Application Of Recommender Systems Research Articles

Federated Multi-Armed Bandits

Federated multi-armed bandits (FMAB) is a new bandit paradigm that parallels the federated learning (FL) framework in supervised learning. It is inspired by practical applications in cognitive radio and recommender systems, and enjoys features that are analogous to FL. This paper proposes a general framework of FMAB and then studies two specific federated bandit models. We first study the approximate model where the heterogeneous local models are random realizations of the global model from an unknown distribution. This model introduces a new uncertainty of client sampling, as the global model may not be reliably learned even if the finite local models are perfectly known. Furthermore, this uncertainty cannot be quantified a priori without knowledge of the suboptimality gap. We solve the approximate model by proposing Federated Double UCB (Fed2-UCB), which constructs a novel “double UCB” principle accounting for uncertainties from both arm and client sampling. We show that gradually admitting new clients is critical in achieving an O(log(T)) regret while explicitly considering the communication loss. The exact model, where the global bandit model is the exact average of heterogeneous local models, is then studied as a special case. We show that, somewhat surprisingly, the order-optimal regret can be achieved independent of the number of clients with a careful choice of the update periodicity. Experiments using both synthetic and real-world datasets corroborate the theoretical analysis and demonstrate the effectiveness and efficiency of the proposed algorithms.

An Overview of Recommendation Techniques and Their Applications in Healthcare

With the increasing amount of information on the internet, recommendation system (RS) has been utilized in a variety of fields as an efficient tool to overcome information overload. In recent years, the application of RS for health has become a growing research topic due to its tremendous advantages in providing appropriate recommendations and helping people make the right decisions relating to their health. This paper aims at presenting a comprehensive review of typical recommendation techniques and their applications in the field of healthcare. More concretely, an overview is provided on three famous recommendation techniques, namely, content-based, collaborative filtering (CF)-based, and hybrid methods. Next, we provide a snapshot of five application scenarios about health RS, which are dietary recommendation, lifestyle recommendation, training recommendation, decision-making for patients and physicians, and disease-related prediction. Finally, some key challenges are given with clear justifications to this new and booming field.

Parallel tensor factorization for relational learning

Link prediction is a statistical relational learning problem that has a variety of applications in recommender systems, expert systems, and knowledge bases. Numerous approaches have already been devised to solve the problem. Tensor factorization is one of the ways to solve the link prediction problem. Many tensor factorization techniques have been devised in the last few decades, including Tucker, CANDECOMP/PARAFAC, and DEDICOM. RESCAL is one of the famous tensor factorization technique that can solve large scale problems with relatively less time and space complexity. The time complexity of RESCAL can further be reduced by making it parallel. This variant can also be applied to large scale datasets. This article focuses on devising a parallel version for RESCAL. A decent decrease in execution time has been observed in the execution of parallel RESCAL.

The application of e-commerce recommendation system in smart cities based on big data and cloud computing

In the era of big data, the amount of Internet data is growing explosively. How to quickly obtain valuable information from massive data has become a challenging task. To effectively solve the problems faced by recommendation technology, such as data sparsity, scalability, and real-time recommendation, a personalized recommendation algorithm for e-commerce based on Hadoop is designed aiming at the problems in collaborative filtering recommendation algorithm. Hadoop cloud computing platform has powerful computing and storage capabilities, which are used to improve the collaborative filtering recommendation algorithm based on project, and establish a comprehensive evaluation system. The effectiveness of the proposed personalized recommendation algorithm is further verified through the analysis and comparison with some traditional collaborative filtering algorithms. The experimental results show that the e-commerce system based on cloud computing technology effectively improves the support of various recommendation algorithms in the system environment; the algorithm has good scalability and recommendation efficiency in the distributed cluster, and the recommendation accuracy is also improved, which can improve the sparsity, scalability and real-time problems in e-commerce personalized recommendation. This study greatly improves the recommendation performance of e-commerce, effectively solves the shortcomings of the current recommendation algorithm, and further promotes the personalized development of e-commerce.

Predict Health Insurance Purchase with Machine Learning Techniques

With the widespread application of product recommender systems, there exists significant scope to enhance predicting customers’ purchasing possibility. Then 4 supervised classification models are constructed based on the data from a financial corporation, including logistic regression model, decision tree, bagging and random forest, to anticipate which customer is more likely to adopt the proposed health insurance policy. After comparing 𝐹1 score using an undersampling train set considering unbalanced sample data, the logistic regression model ultimately represents a superior prediction accuracy for clients’ buying propensity, and therefore has the potential to improve targeted selling system for this company.

Application of Intelligent Recommendation for Agricultural Information: A Systematic Literature Review

With the ever-growing volume of online information, recommender system has been an effective strategy to overcome such information overload. Recommender systems are widely used in many web applications, such as e-commerce, news, agriculture and other fields. Agricultural informatization is an important driving force for the development of agricultural modernization. With the further improvement of agricultural informatization infrastructure construction, the use of modern information technology to achieve personalized agricultural information resource recommendation services and providing users with timely and effective information has become an effective solution. This article aims to provide a comprehensive review of recent research efforts on application of agricultural information based on intelligent recommender systems. Firstly, the method of content analysis used in this article to sort out the papers is introduced. Secondly, the background concepts of recommender systems and the key technologies are presented. Thirdly, the applications of recommender systems/technologies for agricultural information are described in detail. Finally, a summary and outlook on the application of recommender systems for agricultural information are provided.

A Novel IoT Application Recommendation System Using Metaheuristic Multi-Criteria Analysis

There are a variety of Internet of Things (IoT) applications that cover different aspects of daily life. Each of these applications has different criteria and sub-criteria, making it difficult for the user to choose. This requires an automated approach to select IoT applications by considering criteria. This paper presents a novel recommendation system for presenting applications on the IoT. First, using the analytic hierarchy process (AHP), a multi-layer architecture of the criteria and sub-criteria in IoT applications is presented. This architecture is used to evaluate and rank IoT applications. As a result, finding the weight of the criteria and sub-criteria requires a metaheuristic approach. In this paper, a sequential quadratic programming algorithm is used to find the optimal weight of the criteria and sub-criteria automatically. To the best of our knowledge, this is the first study to use an analysis of metaheuristic criteria and sub-criteria to design an IoT application recommendation system. The evaluations and comparisons in the experimental results section show that the proposed method is a comprehensive and reliable model for the construction of an IoT applications recommendation system.

A Singular Value Thresholding with Diagonal-Update Algorithm for Low-Rank Matrix Completion

The singular value thresholding (SVT) algorithm plays an important role in the well-known matrix reconstruction problem, and it has many applications in computer vision and recommendation systems. In this paper, an SVT with diagonal-update (D-SVT) algorithm was put forward, which allows the algorithm to make use of simple arithmetic operation and keep the computational cost of each iteration low. The low-rank matrix would be reconstructed well. The convergence of the new algorithm was discussed in detail. Finally, the numerical experiments show the effectiveness of the new algorithm for low-rank matrix completion.

Structured Gaussian Process Regression of Music Mood

Modeling the music mood has wide applications in music categorization, retrieval, and recommendation systems; however, it is challenging to computationally model the affective content of music due to its subjective nature. In this work, a structured regression framework is proposed to model the valence and arousal mood dimensions of music using a single regression model at a linear computational cost. To tackle the subjectivity phenomena, a confidence-interval based estimated consensus is computed by modeling the behavior of various annotators (e.g. biased, adversarial) and is shown to perform better than using the average annotation values. For a compact feature representation of music clips, variational Bayesian inference is used to learn the Gaussian mixture model representation of acoustic features and chord-related features are used to improve the valence estimation by probing the chord progressions between chroma frames. The dimensionality of features is further reduced using an adaptive version of kernel PCA. Using an efficient implementation of twin Gaussian process for structured regression, the proposed work achieves a significant improvement in R2 for arousal and valence dimensions relative to state-of-the-art techniques on two benchmark datasets for music mood estimation.

A Model-Bias Matrix Factorization Approach for Course Score Prediction

Recommender algorithms are widely used in e-commercial platforms to recommend users suitable items according to users’ preferences. In recent years, an increasing amount of attention has been paid to the application of recommender system in education. There are many online learning systems that can recommend students suitable courses according to students’ learning performances. However, there are few universities using recommender system to recommend students suitable elective courses. It is generally known that students in higher grade take the courses earlier than those in lower grade. Therefore, the elective course scores of sophomores can be predicted by using the course score information from students of higher grades. However, the unbalanced distribution of course-enrollment data makes it hard to predict the score of the courses that are in a low selection rate. Therefore, we propose a model-bias matrix factorization algorithm to predict sophomores’ elective course scores, which takes into account the score prediction deviation caused by the course selection rate so as to make more accurate prediction than the traditional matrix factorization approaches. The experimental results show that our proposed model outperforms the state-of-the-art methods in the task of university students’ course score prediction.

A deep neural architecture based meta-review generation and final decision prediction of a scholarly article

Peer reviews form an essential part of scientific communications. Research papers and proposals are reviewed by several peers before they are finally accepted or rejected for publication and funding, respectively. With the steady increase in the number of research domains, scholarly venues (journal and/or conference), researchers, and papers, managing the peer review process is becoming a daunting task. Application of recommender systems to assist peer reviewing is, therefore, being explored and becoming an emerging research area. In this paper, we present a deep learning network based Meta-Review Generation considering peer review prediction of the scholarly article (MRGen). MRGen is able to provide solutions for: (i) Peer review prediction (Task 1) and (ii) Meta-review generation (Task 2). First, the system takes the peer reviews as input and produces a draft meta-review. Then it employs an integrated framework of convolution layer, long short-term memory (LSTM) model, Bi-LSTM model, and attention mechanism to predict the final decision (accept/reject) of the scholarly article. Based on the final decision, the proposed model MRGen incorporates Pointer Generator Network-based abstractive summarization to generate the final meta-review. The focus of our approach is to give a concise meta-review that maximizes information coverage, coherence, readability and also reduces redundancy. Extensive experiments conducted on the PeerRead dataset demonstrate good consistency between the recommended decisions and original decisions. We also compare the performance of MRGen with some of the existing state-of-the-art multi-document summarization methods. The system also outperforms a few existing models based on accuracy, Rouge scores, readability, non-redundancy, and cohesion.

Artificial intelligence in recommender systems

Recommender systems provide personalized service support to users by learning their previous behaviors and predicting their current preferences for particular products. Artificial intelligence (AI), particularly computational intelligence and machine learning methods and algorithms, has been naturally applied in the development of recommender systems to improve prediction accuracy and solve data sparsity and cold start problems. This position paper systematically discusses the basic methodologies and prevailing techniques in recommender systems and how AI can effectively improve the technological development and application of recommender systems. The paper not only reviews cutting-edge theoretical and practical contributions, but also identifies current research issues and indicates new research directions. It carefully surveys various issues related to recommender systems that use AI, and also reviews the improvements made to these systems through the use of such AI approaches as fuzzy techniques, transfer learning, genetic algorithms, evolutionary algorithms, neural networks and deep learning, and active learning. The observations in this paper will directly support researchers and professionals to better understand current developments and new directions in the field of recommender systems using AI.

A cross-country study on cultural similarities based on book preferences

What people choose to read is believed to be highly influenced by their cultural backgrounds and environment. Thus, understanding the cultural and socioeconomic factors that have significant relations with the reading preferences of nations can be of great importance for the book retail industry. These insights can have applications in recommender systems, sales predictions, and customer relationship management. Motivated by these values, we conducted a large-scale cross-country analysis of cultural similarities and differences based on book preferences using data collected from Goodreads. We use bipartite configuration model and community detection to explore the relationships between countries based on their book preferences. We also investigate the similarities between countries based on their favorite genres and authors. Additionally, this paper explores the significance of cultural, lingual, and socioeconomics factors on book preferences using quadratic assignment procedure statistical tests. Our results indicate that geographical distance, lingual distance, cognitive ability, intelligence quotient, and individualism are all significantly associated with book preference at the country level.

Development of a consumer financial goals ontology for use with FinTech applications for improving financial capability

In this research, we communicate the design and evaluation of a consumer financial goals ontology to be utilized as a knowledgebase within recommender systems applications designed to provide decision support in the domain of financial planning. The goal of this research is to provide a domain conceptualization and knowledge classification of a comprehensive set of financial capability enhancing objectives contextually appropriate for a wide range of socio-economically situated consumers. Currently, to the best of our knowledge, within the domain of consumer financial planning no formal conceptual model or knowledge classification of financial goals exists which might be utilized as a knowledgebase for applications such as a FinTech recommender system. Achieving financial goals is a key behavior associated with consumer financial capability, a topic of national economic importance. A holistic representation of domain concepts is critical for advancement of solutions to problems pertinent to a domain. One primary reason for the dearth of applications designed to assist consumers with financial goal setting is the absence of a common domain ontology of financial goals. This study addresses a gap in the literature by contributing to the research knowledgebase an ontology for a domain of consumer financial goals. In doing so, it advances scholarly research through novel domain knowledge classification while providing researchers and practitioners with an ontological knowledgebase for indexing and retrieval within applications designed to improve consumer financial capability through identification and recommendation of specific, context-aware financial goals. The ontology could be used, for example, as a knowledgebase for a Personal Financial Recommender System (PFRS), or other financial technology (FinTech) application, designed to assist users with identification, setting, and tracking of financial goals.

Feature-Level Rating System Using Customer Reviews and Review Votes

This work studies how we can obtain feature-level ratings of the mobile products from the customer reviews and review votes to influence decision-making, both for new customers and manufacturers. Such a rating system gives a more comprehensive picture of the product than what a product-level rating system offers. While product-level ratings are too generic, feature-level ratings are particular; we exactly know what is good or bad about the product. There has always been a need to know which features fall short or are doing well according to the customer’s perception. It keeps both the manufacturer and the customer well-informed in the decisions to make in improving the product and buying, respectively. Different customers are interested in different features. Thus, feature-level ratings can make buying decisions personalized. We analyze the customer reviews collected on an online shopping site (Amazon) about various mobile products and the review votes. Explicitly, we carry out a feature-focused sentiment analysis for this purpose. Eventually, our analysis yields ratings to 108 features for 4000+ mobiles sold online. It helps in decision-making on how to improve the product (from the manufacturer’s perspective) and in making the personalized buying decisions (from the buyer’s perspective) a possibility. Our analysis has applications in recommender systems, consumer research, and so on.

Functionality-based mobile application recommendation system with security and privacy awareness

Nowadays, there are a variety of mobile device applications to execute tasks, such as paying bills and ordering food. However, some apps (malicious) claim that they perform a certain task just to lure users to damage their devices and/or execute malicious activities such as leaking sensitive information. Because of that, users need a way to choose an app that is safe and meets their needs. Recommendation systems are currently being used to choose apps, but most approaches do not evaluate security and privacy, and when they do, only permissions are considered. In this context, this work presents a novel system to evaluate and suggest apps. The main contributions are the addition of a security layer, the evaluation of the metrics inside a functionality context and a mapping between permissions and API calls raising user confidence and understanding.

Complements and substitutes in online product recommendations: The differential effects on consumers’ willingness to pay

Online product recommendations have been shown to influence consumers’ preferences and purchasing behaviors for recommended products. However, it remains an open empirical question whether and how recommendations of other products affect a consumer’s economic behavior for a focal product. In many e-commerce websites, a product is presented with co-purchase and co-view recommendations, which potentially contain complementary and substitutable products, respectively. Very little research has explored differential effects of recommending complementary and substitutable products. In this study, we explore how types of other recommended products impact consumers’ willingness to pay for a focal product through interactions with prices of recommended products and consumers’ decision stages. We conducted a 23 randomized factorial experiment as well as two 2 × 2 experiments to examine these issues. Experimental results provide evidence that there is a significant interaction effect between the recommendation type and decision stage, which highlights the importance of recommendation timing on e-commerce platforms. Furthermore, it also illustrates that the effect of recommending complementary vs. substitutable products is subject to contextual factors such as consumers’ decision stages. Results of our study have significant implications for the design and application of online recommender systems.

Application of recommendation system with AHP method and sentiment analysis

Over time, people needs are increasing. Needs that must be met, often cause problems in the people in determining a choice. People must make the right choice and according to their needs. Not an easy thing for people to make these choices. Therefore, a recommendation system is needed to support people in making decisions that fit their criteria. This research provides a system that can provide recommendations for decision support people according to their criteria, which are web-based. The decision-making system in this research uses the analytical hierarchy process (AHP) method. AHP is a multi-criteria decision-making method, which in this research one of the criteria is using sentiment analysis. Sentiment analysis is the process of understanding, extracting, and processing textual data to get sentiment information from an opinion sentence. The opinion sentiment value of each alternative will be included in the AHP calculation to get the best alternative recommendations according to the criteria of people. The result of this research is that the system can provide recommendations to people or users according to their criteria and alternatives as well as public opinion about each alternative.

Application intelligent search and recommendation system based on speech recognition technology

With the progress of science and technology, artificial intelligence as the emerging tool has been deeply into our lives. The application of modern intelligent equipment is more and more extensive, and also inseparable from our lives. The mobile intelligent terminal represented by smart phone is a powerful intelligent computing and networking device, which has more perception and interaction capabilities. Due to the emergence of a large number of application software, it is not easy to find and get the app that you really need. Therefore, this paper uses speech recognition technology to build an app intelligent search and recommendation system. We designed the system from the levels of speech information extraction, analysis and finalized recommendation. Experimental results show that the proposed method is more efficient and intelligent.

Deep Match to Rank Model for Personalized Click-Through Rate Prediction

Click-through rate (CTR) prediction is a core task in the field of recommender system and many other applications. For CTR prediction model, personalization is the key to improve the performance and enhance the user experience. Recently, several models are proposed to extract user interest from user behavior data which reflects user's personalized preference implicitly. However, existing works in the field of CTR prediction mainly focus on user representation and pay less attention on representing the relevance between user and item, which directly measures the intensity of user's preference on target item. Motivated by this, we propose a novel model named Deep Match to Rank (DMR) which combines the thought of collaborative filtering in matching methods for the ranking task in CTR prediction. In DMR, we design User-to-Item Network and Item-to-Item Network to represent the relevance in two forms. In User-to-Item Network, we represent the relevance between user and item by inner product of the corresponding representation in the embedding space. Meanwhile, an auxiliary match network is presented to supervise the training and push larger inner product to represent higher relevance. In Item-to-Item Network, we first calculate the item-to-item similarities between user interacted items and target item by attention mechanism, and then sum up the similarities to obtain another form of user-to-item relevance. We conduct extensive experiments on both public and industrial datasets to validate the effectiveness of our model, which outperforms the state-of-art models significantly.