Robustness analysis of arbitrarily distributed data-based recommendation methods

Due to different shopping routines of people, rating preferences of many customers might be partitioned between two parties. Since two different e-companies might sell products from the same range to the identical set of customers, the type of data partition is called arbitrarily. In the case of arbitrarily distributed data, it is a challenge to produce accurate recommendations for those customers, because their ratings are split. Therefore, researchers propose methods for enabling data holders’ collaboration. In this scenario, privacy becomes a deterrent barrier for collaboration, accordingly, the introduced solutions include private protocols for protecting parties’ confidentiality. Although, private protocols encourage data owners to collaborate, they introduce a new drawback for partnership. Since, whole data is distributed and parties do not have full control of data, any malicious user, who knows that two parties collaborate, can easily insert shilling profiles to system by partitioning them between data holders. Parties can have trouble to find such profile injection attacks by employing existing detection methods because of they are arbitrarily distributed. Since profile injection attacks can easily performed on arbitrarily distributed data-based recommender systems, quality, and reliability of such systems decreases, and it causes angry customers. Therefore, in this paper, we try to describe aforementioned problems with arbitrarily distributed data-based recommender systems. As a first step, we analyze robustness of proposed arbitrarily distributed data-based recommendation methods against six well-known shilling attack types. Secondly, we explain why existing detection methods cannot detect malicious user profiles in distributed data. We perform experiments on a well-known movie data set, and according to our results, arbitrarily distributed data-based recommendation methods are vulnerable to shilling attacks.     

e‐Learning recommender system for a group of learners based on the unified learner profile approach

In the age of information explosion, e‐learning recommender systems (eL_RSs) have emerged as effective information filtering techniques that attempt to provide the most appropriate learning resources for learners while using e‐learning systems. These learners are differentiated on the basis of their learning styles, goals, knowledge levels and others. Several attempts have been made in the past to design eL_RSs to recommend resources to individuals; however, an investigation of recommendations to a group of learners in e‐learning is still in its infancy. In this paper, we focus on the problem of recommending resources to a group of learners rather than to an individual. The major challenge in group recommendation is how to merge the individual preferences of different learners that form a group and extract a pseudo unified learner profile (ULP) that closely reflects the preferences of all learners. Firstly, we propose a profile merging scheme for the ULP by utilizing learning styles, knowledge levels and ratings of learners in a group. Thereafter, a collaborative approach is proposed based on the ULP for effective group recommendations. Experimental results are presented to demonstrate the effectiveness of the proposed group recommendation strategy for e‐learning.     

Expert Recommendations Based on Opinion Mining of User‐Generated Product Reviews

In this article, we introduce the idea of expert recommendations whose objective is to relate review comments with users’ tasks or expectations. We propose to use fine‐grained information such as opinions and suggestions extracted using natural language processing techniques from user reviews about products, to improve a recommendation system. While typical recommender systems compare a user profile with some reference characteristics to rate unseen items, they rarely make use of the content of reviews that users have provided on a given product. In this article, we present the application of an opinion extraction system to extract opinions and suggestions from the content of the reviews, the use of the results to compare other products with the reviewed one, and eventually the recommendation of better products to the user. The recommendations are given a confidence weight by using a trust social network.     

Developing recommender systems with the consideration of product profitability for sellers

In electronic commerce web sites, recommender systems are popularly being employed to help customers in selecting suitable products to meet their personal needs. These systems learn about user preferences over time and automatically suggest products that fit the learned model of user preferences. Traditionally, recommendations are provided to customers depending on purchase probability and customers’ preferences, without considering the profitability factor for sellers. This study attempts to integrate the profitability factor into the traditional recommender systems. Based on this consideration, we propose two profitability-based recommender systems called CPPRS (Convenience plus Profitability Perspective Recommender System) and HPRS (Hybrid Perspective Recommender System). Moreover, comparisons between our proposed systems (considering both purchase probability and profitability) and traditional systems (emphasizing an individual’s preference) are made to clarify the advantages and disadvantages of these systems in terms of recommendation accuracy and/or profit from cross-selling. The experimental results show that the proposed HPRS can increase profit from cross-selling without losing recommendation accuracy.     

A testbed for performance evaluation of load‐balancing strategies for Web server systems

To improve response time of a Web site, one replicates the site on multiple servers. The effectiveness of a replicated server system will depend on how the incoming requests are distributed among replicas. A large number of load‐balancing strategies for Web server systems have been proposed. In this paper we describe a testbed that can be used to evaluate the performance of different load‐balancing strategies. The testbed uses a general architecture which allows different load‐balancing approaches to be supported easily. It emulates a typical World Wide Web scenario and allows variable load generation and performance measurement. We have performed some preliminary experiments to measure the performance of a few policies for load balancing using this testbed. Copyright © 2003 John Wiley & Sons, Ltd.     

In‐memory distributed software solution to improve the performance of recommender systems

Many recommender systems are currently available for proposing content (movies, TV series, music, etc.) to users according to different profiling metrics, such as ratings of previously consumed items and ratings of people with similar tastes. Recommendation algorithms are typically executed by powerful servers, as they are computationally expensive. In this paper, we propose a new software solution to improve the performance of recommender systems. Its implementation relies heavily on Apache Spark technology to speed up the computation of recommendation algorithms. It also includes a webserver, an API REST, and a content cache. To prove that our solution is valid and adequate, we have developed a movie recommender system based on two methods, both tested on the freely available Movielens and Netflix datasets. Performance was assessed by calculating root‐mean‐square error values and the times needed to produce a recommendation. We also provide quantitative measures of the speed improvement of the recommendation algorithms when the implementation is supported by a computing cluster. The contribution of this paper lies in the fact that our solution, which improves the performance of competitor recommender systems, is the first proposal combining a webserver, an API REST, a content cache and Apache Spark technology. Copyright © 2016 John Wiley & Sons, Ltd.     

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.     

A fuzzy model for managing natural noise in recommender systems

E-commerce customers demand quick and easy access to products in large search spaces according to their needs and preferences. To support and facilitate this process, recommender systems (RS) based on user preferences have recently played a key role. However the elicitation of customers preferences is not always precise either correct, because of external factors such as human errors, uncertainty and vagueness proper of human beings and so on. Such a problem in RS is known as natural noise and can bias customers recommendations. Despite different proposals have been presented to deal with natural noise in RS none of them is able to manage properly the inherent uncertainty and vagueness of customers preferences. Hence, this paper is devoted to a new fuzzy method for managing in a flexible and adaptable way such uncertainty of natural noise in order to improve recommendation accuracy. Eventually a case study is performed to show the improvements produced by this fuzzy method regarding previous proposals.     

Private personalized social recommendations in an IPTV system

In our connected world, recommender systems have become widely known for their ability to provide expert and personalize referrals to end-users in different domains. The rapid growth of social networks and new kinds of systems so called “social recommender systems” are rising, where recommender systems can be utilized to find a suitable content according to end-users' personal preferences. However, preserving end-users' privacy in social recommender systems is a very challenging problem that might prevent end-users from releasing their own data, which detains the accuracy of extracted referrals. In order to gain accurate referrals, social recommender systems should have the ability to preserve the privacy of end-users registered in this system. In this paper, we present a middleware that runs on end-users' Set-top boxes to conceal their profile data when released for generating referrals, such that computation of recommendation proceeds over the concealed data. The proposed middleware is equipped with two concealment protocols to give users a complete control on the privacy level of their profiles. We present an IPTV network scenario and perform a number of different experiments to test the efficiency and accuracy of our protocols. As supported by the experiments, our protocols maintain the recommendations accuracy with acceptable privacy level.     

Progress in context-aware recommender systems — An overview

Recommender Systems are the set of tools and techniques to provide useful recommendations and suggestions to the users to help them in the decision-making process for choosing the right products or services. The recommender systems tailored to leverage contextual information (such as location, time, companion or such) in the recommendation process are called context-aware recommender systems. This paper presents a review on the continual development of context-aware recommender systems by analyzing different kinds of contexts without limiting to any specific application domain. First, an in-depth analysis is conducted on different recommendation algorithms used in context-aware recommender systems. Then this information is used to find out that how these techniques deals with the curse of dimensionality, which is an inherent issue in such systems. Since contexts are primarily based on users’ activity patterns that leads to the development of personalized recommendation services for the users. Thus, this paper also presents a review on how this contextual information is represented (either explicitly or implicitly) in the recommendation process. We also presented a list of datasets and evaluation metrics used in the setting of CARS. We tried to highlight that how algorithmic approaches used in CARS differ from those of conventional RS. In that, we presented what modification or additions are being applied on the top of conventional recommendation approaches to produce context-aware recommendations. Finally, the outstanding challenges and research opportunities are presented in front of the research community for analysis     

User evaluation of a market-based recommender system

Recommender systems have been developed for a wide variety of applications (ranging from books, to holidays, to web pages). These systems have used a number of different approaches, since no one technique is best for all users in all situations. Given this, we believe that to be effective, systems should incorporate a wide variety of such techniques and then some form of overarching framework should be put in place to coordinate them so that only the best recommendations (from whatever source) are presented to the user. To this end, in our previous work, we detailed a market-based approach in which various recommender agents competed with one another to present their recommendations to the user. We showed through theoretical analysis and empirical evaluation with simulated users that an appropriately designed marketplace should be able to provide effective coordination. Building on this, we now report on the development of this multi-agent system and its evaluation with real users. Specifically, we show that our system is capable of consistently giving high quality recommendations, that the best recommendations that could be put forward are actually put forward, and that the combination of recommenders performs better than any constituent recommender.     

User‐centred design and educational data mining support during the recommendations elicitation process in social online learning environments

Social online learning environments provide new recommendation opportunities to meet users' needs. However, current educational recommender systems do not usually take advantage of these opportunities. To progress on this issue, we have proposed a knowledge engineering approach based on human–computer interaction (i.e. user‐centred design as defined by the standard ISO 9241‐210:2010) and artificial intelligence techniques (i.e. data mining) that involve educators in the process of eliciting educational oriented recommendations. To date, this approach differs from most recommenders in education in focusing on identifying relevant actions to be recommended on e‐learning services from a user‐centric perspective, thus widening the range of recommendation types. This approach has been used to identify 32 recommendations that consider several types of actions, which focus on promoting active participation of learners and on strengthening the sharing of experiences among peers through the usage of the social services provided by the learning environment. The paper describes where data mining techniques have been applied to complement the user‐centred design methods to produce social oriented recommendations in online learning environments.     

基于矩阵聚类的电子商务网站个性化推荐系统

提出一种基于“矩阵聚类”的电子商务网站个性化推荐系统,通过分析Web server日志文件中的访问页面序列行为数据,构建较高购买者的顾客行为的矩阵模型;并使用一种新型的“矩阵聚类”算法挖掘潜在购买者与较高购买者的相似特征,从而帮助顾客发现他所希望购买的产品信息,用于提高实际购买量．该技术特别适合于目前大型的电子商务网站,实验数据表明,该系统是高效并可广泛使用．     

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.     

Proposing improved meta-heuristic algorithms for clustering and separating users in the recommender systems

Electronic Commerce Research - To offer an appropriate recommendation to customers in recommender systems, the issue of clustering and separating users with different tastes from the rest of people...     

EFFICIENT PERSONALIZATION OF E‐LEARNING ACTIVITIES USING A MULTI‐DEVICE DECENTRALIZED RECOMMENDER SYSTEM

Personalization is becoming a key issue in designing effective e‐learning systems and, in this context, a promising solution is represented by software agents. Usually, these systems provide the student with a student agent that interacts with a site agent associated with each e‐learning site. However, in presence of a large number of students and of e‐learning sites, the tasks of the agents are often onerous, even more if the student agents run on devices with limited resources. To face this problem, we propose a new multiagent learning system, called ISABEL. Our system provides each student, that are using a specific device, with a device agent able to autonomously monitor the student's behavior when accessing e‐learning Web sites. Each site is associated, in its turn, with a teacher agent. When a student visits an e‐learning site, the teacher agent collaborates with some tutor agents associated with the student, to provide him with useful recommendations. We present both theoretical and experimental results to show that this distributed approach introduces significant advantages in quality and efficiency of the recommendation activity with respect to the performances of other past recommenders.     

基于相似模式聚类的电子商务网站个性化推荐系统研究

保证个性化推荐系统产生高质量的推荐结果的重要因素是:系统必须要确定访问者在访问行为的相似程度,从而能预测访问者的访问和购买兴趣。实现此功能的关键技术是计算访问者对象在整个或者部分属性空间的相似距离,从而得到访问行为的相似程度。该文首先分析了目前在推荐系统中常用的用于计算访问行为相似程度的距离函数,发现它们是测定访问者对象在所有测试属性空间上的平均测定,而在属性集的子维空间上的相似模式并没有有效地挖掘出来。然后提出一种新的基于相似模式聚类算法的电子商务个性化推荐系统,综合考虑可供挖掘的数据源(如:网站内容,网站的超链接结构,顾客访问网站的行为,以及商业的实际购买情况,顾客的身份数据等)获取用户访问电子商务网站的访问页面序列,构建较高购买者的顾客行为的矩阵模型,高效地得到访问者对象在整个或者部分属性空间的相似访问行为,然后通过挖掘潜在购买者与较高购买者的相似模式特征,帮助顾客发现他所希望购买的产品信息,用于提高实际购买量,实验数据表明,该系统高效并可广泛使用。     

A Deep Learning Based Approach for Context-Aware Multi-Criteria Recommender Systems

Recommender systems are similar to an information filtering system that helps identify items that best satisfy the users’ demands based on their preference profiles. Context-aware recommender systems (CARSs) and multi-criteria recommender systems (MCRSs) are extensions of traditional recommender systems. CARSs have integrated additional contextual information such as time, place, and so on for providing better recommendations. However, the majority of CARSs use ratings as a unique criterion for building communities. Meanwhile, MCRSs utilize user preferences in multiple criteria to better generate recommendations. Up to now, how to exploit context in MCRSs is still an open issue. This paper proposes a novel approach, which relies on deep learning for context-aware multi-criteria recommender systems. We apply deep neural network (DNN) models to predict the context-aware multi-criteria ratings and learn the aggregation function. We conduct experiments to evaluate the effect of this approach on the real-world dataset. A significant result is that our method outperforms other state-of-the-art methods for recommendation effectiveness.     

音乐推荐系统及相关技术研究

随着计算机网络和多媒体技术的迅速普及,推荐系统特别是音乐推荐系统成为了电子商务领域的一大研究热点.对现有的音乐推荐系统及其相关技术作了全面深入的调查和分析,在介绍个人及群体音乐推荐系统的基础上,讨论了音乐推荐系统的发展方向并提出了相应的研究重点.该课题的研究有助于提高音乐推荐质量,增强用户满意度,提高音乐推荐系统的实际可用性.相关研究成果也将对其他推荐系统以及多媒体应用系统的研究起到重要的借鉴作用.     

Distributed Adaptive Event‐Triggered Control for Leader‐Following Consensus of Multi‐Agent Systems

This paper studies the leader‐following consensus problem for Lipschitz nonlinear multi‐agent systems using novel event‐triggered controllers. A distributed adaptive law is introduced for the event‐based control strategy design such that the proposed controllers are independent of system parameters and only use the relative states of neighboring agents, and hence are fully distributed. Due to the introduction of an event‐triggered control scheme, the controller of the agent is only triggered at it's own event times, and thus reduces the amount of communication between controller and actuator and lowers the frequency of controller updates in practice. Based on a quadratic Lyapunov function, the event condition which uses only neighbor information and local computation at trigger instants is established. Infinite triggers within a finite time are also verified to be impossible. The effectiveness of the theoretical results are illustrated through simulation examples.