Collaborative Filtering Systems Research Articles

Comparative Analysis of Functionality and Aspects for Hybrid Recommender Systems

Recommender systems are gradually becoming the backbone of profitable business which interact with users mainly on the web stack. These systems are privileged to have large amounts of user interaction data used to improve them. The systems utilize machine learning and data mining techniques to determine products and features to suggest different users correctly. This is an essential function since offering the right product at the right time might result in increased revenue. This paper gives focus on the importance of different kinds of hybrid recommenders. First, by explaining the various types of recommenders in use, then showing the need for hybrid systems and the multiple kinds before giving a comparative analysis of each of these. Keeping in mind that content-based, as well as collaborative filtering systems, are widely used, research is comparatively done with a keen interest on how this measures up to hybrid recommender systems.

APPLYING COLLABORATIVE FILTERING METHOD FOR DOCUMENT RECOMMENDER SYSTEM

The recommender system helps recommend relevant information items to the user. In recommender systems, collaborative filtering is commonly used to gauge users' interest in new products. Collaborative filtering systems often rely on data about the similarity of users or products in the system in the past to predict preferences or new products for specific users. In this article, we apply the collaborative filtering technique with the k-nearest neighbor to recommend documents for the English center. The implementation process includes the following steps: Firstly, we build a system to collect and store data in the database; Secondly, we implement a recommendation algorithm with three cases, including Case 1 for new users, Case 2 for users who have seen the most document items, and Case 3 for centers' members. The results make it easier for users to find documents.

Revisiting Item Promotion in GNN-Based Collaborative Filtering: A Masked Targeted Topological Attack Perspective

Graph neural networks (GNN) based collaborative filtering (CF) has attracted increasing attention in e-commerce and financial marketing platforms. However, there still lack efforts to evaluate the robustness of such CF systems in deployment. Fundamentally different from existing attacks, this work revisits the item promotion task and reformulates it from a targeted topological attack perspective for the first time. Specifically, we first develop a targeted attack formulation to maximally increase a target item's popularity. We then leverage gradient-based optimizations to find a solution. However, we observe the gradient estimates often appear noisy due to the discrete nature of a graph, which leads to a degradation of attack ability. To resolve noisy gradient effects, we then propose a masked attack objective that can remarkably enhance the topological attack ability. Furthermore, we design a computationally efficient approach to the proposed attack, thus making it feasible to evaluate large-large CF systems. Experiments on two real-world datasets show the effectiveness of our attack in analyzing the robustness of GNN-based CF more practically.

Lipstick color suggested using hybrid hidden Markov model

In today’s lifestyle, facial makeup plays an important role in enhancing visual attractiveness a nd boosting one’s self-esteem. Makeup is known as the second skin of the women, and that too lipstick is a soul of the makeup. According to a survey, an average urban woman spends almost one year and three months of her life just wearing makeup. This much of the time is due to decision-making and choosing the best makeup style that would fit a particular age, skin complexion, profession, and occasion, requiring high imagination and full art. Many makeup recommendations systems exist, but no solitary system has existed to recommend a lipstick color properly to solve this problem computationally. Therefore, as a tiny step towards helping women save their time in decision-making, the proposed model puts forward an idea of a hybrid recommendation model for lipsticks alone. This proposed methodology uses a hidden Markov model to unleash the possible color of the lipsticks based on the given attributes. The collaborative filtering system catalyzes the process to recommend the best lipstick colors using a hybrid recommendation model.

Simulating real profiles for shilling attacks: A generative approach

Collaborative Filtering (CF) approaches are vulnerable to Shilling Attacks, in which malicious users or companies inject a large number of fake profiles in a system in order to manipulate its recommendations. One problem of current Shilling Attack models is that they commonly use straightforward statistical templates, producing profiles with different rating patterns than actual system data, which facilitates its detection, requiring a larger amount of profiles to achieve its goals. To address this problem and create profiles closer to reality, we propose using a generative model, Variational Autoencoder (VAE) to map original data distribution. With VAE, it is possible to generate new profiles based on real data, without explicit copying their actual ratings. Its generated profiles are converted to malicious profiles by adding target item rating value. We test our attack model on MovieLens 100k data set and compare to literature attack models. Our results indicate that our model outperforms all other models in model-based CF system, especially using low attack sizes (from 3% to 5%). Also, analysis comparing profiles generated from it and other approaches shows that our model ratings pattern are very similar to real profiles, which may indicate that attacks mounted using our approach may be less likely to be detected by detection approaches. Thus, we show that our attack model represents an advance on Shilling Attack models, since its superior results in model-based CF and possible indistinction from real profiles may be useful as a baseline to test detection techniques and other tasks among Shilling Attack area.

Hybrid model for movie recommendation system using content K-nearest neighbors and restricted Boltzmann machine

<span>One of the most commonly used techniques in the recommendation framework is collaborative filtering (CF). It performs better with sufficient records of user rating but is not good in sparse data. Content-based filtering works well in the sparse dataset as it finds the similarity between movies by using attributes of the movies. RBM is an energy-based model serving as a backbone of deep learning and performs well in rating prediction. However, the rating prediction is not preferable by a single model. The hybrid model achieves better results by integrating the results of more than one model. This paper analyses the weighted hybrid CF system by integrating content K-nearest neighbors (KNN) with restricted Boltzmann machine (RBM). Movies are recommended to the active user in the proposed system by integrating the effects of both content-based and collaborative filtering. Model efficacy was tested with MovieLens benchmark datasets.</span>

CEBRA: A CasE-Based Reasoning Application to recommend banking products

Following data ethics and respecting the clients’ privacy, the banking environment can use the client data that is available to them to offer personalized services to its clients. Intelligent recommender systems can support this attempt through specialized technological architectures. This article proposes the inclusion of CEBRA (CasE-Based Reasoning Application), a case-based reasoning system oriented to commercial banking, in a Fog Computing architecture coordinated by virtual agents. Throughout this article, the model of this architecture is presented and its life cycle is described, and improvements are proposed through the incorporation of several techniques in the retrieve and reuse phases, including the extraction of interests expressed by users on their social network profiles and collaborative filtering systems. A comprehensive case study has been carried out and a dataset of 60,000 cases has been generated to evaluate CEBRA. As a result, the Recommender System is presented, by including, the recommendation algorithm and a REST interface for its use. The recommendations are based on the user’s profile, previous ratings and/or additional knowledge such as the user’s contextual information. The proposal takes advantage of contextual information to support the promotion of banking and financial products, improving user satisfaction.

Time-Aware CF and Temporal Association Rule-Based Personalized Hybrid Recommender System

Most recommender systems usually combine several recommendation methods to enhance the recommendation accuracy. Collaborative filtering (CF) is a best-known personalized recommendation technique. While temporal association rule-based recommendation algorithm can discover users' latent interests with time-specific leveraging historical behavior data without domain knowledge. The concept-drifting and user interest-drifting are two key problems affecting the recommendation performance. Aiming at the above problems, a time-aware CF and temporal association rule-based personalized hybrid recommender system, TP-HR, is proposed. The proposed time-aware CF algorithm considers evolving features of users' historical feedback. And time-aware users' similar neighbors selecting measure and time-aware item rating prediction function are proposed to keep track of the dynamics of users' preferences. The proposed temporal association rule-based recommendation algorithm considers the time context of users' historical behaviors when mining effective temporal association rules. Experimental results on real datasets show the feasibility and performance improvement of the proposed hybrid recommender system compared to other baseline approaches.

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

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 is of significant importance. The MkMeans + + algorithm is a technique for clustering and separating users in collaborative filtering systems. This algorithm utilizes a specific procedure for selecting the initial centroids of the clusters and has a better function compared with its similar algorithms such as kMeans + + . In this paper, MkMeans + + algorithm is combined with Firefly, Cuckoo, and Krill algorithms and new algorithms called FireflyMkMeans + + , CuckooMkMeans + + , and KrillMkMeans + + are introduced in order to specify the optimal centroid of the cluster, better separate users, and avoid local optimals. In the proposed hybrid clustering approach, the initial population of firefly, cuckoo, and krill algorithms is initialized through the solutions generated by MkMeans + + algorithm, and it makes use of the benefits of MkMeans + + as well as firefly, cuckoo, and krill algorithms. Results and implementations on both MovieLens and FilmTrust datasets indicate that the proposed algorithms can perform better than their similar algorithms in clustering and separating users with different tastes (graysheep users), and enhance the quality of clusters and the accuracy of recommendations for users with similar tastes (white users).

Contextual Information Retrieval within Recommender System: Case Study "E-learning System"

This paper focuses on monitoring and analyzing user activities on collaborative filtering -based recommender system in order to guess suitable and unsuitable items' context information using rating matrix which makes more efficient adaptation task. An ontology-based user profile and rules-based context modeling for reasoning about context information is proposed in this research work, in addition to an investigation to apply Semantic Web technologies in user modeling and context reasoning. This proposal is applied in education field in which we have designed an authoring tool for learning objects within ubiquitous environment. This system aims to improve the learning object production task (creation, review, edition…) on behalf of technologies offered by collaborative filtering systems as well as user behaviors monitoring to improve the recommendation process.

Exposing Private User Behaviors of Collaborative Filtering via Model Inversion Techniques

AbstractPrivacy risks of collaborative filtering (CF) have been widely studied. The current state-of-theart inference attack on user behaviors (e.g., ratings/purchases on sensitive items) for CF is by Calandrino et al. (S&P, 2011). They showed that if an adversary obtained a moderate amount of user’s public behavior before some timeT, she can infer user’s private behavioraftertimeT. However, the existence of an attack that infers user’s private behaviorbefore Tremains open. In this paper, we propose the first inference attack that reveals past private user behaviors. Our attack departs from previous techniques and is based onmodel inversion(MI). In particular, we propose the first MI attack on factorization-based CF systems by leveraging data poisoning by Li et al. (NIPS, 2016) in a novel way. We inject malicious users into the CF system so that adversarialy chosen “decoy” items are linked with user’s private behaviors. We also show how to weaken the assumption made by Li et al. on the information available to the adversary from the whole rating matrix to only the item profile and how to create malicious ratings effectively. We validate the effectiveness of our inference algorithm using two real-world datasets.

Autonomous Process Model Identification using Recurrent Neural Networks and Hyperparameter Optimization

We demonstrate the application of automated machine learning to the problem of identifying dynamic process models using recurrent neural networks (RNNs). The general concept relies on continuous monitoring of input-output data from a plant and the processing of this data by a collection of algorithms. The data is first processed by a collaborative filtering system, which suggests a classification of system dynamics per output channel. The proposed classification and the number of input channels is used to initialize a search over RNN hyperparameters. The search algorithm uses subsets of historical data for training and validation to select the RNN architecture and determine the network parameters according to preselected objectives for balancing model accuracy and model compactness. The proposed approach is demonstrated on a simulated case study for online system identification of a chemical reactor, where the underlying dynamic characteristics of the simulated system are changed during the simulation as the system undergoes a number of disturbances and handles control tasks. Process models for the system in question are obtained via the automated machine learning approach and the models are updated as the system dynamics change. The results show good prediction accuracy of the models throughout the simulation representing changes in system dynamics.

SCOL: similarity and credibility-based approach for opinion leaders detection in collaborative filtering-based recommender systems

Recommender systems (RSs) have recently gained significant attention from both research and industrial communities. These systems generate the recommendations of items in one of two ways, namely collaborative or content-based filtering. Collaborative filtering is a technique used by recommender systems in order to suggest to the user a set of items based on the opinions of other users who share with him the same preferences. One of the key issues in collaborative filtering systems (CFSs) is how to generate adequate recommendations for newcomers who rate only a small number of items, a problem known as cold start user. Another interesting problem is the cold start item when a new item is introduced in the system and cannot be recommended. In this paper, we present a clustering-based approach SCOL that aims to alleviate the cold start challenges; by identifying the most effective opinion leaders among the social network of the CFS. SCOL clustering focuses on the credibility and correlation similarity concepts.

SCOL: similarity and credibility-based approach for opinion leaders detection in collaborative filtering-based recommender systems

Recommender systems (RSs) have recently gained significant attention from both research and industrial communities. These systems generate the recommendations of items in one of two ways, namely collaborative or content-based filtering. Collaborative filtering is a technique used by recommender systems in order to suggest to the user a set of items based on the opinions of other users who share with him the same preferences. One of the key issues in collaborative filtering systems (CFSs) is how to generate adequate recommendations for newcomers who rate only a small number of items, a problem known as cold start user. Another interesting problem is the cold start item when a new item is introduced in the system and cannot be recommended. In this paper, we present a clustering-based approach SCOL that aims to alleviate the cold start challenges; by identifying the most effective opinion leaders among the social network of the CFS. SCOL clustering focuses on the credibility and correlation similarity concepts.

Multi-criteria collaborative filtering using rough sets theory

Recommender systems have recently become a significant part of e-commerce applications. Through the different types of recommender systems, collaborative filtering is the most popular and successful recommender system for providing recommendations. Recent studies have shown that using multi-criteria ratings helps the system to know the customers better. However, bringing multi aspects to collaborative filtering causes new challenges such as scalability and sparsity. Additionally, revealing the relation between criteria is yet another optimization problem. Hence, increasing the accuracy in prediction is a challenge. In this paper, an aggregation-function based multi-criteria collaborative filtering system using Rough Sets Theory is proposed as a novel approach. Rough Sets Theory is used to uncover the relationship between the overall criterion and the individual criteria. Experimental results show that the proposed model (RoughMCCF) successfully improves the predictive accuracy without compromising on online performance.

DNNRec: A novel deep learning based hybrid recommender system

We propose a novel deep learning hybrid recommender system to address the gaps in Collaborative Filtering systems and achieve the state-of-the-art predictive accuracy using deep learning. While collaborative filtering systems are popular with many state-of-the-art achievements in recommender systems, they suffer from the cold start problem, when there is no history about the users and items. Further, the latent factors learned by these methods are linear in nature. To address these gaps, we describe a novel hybrid recommender system using deep learning. The solution uses embeddings for representing users and items to learn non-linear latent factors. The solution alleviates the cold start problem by integrating side information about users and items into a very deep neural network. The proposed solution uses a decreasing learning rate in conjunction with increasing weight decay, the values cyclically varied across epochs to further improve accuracy. The proposed solution is benchmarked against existing methods on both predictive accuracy and running time. Predictive Accuracy is measured by Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) and R-squared. Running time is measured by the mean and standard deviation across seven runs. Comprehensive experiments are conducted on several datasets such as the MovieLens 100 K, FilmTrust, Book-Crossing and MovieLens 1 M. The results show that the proposed technique outperforms existing methods in both non-cold start and cold start cases. The proposed solution framework is generic from the outperformance on four different datasets and can be leveraged for other ratings prediction datasets in recommender systems.

Recommendation over time: a probabilistic model of time-aware recommender systems

In time-aware recommender systems, we have to consider the dynamic aspect of recommendation that is fond of new coming data. Usually, the recent data is more closely related to current recommendation tasks and the early data are useful to indicate overall measurements of the preferences. We propose a probabilistic model that uses the early data to generate the prior distribution and the recent data to capture the change of the states of both users and items in collaborative filtering systems. Our model is dynamic in the sense that it updates every time receiving new data. The time cost of every updating has a constant limit, which is suitable to deal with large scale data for online recommendation. Experiments on real datasets show the improvement performance of our model over the existing time-aware recommender systems.

Boosting Memory-Based Collaborative Filtering Using Content-Metadata

Recommendation systems are widely used in conjunction with many popular personalized services, which enables people to find not only content items they are currently interested in, but also those in which they might become interested. Many recommendation systems employ the memory-based collaborative filtering (CF) method, which has been generally accepted as one of consensus approaches. Despite the usefulness of the CF method for successful recommendation, several limitations remain, such as sparsity and cold-start problems that degrade the performance of CF systems in practice. To overcome these limitations, we propose a content-metadata-based approach that uses content-metadata in an effective way. By complementarily combining content-metadata with conventional user-content ratings and trust network information, our proposed approach remarkably increases the amount of suggested content and accurately recommends a large number of additional content items. Experimental results show a significant enhancement of performance, especially under a sparse rating environment.

Memory-based Collaborative Filtering: Impacting of Common Items on the Quality of Recommendation

In this study, the impact of the common items between a pair of users on the accuracy of memory-based collaborative filtering (CF) is investigated. Although CF systems are a widely used recommender system, data sparsity remains an issue. As a result, the similarity weight between a pair of users with few ratings is almost a fake relationship. In this work, the similarity weight of the traditional similarity methods is determined using exponential functions with various thresholds. These thresholds are used to specify the size of the common items amongst the users. Exponential functions can devalue the similarity weight between a pair of users who has few common items and increase the similarity weight for users who have sufficient co-rated items. Therefore, the pair of users with sufficient co-rated items obtains a stronger relationship than those with few common items. Thus, the significance of this paper is to succinctly test the impacting of common items on the quality of recommendation that creates an understanding for the researchers by discussing the findings presented in this study. The MovieLens datasets are used as benchmark datasets to measure the effect of the ratio of common items on the accuracy. The result verifies the considerable impact exerted by the factor of common items.

Impact of Clustering on quality of Recommendation in Cluster based Collaborative Filtering: an Empirical Study

In memory nearest neighbour computation is a typical approach for collaborative filtering (CF) due to its high recommendation accuracy. However, this approach fails on scalability; which is the declined performance of the same due to the rapid increase in the number of users and items in archetypal merchandising applications. One of the popular techniques to attenuate scalability issue is cluster-based collaborative filtering (CBCF), which uses clustering approach to group most similar users/items from complete dataset. In this work we present a detailed analysis of the impact of clustering in CF approach. Specifically, we study how the extent of clustering impacts collaborative filtering systems in terms of quality of predictions, quality of recommendations, throughput and coverage. Based on the empirical results obtained from two datasets, Movielens100K and Jester; we conclude that with increasing number of clusters the quality of predictions, the quality of recommendations and the throughput are enhanced but the coverage provided by clustered subsystems declines.