Fuzzy-genetic approach to recommender systems based on a novel hybrid user model

The main strengths of collaborative filtering (CF), the most successful and widely used filtering technique for recommender systems, are its cross-genre or ‘outside the box’ recommendation ability and that it is completely independent of any machine-readable representation of the items being recommended. However, CF suffers from sparsity, scalability, and loss of neighbor transitivity. CF techniques are either memory-based or model-based. While the former is more accurate, its scalability compared to model-based is poor. An important contribution of this paper is a hybrid fuzzy-genetic approach to recommender systems that retains the accuracy of memory-based CF and the scalability of model-based CF. Using hybrid features, a novel user model is built that helped in achieving significant reduction in system complexity, sparsity, and made the neighbor transitivity relationship hold. The user model is employed to find a set of like-minded users within which a memory-based search is carried out. This set is much smaller than the entire set, thus improving system’s scalability. Besides our proposed approaches are scalable and compact in size, computational results reveal that they outperform the classical approach.     

一种检测兴趣漂移的图结构推荐系统

协同过滤是构造推荐系统最有效的方法之一.其中,基于图结构推荐方法成为近来协同过滤的研究热点.基于图结构的方法视用户和项为图的结点,并利用图理论去计算用户和项之间的相似度.尽管人们对图结构推荐系统开展了很多的研究和应用,然而这些研究都认为用户的兴趣是保持不变的,所以不能够根据用户兴趣的相关变化做出合理推荐.本文提出一种新的可以检测用户兴趣漂移的图结构推荐系统.首先,设计了一个新的兴趣漂移检测方法,它可以有效地检测出用户兴趣在何时发生了哪种变化.其次,根据用户的兴趣序列,对评分项进行加权并构造用户特征向量.最后,整合二部投影与随机游走进行项推荐.在标准数据集MovieLens上的测试表明算法优于两个图结构推荐方法和一个评分时间加权的协同过滤方法.     

Applications of wavelet data reduction in a recommender system

Memory-based collaborative filtering (CF) recommender systems have emerged as an effective technique for information filtering. CF recommenders are being widely adopted for e-commerce applications to assist users in finding and selecting items of interest. As a result, the scalability of CF recommenders presents a significant challenge; one that is particularly resilient because the volume of data these systems utilize will continue to increase over time. This paper examines the impact of discrete wavelet transformation (DWT) as an approach to enhance the scalability of memory-based collaborative filtering recommender systems. In particular, a wavelet transformation methodology is proposed and applied to both synthetic and real-world recommender ratings. For experimental purposes, the DWT methodology’s effect on predictive accuracy and calculation speed is evaluated to compare recommendation quality and performance.     

基于认知度的协同过滤推荐算法

协同过滤技术被广泛应用于各种推荐系统当中.基于内存的协同过滤算法通过比较目标用户与其他用户的已有评分,为目标用户的未评分项目作出相应的预测.提出了一种新的基于内存的算法.根据项目的关键属性对它们进行分类,通过计算用户对各类项目的认知度,为目标用户选择相似用户并预测评分.通过MovieLens数据集的实验结果表明,该算法可以有效地解决包括数据稀疏性和新用户在内的一些协同过滤的基本问题,提供更高质量的推荐.     

Rating prediction by exploring user’s preference and sentiment

With the development of e-commerce, shopping on-line is becoming more and more popular. The explosion of reviews have led to a serious problem, information overloading. How to mine user interest from these reviews and understand users’ preference is crucial for us. Traditional recommender systems mainly use structured data to mine user interest preference, such as product category, user’s tag, and the other social factors. In this paper, we firstly use LDA+Word2vec model to mine user interest. Then, we propose a social user sentimental measurement approach. At last, three factors, including user topic, user sentiment and interpersonal influence, are fused into a recommender system (RS) based on probabilistic matrix factorization. We conduct a series of experiments on Yelp dataset, and experimental results show the proposed approach outperforms the existing approaches.     

JacUOD: A New Similarity Measurement for Collaborative Filtering

Collaborative filtering(CF) has been widely applied to recommender systems,since it can assist users to discover their favorite items.Similarity measurement that measures the similarity between two users or items is critical to CF.However,traditional similarity measurement approaches for memory-based CF can be strongly improved.In this paper,we propose a novel similarity measurement,named Jaccard Uniform Operator Distance(JacUOD),to effectively measure the similarity.Our JacUOD approach aims at unifying similarity comparison for vectors in different multidimensional vector spaces.Compared with traditional similarity measurement approaches,JacUOD properly handles dimension-number difference for different vector spaces.We conduct experiments based on the well-known MovieLens datasets,and take user-based CF as an example to show the effectiveness of our approach.The experimental results show that our JacUOD approach achieves better prediction accuracy than traditional similarity measurement approaches.     

An empirical study on user-topic rating based collaborative filtering methods

User based collaborative filtering (CF) has been successfully applied into recommender system for years. The main idea of user based CF is to discover communities of users sharing similar interests, thus, in which, the measurement of user similarity is the foundation of CF. However, existing user based CF methods suffer from data sparsity, which means the user-item matrix is often too sparse to get ideal outcome in recommender systems. One possible way to alleviate this problem is to bring new data sources into user based CF. Thanks to the rapid development of social annotation systems, we turn to using tags as new sources. In these approaches, user-topic rating based CF is proposed to extract topics from tags using different topic model methods, based on which we compute the similarities between users by measuring their preferences on topics. In this paper, we conduct comparisons between three user-topic rating based CF methods, using PLSA, Hierarchical Clustering and LDA. All these three methods calculate user-topic preferences according to their ratings of items and topic weights. We conduct the experiments using the MovieLens dataset. The experimental results show that LDA based user-topic rating CF and Hierarchical Clustering outperforms the traditional user based CF in recommending accuracy, while the PLSA based user-topic rating CF performs worse than the traditional user based CF.     

Evaluation of recommender systems: A new approach

It is difficult to deny that comparison between recommender systems requires a common way for evaluating them. Nevertheless, at present, they have been evaluated in many, often incompatible, ways. We affirm this problem is mainly due to the lack of a common framework for recommender systems, a framework general enough so that we may include the whole range of recommender systems to date, but specific enough so that we can obtain solid results. In this paper, we propose such a framework, attempting to extract the essential features of recommender systems. In this framework, the most essential feature is the objective of the recommender system. What is more, in this paper, recommender systems are viewed as applications with the following essential objective. Recommender systems must: (i) choose which (of the items) should be shown to the user, (ii) decide when and how the recommendations must be shown. Next, we will show that a new metric emerges naturally from this framework. Finally, we will conclude by comparing the properties of this new metric with the traditional ones. Among other things, we will show that we may evaluate the whole range of recommender systems with this single metric.     

基于主题提取和记忆模型的新闻推荐系统设计

互联网的飞速发展产生了＂信息过载＂问题,新闻推荐系统可以帮助用户快速找到符合自己兴趣的新闻。文章完成了一个基于主题推荐的新闻推荐系统的研究和实现,针对该系统的关键部分即新闻主题和用户兴趣模型做了深入的研究并进行了程序上的实现。文章提出了一种基于主题的新闻推荐方式,将概率主题模型引入到文本推荐中,并深入研究了采用Gibbs抽样算法的LDA主题提取模型。文章在研究基于记忆的用户兴趣模型基础上提出了相应的改进方法,主要是针对记忆模型对用户长短期兴趣不适应的问题,提出了根据用户访问频率来确定不同兴趣度衰减速度的改进方案。     

Power coefficient as a similarity measure for memory-based collaborative recommender systems

E-commerce systems employ recommender systems to enhance the customer loyalty and hence increasing the cross-selling of products. However, choosing appropriate similarity measure is a key to the recommender system success. Based on this measure, a set of neighbors for the current active user is formed which in turn will be used later to recommend unseen items to this active user. Pearson correlation coefficient, the most popular similarity measure for memory-based collaborative recommender system (CRS), measures how much two users are correlated. However, statistic’s literature introduced many other coefficients for matching two sets (vectors) that may perform better than Pearson correlation coefficient. This paper explores Jaccard and Dice coefficients for matching users of CRS. A more general coefficient called a Power coefficient is proposed in this paper which represents a family of coefficients. Specifically, Power coefficient gives many degrees for emphasizing on the positive matches between users. However, CRS users have positive and negative matches and therefore these coefficients have to be modified to take negative matches into consideration. Consequently, they become more suitable for CRS research. Many experiments are carried out for all the proposed variants and are compared with the traditional approaches. The experimental results show that the proposed variants outperform Pearson correlation coefficient and cosine similarity measure as they are the most common approaches for memory-based CRS.     

Typicality‐based collaborative filtering for book recommendation

Nowadays, personalized recommender system placed an important role to predict the customer needs, interest about particular product in various application domains, which is identified according to the product ratings. During this process, collaborative filtering (CF) has been utilized because it is one of familiar techniques in recommender systems. The conventional CF methods analyse historical interactions of user‐item pairs based on known ratings and then use these interactions to produce recommendations. The major challenge in CF is that it needs to calculate the similarity of each pair of users or items by observing the ratings of users on same item, whereas the typicality‐based CF determines the neighbours from user groups based on their typicality degree. Typicality‐based CF can predict the ratings of users with improved accuracy. However, to eliminate the cold start problem in the proposed recommender system, the demographic filtering method has been employed in addition to the typicality‐based CF. A weighted average scheme has been applied on the combined recommendation results of both typicality‐based CF and demographic‐based CF to produce the best recommendation result for the user. Thereby, the proposed system has been able to achieve a coverage ratio of more than 95%, which indicates that the system is able to provide better recommendation for the user from the available lot of products.     

Collaborative filtering and deep learning based recommendation system for cold start items

Recommender system is a specific type of intelligent systems, which exploits historical user ratings on items and/or auxiliary information to make recommendations on items to the users. It plays a critical role in a wide range of online shopping, e-commercial services and social networking applications. Collaborative filtering (CF) is the most popular approaches used for recommender systems, but it suffers from complete cold start (CCS) problem where no rating record are available and incomplete cold start (ICS) problem where only a small number of rating records are available for some new items or users in the system. In this paper, we propose two recommendation models to solve the CCS and ICS problems for new items, which are based on a framework of tightly coupled CF approach and deep learning neural network. A specific deep neural network SADE is used to extract the content features of the items. The state of the art CF model, timeSVD++, which models and utilizes temporal dynamics of user preferences and item features, is modified to take the content features into prediction of ratings for cold start items. Extensive experiments on a large Netflix rating dataset of movies are performed, which show that our proposed recommendation models largely outperform the baseline models for rating prediction of cold start items. The two proposed recommendation models are also evaluated and compared on ICS items, and a flexible scheme of model retraining and switching is proposed to deal with the transition of items from cold start to non-cold start status. The experiment results on Netflix movie recommendation show the tight coupling of CF approach and deep learning neural network is feasible and very effective for cold start item recommendation. The design is general and can be applied to many other recommender systems for online shopping and social networking applications. The solution of cold start item problem can largely improve user experience and trust of recommender systems, and effectively promote cold start items.     

A Web service QoS prediction approach based on time- and location-aware collaborative filtering

In QoS-based Web service recommendation, predicting quality of service (QoS) for users will greatly aid service selection and discovery. Collaborative filtering (CF) is an effective method for Web service selection and recommendation. CF algorithms can be divided into two main categories: memory-based and model-based algorithms. Memory-based CF algorithms are easy to implement and highly effective, but they suffer from a fundamental problem: inability to scale-up. Model-based CF algorithms, such as clustering CF algorithms, address the scalability problem by seeking users for recommendation within smaller and highly similar clusters, rather than within the entire database. However, they are often time-consuming to build and update. In this paper, we propose a time-aware and location-aware CF algorithms. To validate our algorithm, this paper conducts series of large-scale experiments based on a real-world Web service QoS data set. Experimental results show that our approach is capable of addressing the three important challenges of recommender systems–high quality of prediction, high scalability, and easy to build and update.     

Collaborative filtering adapted to recommender systems of e-learning

In the context of e-learning recommender systems, we propose that the users with greater knowledge (for example, those who have obtained better results in various tests) have greater weight in the calculation of the recommendations than the users with less knowledge. To achieve this objective, we have designed some new equations in the nucleus of the memory-based collaborative filtering, in such a way that the existent equations are extended to collect and process the information relative to the scores obtained by each user in a variable number of level tests.     

From similarity perspective: a robust collaborative filtering approach for service recommendations

Collaborative filtering (CF) is a technique commonly used for personalized recommendation and Web service quality-of-service (QoS) prediction. However, CF is vulnerable to shilling attackers who inject fake user profiles into the system. In this paper, we first present the shilling attack problem on CF-based QoS recommender systems for Web services. Then, a robust CF recommendation approach is proposed from a user similarity perspective to enhance the resistance of the recommender systems to the shilling attack. In the approach, the generally used similarity measures are analyzed, and the DegSim (the degree of similarities with top k neighbors) with those measures is selected for grouping and weighting the users. Then, the weights are used to calculate the service similarities/differences and predictions.We analyzed and evaluated our algorithms using WS-DREAM and Movielens datasets. The experimental results demonstrate that shilling attacks influence the prediction of QoS values, and our proposed features and algorithms achieve a higher degree of robustness against shilling attacks than the typical CF algorithms.     

Bayesian dual neural networks for recommendation

Most traditional collaborative filtering (CF) methods only use the user-item rating matrix to make recommendations, which usually suffer from cold-start and sparsity problems. To address these problems, on the one hand, some CF methods are proposed to incorporate auxiliary information such as user/item profiles; on the other hand, deep neural networks, which have powerful ability in learning effective representations, have achieved great success in recommender systems. However, these neural network based recommendation methods rarely consider the uncertainty of weights in the network and only obtain point estimates of the weights. Therefore, they maybe lack of calibrated probabilistic predictions and make overly confident decisions. To this end, we propose a new Bayesian dual neural network framework, named BDNet, to incorporate auxiliary information for recommendation. Specifically, we design two neural networks, one is to learn a common low dimensional space for users and items from the rating matrix, and another one is to project the attributes of users and items into another shared latent space. After that, the outputs of these two neural networks are combined to produce the final prediction. Furthermore, we introduce the uncertainty to all weights which are represented by probability distributions in our neural networks to make calibrated probabilistic predictions. Extensive experiments on real-world data sets are conducted to demonstrate the superiority of our model over various kinds of competitors.     

Collaborative error-reflected models for cold-start recommender systems

Collaborative Filtering (CF), one of the most successful technologies among recommender systems, is a system assisting users to easily find useful information. One notable challenge in practical CF is the cold start problem, which can be divided into cold start items and cold start users. Traditional CF systems are typically unable to make good quality recommendations in the situation where users and items have few opinions. To address these issues, in this paper, we propose a unique method of building models derived from explicit ratings and we apply the models to CF recommender systems. The proposed method first predicts actual ratings and subsequently identifies prediction errors for each user. From this error information, pre-computed models, collectively called the error-reflected model, are built. We then apply the models to new predictions. Experimental results show that our approach obtains significant improvement in dealing with cold start problems, compared to existing work.     

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.     

Explaining the user experience of recommender systems

Research on recommender systems typically focuses on the accuracy of prediction algorithms. Because accuracy only partially constitutes the user experience of a recommender system, this paper proposes a framework that takes a user-centric approach to recommender system evaluation. The framework links objective system aspects to objective user behavior through a series of perceptual and evaluative constructs (called subjective system aspects and experience, respectively). Furthermore, it incorporates the influence of personal and situational characteristics on the user experience. This paper reviews how current literature maps to the framework and identifies several gaps in existing work. Consequently, the framework is validated with four field trials and two controlled experiments and analyzed using Structural Equation Modeling. The results of these studies show that subjective system aspects and experience variables are invaluable in explaining why and how the user experience of recommender systems comes about. In all studies we observe that perceptions of recommendation quality and/or variety are important mediators in predicting the effects of objective system aspects on the three components of user experience: process (e.g. perceived effort, difficulty), system (e.g. perceived system effectiveness) and outcome (e.g. choice satisfaction). Furthermore, we find that these subjective aspects have strong and sometimes interesting behavioral correlates (e.g. reduced browsing indicates higher system effectiveness). They also show several tradeoffs between system aspects and personal and situational characteristics (e.g. the amount of preference feedback users provide is a tradeoff between perceived system usefulness and privacy concerns). These results, as well as the validated framework itself, provide a platform for future research on the user-centric evaluation of recommender systems.     

Interactive recommender systems: A survey of the state of the art and future research challenges and opportunities

Recommender systems have been researched extensively over the past decades. Whereas several algorithms have been developed and deployed in various application domains, recent research efforts are increasingly oriented towards the user experience of recommender systems. This research goes beyond accuracy of recommendation algorithms and focuses on various human factors that affect acceptance of recommendations, such as user satisfaction, trust, transparency and sense of control. In this paper, we present an interactive visualization framework that combines recommendation with visualization techniques to support human-recommender interaction. Then, we analyze existing interactive recommender systems along the dimensions of our framework, including our work. Based on our survey results, we present future research challenges and opportunities.