Collaborative Recommender Systems Research Articles

Multi‐model deep learning approach for collaborative filtering recommendation system

As a result of a huge volume of implicit feedback such as browsing and clicks, many researchers are involving in designing recommender systems (RSs) based on implicit feedback. Though implicit feedback is too challenging, it is highly applicable to use in building recommendation systems. Conventional collaborative filtering techniques such as matrix decomposition, which consider user preferences as a linear combination of user and item latent features, have limited learning capacities, hence suffer from a cold start and data sparsity problems. To tackle these problems, the research direction towards considering the integration of conventional collaborative filtering with deep neural networks to maps user and item features. Conversely, the scalability and the sparsity of the data affect the performance of the methods and limit the worthiness of the results of the recommendations. Therefore, the authors proposed a multi-model deep learning (MMDL) approach by integrating user and item functions to construct a hybrid RS and significant improvement. The MMDL approach combines deep autoencoder with a one-dimensional convolution neural network model that learns user and item features to predict user preferences. From detail experimentation on two real-world datasets, the proposed work exhibits substantial performance when compared to the existing methods.

Novel predictive model to improve the accuracy of collaborative filtering recommender systems

The recommendation problem involves the prediction of a set of items that maximize the utility for users. Numerous factors, such as the filtering method and similarity measure, affect the prediction accuracy. We propose a novel prediction mechanism that can be applied to collaborative filtering recommender systems. This prediction mechanism consists of a novel adaptable predictive model, called inheritance-based prediction (INH-BP), and a suitable heuristic search algorithm. INH-BP enables the customization of the predictor to suit the user context. It helps in defining a user interest print (UIP) matrix and employs an optimization algorithm such as a genetic algorithm. The UIP matrix should reflect the degree of user satisfaction based on the concept levels instead of the instance level. The optimization algorithm is used to determine the optimal predictor for each user. A set of experiments were conducted to compare INH-BP with Resnick’s well-known adjusted weighted sum. Two benchmark datasets, MovieLens-100K and MovieLens-Last, were used. Both prediction methods were employed using different collaborative filtering techniques. The results demonstrate the superiority of INH-BP and its capability to achieve an accurate prediction irrespective of the number of k-neighbors and their quality. In addition, the results show that INH-BP alleviates the cold start and sparsity issues.

Catering for unique tastes: Targeting grey-sheep users recommender systems through one-class machine learning

In recommendation systems, the grey-sheep problem refers to users with unique preferences and tastes that make it difficult to develop accurate profiles. That is, the similarity search approach typically followed during the recommendation process fails to yield good results. Most research does not focus on such users and thus fails to cater to more exotic tastes and emerging trends, leading to a subsequent loss in revenue and marketing opportunities. One suggested solution is to use one-class classification to generate a prediction list for these users, where decision boundaries are learned that distinguish between normal and grey-sheep users. In this paper, we present the grey-sheep one-class recommendation (GSOR) framework designed to create accurate prediction models while taking both regular and grey-sheep users into account. In addition, we introduce a novel grey-sheep movie recommendation benchmark to be used by current and future researchers. When evaluating our GSOR framework against this benchmark, our results indicate the value of combining cluster analysis, outlier detection, and one-class learning to generate relevant and timely recommendation lists from data sets that contain grey-sheep users. Specifically, by employing one-class decision tree algorithms, our GSOR framework was able to outperform traditional collaborative filtering-based recommendation systems in both accuracy and model construction time. Furthermore, we report that having grey-sheep users in the system often had a positive impact on the learning and recommendation processes.

A survey of attack detection approaches in collaborative filtering recommender systems

Nowadays, due to the increasing amount of data, the use of recommender systems has increased. Therefore, the quality of the recommendations for the users of these systems is very important. One of the recommender systems models is collaborative filtering (CF) which uses the ratings given by the users to the items. But many of these ratings may be noisy or inaccurate so they reduce the quality of the recommendations. Sometimes users, using fake profiles, try to change the recommendations in their favor. Since satisfaction and trust in such systems are very important and useful, it would be better to find a way to identify these types of users. Despite numerous studies on CF recommender systems, the design of a robust recommender system is still a challenging problem. In this paper, we have analyzed the 25 previous samples of research on collaborative filtering recommender system (CFRS) for attack detection from 2009 to 2019. Most of these papers focus mainly on movie recommendations. According to these analyzes, we have categorized attack detection methods on CFRS in four categories: clustering, classifying, feature extraction and probabilistic approaches. The evaluation measures, the dataset, and attacks features used in the attack detection approaches are discussed.

Exploiting the User Social Context to Address Neighborhood Bias in Collaborative Filtering Music Recommender Systems

Recent research in the field of recommender systems focuses on the incorporation of social information into collaborative filtering methods to improve the reliability of recommendations. Social networks enclose valuable data regarding user behavior and connections that can be exploited in this area to infer knowledge about user preferences and social influence. The fact that streaming music platforms have some social functionalities also allows this type of information to be used for music recommendation. In this work, we take advantage of the friendship structure to address a type of recommendation bias derived from the way collaborative filtering methods compute the neighborhood. These methods restrict the rating predictions for a user to the items that have been rated by their nearest neighbors while leaving out other items that might be of his/her interest. This problem is different from the popularity bias caused by the power-law distribution of the item rating frequency (long-tail), well-known in the music domain, although both shortcomings can be related. Our proposal is based on extending and diversifying the neighborhood by capturing trust and homophily effects between users through social structure metrics. The results show an increase in potentially recommendable items while reducing recommendation error rates.

“SeoulHouse2Vec”: An Embedding-Based Collaborative Filtering Housing Recommender System for Analyzing Housing Preference

Housing preference is the subjective and relative preference of users toward housing alternatives and studies in the field have been conducted to analyze the housing preferences of groups with sharing the same socio-demographic attributes. However, previous studies may not suggest the preference of individuals. In this regard, this study proposes “SeoulHouse2Vec,” an embedding-based collaborative filtering housing recommendation system for analyzing atypical and nonlinear housing preference of individuals. The model maps users and items in each dense vector space which are called embedding layers. This model may reflect trade-offs between the alternatives and recommend unexpected housing items and thus improve rational housing decision-making. The model expanded the search scope of housing alternatives to the entire city of Seoul utilizing public big data and GIS data. The preferences derived from the results can be used by suppliers, individual investors, and policymakers. Especially for architects, the architectural planning and design process will reflect users’ perspective and preferences, and provide quantitative data in the housing decision-making process for urban planning and administrative units.

A Hybrid Knowledge-Based and Collaborative Filtering Recommender System Model for Recommending Interventions to Improve Elderly Wellbeing

A Hybrid Knowledge-Based and Collaborative Filtering Recommender System Model for Recommending Interventions to Improve Elderly Wellbeing

Job matcher: A web application job placement using collaborative filtering recommender system

Job matcher: A web application job placement using collaborative filtering recommender system

Diversified service recommendation with high accuracy and efficiency

Collaborative filtering-based recommender systems are regarded as an important tool to predict the items that users will appreciate based on the historical usage of users. However, traditional recommendation solutions often pay more attentions to the accuracy of the recommended items while neglect the diversity of the final recommended list, which may produce partial redundant items in the recommended list and as a result, decrease the satisfaction degree of users. Moreover, historical usage data for recommendation decision-makingoften update frequently, which may lead to low recommendation efficiency as well as scalability especially in the big data environment. Considering these drawbacks, a novel method called DivRec_LSH is proposed in this paper to achieve diversified and efficient recommendations, which is based on the historical usage records and the Locality-Sensitive Hashing (LSH) technique. Finally, we compare our method with existing methods on the MovieLens dataset. Experiment results indicate that our proposal is feasible in addressing the triple dilemmas of recommender systems simultaneously, i.e., high efficiency, accuracy and diversity.

An item based collaborative filtering recommender system

In the present computerized world where there is an interminable assortment of substance to be devoured like books, recordings, articles, motion pictures, and so on., finding the substance of one's preferring has become an annoying errand. Then again, computerized content suppliers need to connect with whatever number clients on their administration as could be expected under the circumstances for the most extreme time. This is where the recommendation framework comes into the picture, as suppliers refer to material to clients as indicated by client preference. In this paper, we have proposed a film recommender framework Movie Mender. The target of Movie Mender is to give precise film suggestions to clients. As a rule, the essential recommender frameworks think about one of the accompanying variables for producing suggestions; the inclination of client (for example content-based sifting) or the inclination of comparable clients (for example cooperative sifting). To fabricate a steady and exact recommender framework a half and half of substance based separating just as community sifting will be utilized.

Bearing fault identification based on ASMOTE-CFR

Aiming at the problem of data unbalance caused by the lack of bearing failure test data, the paper proposes a collaborative filtering recommendation (CFR) method for adaptive Smote (ASMOTE) resampling and matrix decomposition of minority samples (ASMOTE-CFR). The method first adopts adaptive Smote method to synthesize different number of new sample equalization test data sets according to the data distribution. and then a variety of typical feature values such as time domain, frequency domain, time frequency domain, etc. are extracted to obtain the bearing feature matrix, and then a scoring matrix that accurately describes the bearing state is designed and based on the matrix Based on the decomposed collaborative filtering algorithm, a set of collaborative filtering recommendation system for bearing state recognition is proposed. Using this method, different forms of fault data on the outer ring of the rolling bearing were identified and verified. The accuracy of identification reached more than 98 %. Compared with the recognition accuracy of the collaborative filtering recommendation algorithm, this method improved 8 %.

Recommender Systems Based on Collaborative Filtering Using Review Texts—A Survey

In e-commerce websites and related micro-blogs, users supply online reviews expressing their preferences regarding various items. Such reviews are typically in the textual comments form, and account for a valuable information source about user interests. Recently, several works have used review texts and their related rich information like review words, review topics and review sentiments, for improving the rating-based collaborative filtering recommender systems. These works vary from one another on how they exploit the review texts for deriving user interests. This paper provides a detailed survey of recent works that integrate review texts and also discusses how these review texts are exploited for addressing some main issues of standard collaborative filtering algorithms.

A collaborative filtering recommender system using genetic algorithm

This paper presents a novel genetic-based recommender system (BLIGA) that depends on the semantic information and historical rating data. The main contribution of this research lies in evaluating the possible recommendation lists instead of evaluating items then forming the recommendation list. BLIGA utilizes the genetic algorithm to find the best list of items to the active user. Thus, each individual represents a candidate recommendation list. BLIGA hierarchically evaluates the individuals using three fitness functions. The first function uses semantic information about items to estimates the strength of the semantic similarity between items. The second function estimates the similarity in satisfaction level between users. The third function depends on the predicted ratings to select the best recommendation list.BLIGA results have been compared against recommendation results from alternative collaborative filtering methods. The results demonstrate the superiority of BLIGA and its capability to achieve more accurate predictions than the alternative methods regardless of the number of K-neighbors.

Collaborative Recommendation System in Users of Anime Films

The recommendation system is one method to know the preference consumer by showing the potential object. This recommendation also helps the consumer gets the preference object. One of the popular objects in the recommendation is anime film. In this case, we conduct research to recommend anime films based on ratings of previously watched films. Collaborative filtering is a technique that consists of calculating similarities, predictions, and recommendations. This study is taken from dataset Kaggle which consists of 73,516 users and 12,294 anime. A user’s history will be matched with the whole user’s history with alternating least squares (ALS) method. The anime will be recommended based on that results. This method is expected to help millions of users find the desired anime.

A distributed collaborative trust service recommender system for secure cloud computing

AbstractA model for providing solutions to the security issue of the cloud computing environment is addressed in this article by proposing a distributed collaborative trust service recommender (DTSR) system. DTSRs are kept in a distributed manner spread over the clouds, and they are used to extract raw trust from different sources. This trust information is based on the feedback by cloud service user's observation about the adherence of a cloud service provider (CSP) to a service level agreement for the cloud‐based service provided. Using this trust data, the overall trust of CSPs is computed by using collaborative computation. The trust values are propagated among the distributed DTSRs in the network so that the trust values are available to everyone in the cloud environment. Experiments were conducted, which clearly shows that our proposed system is useful in providing a secure multicloud environment.

User-item content awareness in matrix factorization based collaborative recommender systems

User-item content awareness in matrix factorization based collaborative recommender systems

Electricity plan recommender system with electrical instruction-based recovery

Several electricity tariffs have emerged for Demand Side Management (DSM) and residential customers are faced with challenges to choose the plan satisfying their personal needs. Electricity Plan Recommender System (EPRS) can alleviate the problem. This paper proposes a novel EPRS model named EPRS with Electrical Instruction-based Recovery (EPRS-EI), which is a dual-stage model consisting of feature formulation stage and recommender stage. In the feature formulation stage, matrix recovery with electrical instructions is applied to recover appliance usages, and the recovered data is set as features representing customers’ living patterns. In the recommender stage, Collaborative Filtering Recommender System (CFRS) based on K-Nearest Neighbors (KNN) and adjusted similarity is applied to recommend personal electricity plans to customers based on the above features. Different from other EPRS models, EPRS-EI is the first model utilizing matrix recovery methods and similarity computation with electrical instructions. With these electrical instructions, the proposed model is able to utilize more explicit features and recommend more personalized plans. We then apply EPRS-EI to predict the testing customers’ preference for electricity plans. Simulation results on recovering electricity data and their applications in EPRS confirm the effectiveness of the proposed methods in comparison to state-of-the-art methods, with 93.56%–94.85% customers correctly recommended.

Graph embedding-based approach for detecting group shilling attacks in collaborative recommender systems

Over the past decade, many approaches have been presented to detect shilling attacks in collaborative recommender systems. However, these approaches focus mainly on detecting individual attackers and rarely consider the collusive shilling behaviors among attackers, i.e., a group of attackers working together to bias the output of collaborative recommender systems by injecting fake profiles. Such shilling behaviors are generally termed group shilling attacks, which are more harmful to collaborative recommender systems than traditional shilling attacks. In this paper, we propose a graph embedding-based method to detect group shilling attacks in collaborative recommender systems. First, we construct a user relationship graph by analyzing the user rating behaviors and use a graph embedding method to obtain the low-dimensional vector representation of each node in the user relationship graph. Second, we employ the k-means++ clustering algorithm to obtain candidate groups based on the generated user feature vectors. Finally, we calculate the suspicious degree of each candidate group according to the attack group detection indicators and use the Ward’s hierarchical clustering method to cluster the candidate groups according to their suspicious degrees and obtain the attack groups. The experimental results on the Amazon and Netflix datasets show that the proposed method outperforms the baseline methods in detection performance.

Online decision aids: the role of decision-making styles and decision-making stages

PurposeDecision aids (DAs) in online retail stores ease consumers' information processing. However, online consumers do not use all decision aids in purchase decision-making. While the literature has documented the effects of individual decision aids or two decision aids at a time, no study has compared the efficacy of multiple decision aids simultaneously. Also, very few studies have looked at the use of decision aids for consumers with maximizing and satisficing tendencies. Hence, this study aims to understand the preferences of maximizers and satisficers towards online decision aids during the choice-making process.Design/methodology/approachThis is an observational study with 60 individuals who were asked to purchase either a search-based or an experience-based product online. Participants' browsing actions and verbalizations during online shopping, were recorded and analysed using NVivo, and later the use of decision aids was mapped along their choice process.FindingsConsumer's preference of decision aids varies across the two stages of the choice process (that is, consideration set formation and evaluation & choice). In their choice formation, maximizers use different decision aids in both stages, that is, filter tool and in-website search tool for search products, and collaborative filtering-based recommender systems and eWOM for experience products. Satisficers used more decision aids as compared to maximizers across the two stages for both product types.Originality/valueThis study is an exploratory attempt to understand how consumers use multiple decision aids present on e-commerce websites.

New contextual collaborative filtering system with application to personalized healthy nutrition education

Nowadays, the Internet is becoming a platform of choice where the number of users and items grows dramatically making recommender systems (RS) the most required and widespread technology. This paper deals with context aware collaborative RS and presents a double contribution that consists of a two Dimensions Contextual Collaborative Recommender System (2DCCRS) and a related application. Our first contribution proposes a new framework for collaborative context aware RS that relies on two key ideas. The first one suggests splitting the context into two parts namely internal and external contexts in order to deal with both internal and external context attributes in different and more appropriate manners. This allows addressing the complexity of the context model in a more effective way. In the second idea, we introduce two concepts; namely the “Stakeholders” and “Aggregation” to effectively alleviate the problems of new user and new item. 2DCCRS is based on a multi-layer architecture. Its highest layer relies on a pre-filtering algorithm that deals with the cold start system problem, and is mainly based on the similarity between the user profile and the items features. The middle layer is based on a collaborative filtering algorithm that takes into account the users’ preferences, interests and priorities; while the deepest layer, which is considered the most relevant in our multilayer architecture, focuses on a post-filtering algorithm in which the recommendations are much more adapted to the user environment. In Our second contribution, we present a case study of 2DCCRS in order to demonstrate the usefulness and effectiveness of the proposed approach. Indeed, we propose a personalized Healthy and Tasty application (H&T) that generates items based on 2DCCRS framework to guide the user toward the healthy and tasty meals that best meet his needs. The obtained results are very promising and show the effectiveness of our proposal.