against such attacks for traditional recommenders, achieving robust systems by capturing shill profiles remains elusive for multi-criteria rating-based ones. Therefore, in this study, we first consider a prominent and novel attack type, that is, the power-item attack model, and introduce its four distinct variants adapted for multi-criteria data collections. Then, we propose a classification method detecting shill profiles based on various generic and model-based user attributes, most of which are new features usually related to item popularity and distribution of rating values. The experiments conducted on three benchmark datasets conclude that the proposed method successfully detects attack profiles from genuine users even with a small selected size and attack size. The empirical outcomes also demonstrate that item popularity and user characteristics based on their rating profiles are highly beneficial features in capturing shilling attack profiles.