Existing Recommender Systems Research Articles

User-Review Oriented Social Recommender System for Event Planning

Recommender system is used to suggest product or topic based on user’s interest. Existing recommender system have focused on books, product, music etc. The problem in existing recommender system is that wedding/event based suggestions are not available. In the modern information era; storage, communication has been a challenge due to information veracity, volume, and velocity. Due to the constant and exponential growth of information, the utilization of information for context-oriented services is not productive. In this paper, a wedding planner recommender system framework has been proposed based on hybrid approach i.e., content based, collaborative filtering technique. The motive of proposed framework is to generate user-specific recommendations for different tasks related to the event specially wedding event, analyzed from the user comments on his social networking portal. Its main objective is to assist the user for organizing the events by suggesting specific vendors needed to arrange the event activities. Also, it would enhance the sales of location sensitive products in social commerce. The trial study conducted using a set of Facebook users is carried out to validate the proposed recommendation system framework. The success of the proposed framework is reported in terms of the level of user satisfaction achieved.

Deep matrix factorization based on self-attention mechanism for student grade prediction

Deep learning is gradually emerging in the field of educational data mining. Aiming at student grade prediction in education data mining, a prediction model combining self-attention mechanism and deep matrix factorization (ADMFN) is proposed. It can quickly extract important features of sparse data and process complex nonlinear data. Firstly, the student and course vector corresponding to the score matrix are input into the model and projected to obtain the potential feature vector of the student (course). Then, the potential feature vectors of students (courses) are added into the self-attention mechanism to construct a multi-layer perceptron network. Finally, by constructing a bilinear pooling layer, the output vectors of rows and columns are fused to obtain the predicted value of the score. We compare the existing recommendation system baselines to evaluate our model. The experimental results show that the proposed model is effective in real dataset.

Event driven Recommendation System for E-commerce using Knowledge based Collaborative Filtering Technique

The Internet is changing the method of selling and purchasing items. Nowadays online trading replaces offline trading. The items offered by the online system can influence the nature of buying customers. The recommendation system is one of the basic tools to provide such an environment. Several techniques are used to design and implement the recommendation system. Every recommendation system passes from two phases similarity computation among the users or items and correlation between target user and items. Collaborative filtering is a common technique used for designing such a system. The proposed system uses a knowledge base generated from knowledge graph to identify the domain knowledge of users, items, and relationships among these, knowledge graph is a labelled multidimensional directed graph that represents the relationship among the users and the items. Almost every existing recommendation system is based on one of feature, review, rating, and popularity of the items in which users’ involvement is very less or none. The proposed approach uses about 100 percent of users’ participation in the form of activities during navigation of the web site. Thus, the system expects under the users’ interest that is beneficial for both seller and buyer. The proposed system relates the category of items, not just specific items that may be interested in the users. We see the effectiveness of this approach in comparison with baseline methods in the area of recommendation system using three parameters precision, recall, and NDCG through online and offline evaluation studies with user data, and its performance is better than all other baseline systems in all aspects.

Towards Cognitive Recommender Systems

Intelligence is the ability to learn from experience and use domain experts’ knowledge to adapt to new situations. In this context, an intelligent Recommender System should be able to learn from domain experts’ knowledge and experience, as it is vital to know the domain that the items will be recommended. Traditionally, Recommender Systems have been recognized as playlist generators for video/music services (e.g., Netflix and Spotify), e-commerce product recommenders (e.g., Amazon and eBay), or social content recommenders (e.g., Facebook and Twitter). However, Recommender Systems in modern enterprises are highly data-/knowledge-driven and may rely on users’ cognitive aspects such as personality, behavior, and attitude. In this paper, we survey and summarize previously published studies on Recommender Systems to help readers understand our method’s contributions to the field in this context. We discuss the current limitations of the state of the art approaches in Recommender Systems and the need for our new approach: A vision and a general framework for a new type of data-driven, knowledge-driven, and cognition-driven Recommender Systems, namely, Cognitive Recommender Systems. Cognitive Recommender Systems will be the new type of intelligent Recommender Systems that understand the user’s preferences, detect changes in user preferences over time, predict user’s unknown favorites, and explore adaptive mechanisms to enable intelligent actions within the compound and changing environments. We present a motivating scenario in banking and argue that existing Recommender Systems: (i) do not use domain experts’ knowledge to adapt to new situations; (ii) may not be able to predict the ratings or preferences a customer would give to a product (e.g., loan, deposit, or trust service); and (iii) do not support data capture and analytics around customers’ cognitive activities and use it to provide intelligent and time-aware recommendations.

Research on User Interest Expression and Recommendation Service based on Three-dimensional Relationship of Users and Items

The existing recommendation algorithms often rely heavily on the original score information in the user rating matrix. However, the user's rating of items does not fully reflect the user's real interest. Therefore, the key to improve the existing recommendation system algorithm effectively is to eliminate the influence of these unfavorable factors and the accuracy of the recommendation algorithm can be improved by correcting the original user rating information reasonably. This paper makes a comprehensive theoretical analysis and method design from three aspects: the quality of the item, the memory function of the user and the influence of the social friends trusted by the user on the user's rating. Based on these methods, this paper finally proposes a collaborative filtering recommendation algorithm (FixCF) based on user rating modification. Using data sets such as Movielens, Epinions and Flixster, the data sets are divided into five representative subsets, and the experimental demonstration is carried out. FixCF and classical collaborative filtering algorithms, existing matrix decomposition-based algorithms and trust network-based inference are compared. The experimental results show that the accuracy and coverage of FixCF have been improved under many experimental conditions.

A group preference-based privacy-preserving POI recommender system

Ubiquitous smartphones with their built-in location services enable people to explore various points-of-interest (POIs) through location-based apps, e.g., Yelp and Foursquare City Guide. With these apps, users can receive personalized recommendations on nearby places, e.g., restaurants and arcades, which not only saves them searching time, but also helps find POIs that are of interest to them. One issue with these apps and almost all existing recommender systems is that they require users to share their preference data with the service providers. This information, if not properly used, can leak users’ privacy. In this paper, we propose a group preference-based POI recommendation scheme which fuses matrix factorization and clustering techniques to provide quality recommendations without sacrificing users’ privacy.

Keywords-Driven and Popularity-Aware Paper Recommendation Based on Undirected Paper Citation Graph

Nowadays, scholar recommender systems often recommend academic papers based on users’ personalized retrieval demands. Typically, a recommender system analyzes the keywords typed by a user and then returns his or her preferred papers, in an efficient and economic manner. In practice, one paper often contains partial keywords that a user is interested in. Therefore, the recommender system needs to return the user a set of papers that collectively covers all the queried keywords. However, existing recommender systems only use the exact keyword matching technique for recommendation decisions, while neglecting the correlation relationships among different papers. As a consequence, it may output a set of papers from multiple disciplines that are different from the user’s real research field. In view of this shortcoming, we propose a keyword-driven and popularity-aware paper recommendation approach based on an undirected paper citation graph, named PRkeyword+pop. At last, we conduct large-scale experiments on the real-life Hep-Th dataset to further demonstrate the usefulness and feasibility of PRkeyword+pop. Experimental results prove the advantages of PRkeyword+pop in searching for a set of satisfactory papers compared with other competitive approaches.

A hybrid context-aware approach for e-tourism package recommendation based on asymmetric similarity measurement and sequential pattern mining

Abstract Personalized travel package recommendation for tourists is an important task in the e-Tourism field. With the excessive growth of data over the internet, it has become difficult to find relevant information among all of the Points-of-Interest (PoIs) for tourists. Recommendation Systems (RSs) are the essential tools to tackle the information overload problem and suggesting relevant items to the users. But, due to differences in users’ interests, dynamic contexts and sequential travel patterns in their behaviors, the existing recommender systems could not provide accurate recommendations to the users. Moreover, due to the lack of sufficient historical data about users in tourism area, cold start and data sparsity problems lead to more challenges for recommending precise and reliable suggestions. In this paper, a personalized travel package recommendation approach is proposed to generate dynamic recommendations to the users by taking into account the multidimensional data of time, location, users’ implicit ratings, tourists’ characteristics and their sequential travel movement patterns based on the geo-tagged photos. Therefore, we combine four different recommendation methods including, Collaborative Filtering (CF), Context-Awareness (CA), Demographic-Based (DB) and Sequential Pattern Mining (SPM) to ameliorate the quality of the suggestion results. Further, a dynamic contextual modelling approach is used to incorporate contexts information into the recommendation procedure to cope with the context pre/post filtering problems, and provide dynamic travel recommendation to the tourist based on his/her current contexts information. Furthermore, this approach extends the CF method by using multidimensional data and an asymmetric similarity scheme for score function to alleviate the limitation of CF and improve the accuracy of predicted recommendations. Moreover, the proposed approach recommendations will be optimized by applying the personalized PoIs to the sequential travel patterns and personalizes the travel package recommendations for each user based on his/her interests. The experimental results based on Flickr dataset illustrate the effectiveness and quality of the proposed approach over state-of-the-art approaches under cold-start and data sparsity conditions by contextualizing users’ interests, utilizing demographic information, applying the asymmetric similarity scheme and using the sequential pattern mining.

Question-Driven Purchasing Propensity Analysis for Recommendation

Merchants of e-commerce Websites expect recommender systems to entice more consumption which is highly correlated with the customers' purchasing propensity. However, most existing recommender systems focus on customers' general preference rather than purchasing propensity often governed by instant demands which we deem to be well conveyed by the questions asked by customers. A typical recommendation scenario is: Bob wants to buy a cell phone which can play the game PUBG. He is interested in HUAWEI P20 and asks “can PUBG run smoothly on this phone?” under it. Then our system will be triggered to recommend the most eligible cell phones to him. Intuitively, diverse user questions could probably be addressed in reviews written by other users who have similar concerns. To address this recommendation problem, we propose a novel Question-Driven Attentive Neural Network (QDANN) to assess the instant demands of questioners and the eligibility of products based on user generated reviews, and do recommendation accordingly. Without supervision, QDANN can well exploit reviews to achieve this goal. The attention mechanisms can be used to provide explanations for recommendations. We evaluate QDANN in three domains of Taobao. The results show the efficacy of our method and its superiority over baseline methods.

Towards Comprehensive Recommender Systems: Time-Aware Unified Recommendations Based on Listwise Ranking of Implicit Cross-Network Data

The abundance of information in web applications make recommendation essential for users as well as applications. Despite the effectiveness of existing recommender systems, we find two major limitations that reduce their overall performance: (1) inability to provide timely recommendations for both new and existing users by considering the dynamic nature of user preferences, and (2) not fully optimized for the ranking task when using implicit feedback. Therefore, we propose a novel deep learning based unified cross-network solution to mitigate cold-start and data sparsity issues and provide timely recommendations for new and existing users. Furthermore, we consider the ranking problem under implicit feedback as a classification task, and propose a generic personalized listwise optimization criterion for implicit data to effectively rank a list of items. We illustrate our cross-network model using Twitter auxiliary information for recommendations on YouTube target network. Extensive comparisons against multiple time aware and cross-network baselines show that the proposed solution is superior in terms of accuracy, novelty and diversity. Furthermore, experiments conducted on the popular MovieLens dataset suggest that the proposed listwise ranking method outperforms existing state-of-the-art ranking techniques.

Explicit feedback meet with implicit feedback in GPMF: a generalized probabilistic matrix factorization model for recommendation

Recommender Systems focus on implicit and explicit feedback or parameters of users for better rating prediction. Most of the existing recommender systems use only one type of feedback ignoring the other one. Based on the availability of resources, we may consider more number of feedback of both the types to predict user’s rating for a particular item more accurately. However to the best of our knowledge, there is no generalized model that is fitted for multiple parameters or feedback. In this paper, we have proposed a Generalized Probabilistic Matrix Factorization (GPMF) model which uses multiple parameters of both the types for recommendation. To build GPMF, first we develop three models focusing on users’ crucial side information. First model PMFE (P robabilistic M atrix F actorization with E xplicit_Feedback) is proposed based on an explicit feedback of users and second one is PMFI (P robabilistic M atrix F actorization with I mplicit_Feedback), where an implicit feedback is considered. The last one is PMFEI (P robabilistic M atrix F actorization with E xplicit and I mplicit_Feedback), where both explicit and implicit feedback are considered. Extensive experiments on real world datasets show that PMFEI performs better compare to baselines. PMFEI model also performs better compare to baselines for cold-start users and cold-start items also. In our experimental section, it is shown that GPMF performs better when we consider both explicit and implicit feedback. The effectiveness of each parameter is not same for recommendation. Using GPMF we can estimate the effectiveness of a parameter. Based on this effectiveness, we can add or remove more parameters for better rating prediction.

Improving Implicit Recommender Systems with Auxiliary Data

Most existing recommender systems leverage the primary feedback only, despite the fact that users also generate a large amount of auxiliary feedback. These feedback usually indicate different user preferences when comparing to the primary feedback directly used to optimize the system performance. For example, in E-commerce sites, view data is easily accessible, which provides a valuable yet weaker signal than the primary feedback of purchase. In this work, we improve implicit feedback-based recommender systems (dubbed Implicit Recommender Systems ) by integrating auxiliary view data into matrix factorization (MF). To exploit different preference levels, we propose both pointwise and pairwise models in terms of how to leverage users’ viewing behaviors. The latter model learns the pairwise ranking relations among purchased, viewed, and non-viewed interactions, being more effective and flexible than the former pointwise MF method. However, such a pairwise formulation poses a computational efficiency problem in learning the model. To address this problem, we design a new learning algorithm based on the element-wise Alternating Least Squares (eALS) learner. Notably, our designed algorithm can efficiently learn model parameters from the whole user-item matrix (including all missing data), with a rather low time complexity that is dependent on the observed data only. Extensive experiments on two real-world datasets demonstrate that our method outperforms several state-of-the-art MF methods by 6.43%∼ 6.75%. Our implementation is available at https://github.com/dingjingtao/Auxiliary_enhanced_ALS.

A Multi-Period Product Recommender System in Online Food Market based on Recurrent Neural Networks

A recommender system supports customers to find information, products, or services (such as music, books, movies, web sites, and digital contents), so it could help customers to make rapid routine decisions and save their time and money. However, most existing recommender systems do not recommend items that are already purchased by the target customer, so are not suitable for considering customers’ repetitive purchase behavior or purchasing order. In this research, we suggest a multi-period product recommender system, which can learn customers’ purchasing order and customers’ repetitive purchase pattern. For such a purpose we applied the Recurrent Neural Network (RNN), which is one of the artificial neural network structures specialized in time series data analysis, instead of collaborative filtering techniques. Recommendation periods are segmented as various time-steps, and the proposed RNN-based recommender system can recommend items by multiple periods in a time sequence. Several experiments with real online food market data show that the proposed system shows higher performance in accuracy and diversity in a multi-period perspective than the collaborative filtering-based system. From the experimental results, we conclude that the proposed system is suitable for multi-period product recommendation, which results in robust performance considering well customers’ purchasing orders and customers’ repetitive purchase patterns. Moreover, in terms of sustainability, we expect that our study contributes to the reduction of food wastes by inducing planned consumption, and the reduction of shopping time and effort.

A hybrid recommender system for product sales in a banking environment

Recommender systems have been successfully applied in many domains, including in e-commerce and entertainment to boost sales. However, most existing recommender systems employ the collaborative or community-based approach which relies on the preferences or behaviour of other users, in conjunction with that of the target user. This approach may not be applicable to domains such as banking. The two major challenges to using the collaborative approach in the banking domain are: (1) absence of explicit ratings of products by customers for recommendation purpose, (2) cold-start problem which makes it difficult to recommend products to a prospective or new customer who has no preference at all. To tackle the first issue, we develop an algorithm that implicitly infers customer preferences from transaction data. To address the second issue, we propose a hybrid recommender system that combines the item-based collaborative filtering technique (which uses the customer preference data from the algorithm) and the demographic-based approach (which uses customers’ demographics). We contribute to knowledge by developing a practical and feasible approach for implementing recommender systems that drive product marketing in the banking sector. We also discuss the performance of this approach based on 393,816 customers dataset. The hybrid approach is applicable to other domains with similar challenges.

A Hybrid Recommender Method Based on Multiple Dimension Attention Analysis

With the development of the Internet and the popularity of Big Data, recommender systems have become an indispensable field due to its excellent ability to solve the problem of information overload. The existing recommender system mainly uses collaborative filtering to make recommendation by mining the interaction relationship between users and items. In order to better analyze the interaction relationship between users and items, a hybrid recommender method based on multiple dimension attention analysis is proposed. The idea is to fuse the embedded vectors of users and items into mapping vectors (or matrices) of different shapes through different methods, and learn the interactive relationship between users and items through the neural network model with attention mechanism. Experimental results show that compared with traditional analytical methods, multiple dimension analysis can more comprehensively explore the interaction between users and items, and the attention mechanism can greatly improve the analytical ability of the model.

Recommendation System Based on Heterogeneous Feature: A Survey

Recommendation systems have become an important field of research in computer science and physics. In recent years, breakthroughs have been achieved in social, biological, and research cooperation networks. With the popularization of big data and deep learning technology development, graph structures are increasingly being used to represent large-scale and complex data in the real world. In this paper, we reviewed the progress made in recommendation systems research in the past 20 years and comprehensively classified recommender systems based on the heterogeneous input features. We introduced layering in the classification of recommendation systems. Furthermore, we proposed a new hierarchical classification model of recommendation systems divided into three layers: feature input, feature learning, and output layers. In the feature learning layer, existing recommendation systems were divided into graph-based, text-based, behavior-based, spatiotemporal-based, and hybrid recommendation systems. Additionally, we provided evaluation index, open-source implementation, experimental comparison and the relative merits for each recommendation method. Subsequently, future development directions of recommendation systems are discussed.

Application of clustering algorithm in social network user scenario prediction

In order to improve the ability of social network user behavior analysis and scenario pattern prediction, optimize social network construction, combine data mining and behavior analysis methods to perform social network user characteristic analysis and user scenario pattern optimization mining, and discover social network user behavior characteristics. Design multimedia content recommendation algorithms in multimedia social networks based on user behavior patterns. The current existing recommendation systems do not know how much the user likes the currently viewed content before the user scores the content or performs other operations, and the user’s preference may change at any time according to the user’s environment and the user’s identity, Usually in multimedia social networks, users have their own grading habits, or users’ ratings may be casual. Cluster-based algorithm, as an application of cluster analysis, based on clustering, the algorithm can predict the next position of the user. Because the algorithm has a “cold start”, it is suitable for new users without trajectories. You can also make predictions. In addition, the algorithm also considers the user’s feedback information, and constructs a scoring system, which can optimize the results of location prediction through iteration. The simulation results show that the accuracy of social network user scenario prediction using this method is higher, the accuracy of feature registration of social network user scenario mode is improved, and the real-time performance of algorithm processing is better.

Co-Displayed Items Aware List Recommendation

Existing recommender systems usually generate personalized recommendation lists based on the estimation of the preference scores over user-item pairs, while ignoring the impacts of the entire display list that plays a central part in the decision making process of a user. This leaves us an opportunity to generate better recommendation results by considering the impacts of all offered choices. However, such an extension cannot be handled efficiently by traditional top- $k$ list recommendation methods, due to the entire list dependency issue which means a complete list of items is needed before we can precisely measure any item preference among the list. In this paper, we propose a Co-displayed Items Aware (CDIA) list generation approach, which is based on the reinforcement learning architecture, and can efficiently generate high-utility lists. Specifically, we propose CDIA-Sim to predict users’ preferences, which considers the impacts of the co-displayed items. Then, to overcome the entire list dependency issue in the list recommendation task, we utilize the reinforcement learning technique and design CDIA-RL to generate high-utility lists. Experimental results show that CDIA-Sim achieves significant improvements in modeling user-item preferences, and CDIA-RL can yield lists efficiently and effectively, illustrating better performance than other competitors.

HYPNER: A Hybrid Approach for Personalized News Recommendation

A personalised news recommendation system extracts news set from multiple press releases and presents the recommended news to the user. In an effort to build a better recommender system with high accuracy, this paper proposes a personalised news recommendation framework named Hybrid Personalised NEws Recommendation (HYPNER). HYPNER combines both collaborative filtering-based and content-based filtering methods. The proposed framework aims at improving the accuracy of news recommendation by resolving the issues of scalability due to large news corpus, enriching the user's profile, representing the exact properties and characteristics of news items, and recommending diverse set of news items. Validation experiments showed that HYPNER achieved 81.56% improvement in F1 -score and 5.33% in diversity as compared to an existing recommender system, SCENE.

Tree-Based Real-Time Advertisement Recommendation System in Online Broadcasting

The viewing time of media content per week through TV is still dominant. Users are exposed to numerous advertisements, such as commercials, electronic home shopping, product placement (PPL), and T-Commerce while watching TV programs. Most of the advertisement systems provide a good overview of products. However, traditional advertising services do not consider user preferences, meaning it is difficult to expect anything more than mere exposure to them. We can adopt a recommendation system to predict the preference. However, existing recommendation systems find it difficult to satisfy the real-time requirements of online broadcasting because of the large overhead incurred in preference prediction processes. In this paper, we propose a real-time recommendation system to provide personalized advertisements. The proposed system generates tree models based on user historical data. To reduce the overhead of preference prediction, we introduce a sorted HashMap that enables fast tree searches. For sophisticated preference prediction, the proposed system normalizes the users' preferences by considering the characteristics of their tree model. Finally, we conduct experiments to evaluate the performance of the proposed tree-based recommendation system.