Recommender System Algorithms Research Articles

Rating Prediction in Recommender Systems Based on User Behavior Probability and Complex Network Modeling

In recommender systems, measuring user similarity is essential for predicting a user’s ratings on items. Most traditional works calculate the similarity based on historical ratings shared between two users, without considering the probability of users’ different behaviors. To address this issue, our work designs a similarity measure based on the users’ historical behavior probabilities. Based on the similarity method, a complex network of user relationships is modeled. The user degree and community information of the modeled network, as well as the number of shared ratings between users, are used with the proposed similarity measure to design a rating prediction algorithm for recommender systems. Experiments based on MovieLens and Netflix data sets show that this method is effective and can successfully improve the accuracy of rating predictions and reduce the number of neighbors required to achieve the optimal prediction accuracy. Our research shows that in a complex system, the relationship between users can be effectively measured by the users’ historical behavior probability, providing a new perspective for future research on similarity measurement.

DARES: An Asynchronous Distributed Recommender System Using Deep Reinforcement Learning

Traditional Recommender Systems (RS) use central servers to collect user data, compute user profiles and train global recommendation models. Central computation of RS models has great results in performance because the models are trained using all the available information and the full user profiles. However, centralised RS require users to share their whole interaction history with the central server and in general are not scalable as the number of users and interactions increases. Central RSs also have a central point of attack with respect to user privacy, because all user profiles and interactions are stored centrally. In this work we propose DARES, an distributed recommender system algorithm that uses reinforcement learning and is based on the asynchronous advantage actor-critic model (A3C). DARES is developed combining the approaches of A3C and federated learning (FL) and allows users to keep their data locally on their own devices. The system architecture consists of (i) a local recommendation model trained locally on the user devices using their interaction and (ii) a global recommendation model that is trained on a central server using the model updates that are computed on the user devices. We evaluate the proposed algorithm using well-known datasets and we compare its performance against well-known state of the art algorithms. We show that although being distributed and asynchronous, it can achieve comparable and in many cases better performance than current state-of-the-art algorithms.

Comparative Study of Machine Learning Algorithms for Recommendation System

The role of recommender system is very vital in recent times for a lot of individuals. It helps in taking decisions without exploring physically. Broadly there are two types of recommender system: Content based and Collaborative Filtering. The first one focus on user’s history and takes decisions. But there could be times when decisions based on only user history is not sufficient. For this, there is a need to analyze many parameters influencing the decision such as previous history, Age, gender, location etc. In the second approach it finds similar group of users based on several parameters and then takes decisions. Over the last few decades machine learning algorithms have proved their worth in this area because of their ability to learn from the given data and identify various hidden patterns. With this learning, these algorithms are able to generalize very well for unknown data. In this research work, a survey on three different machine learning based collaborative filtering methods are presented using Movie Lens dataset. The comparison of all three methods based on RMSE and MAE error is also discussed.

ConvSVD++: A Hybrid Deep CF Recommender Model using Convolutional Neural Network

Recommender systems are powerful systems that give added value to business and corporation. They are relatively recent technology and they will only keep improving in the future. The most widely used algorithms for recommender systems are categorized into the traditional recommender and deep-based recommender system. The traditional recommendation algorithm suffers from sparse data that significantly degrades recommendation accuracy. The hybrid approaches are attempts to tackle recommendation challenges. This paper addresses the integration of deep learning into traditional recommendation approaches especially, Collaborative Filtering (CF) algorithms to get a significant accurate prediction. It proposes a hybrid deep CF recommender model called ConvSVD++ that tightly integrates Convolution Neural Network (CNN) and Singular Value Decomposition (SVD++). The proposed model incorporates items’ content, implicit user’s feedback along with explicit item-user interaction to enhance prediction accuracy and handle sparsity problem. The proposed model is evaluated and all baseline models based on Movielens- 1M datasets. The results are evaluated using Root Mean Squared Error (RMSE) metric and it is concluded that the proposed model ConvSVD++ outperforms the baselines models. Accordingly, it is concluded that integrating CNN with SVD++ algorithm improves rating prediction accuracy.

A deep learning based algorithm for multi-criteria recommender systems

Recommender systems have become exceptionally widespread in recent years to deal with the information overload problem by providing personalized recommendations. Multi-criteria recommender systems proved to have more accurate recommendations compared to single-criterion recommender systems as multi-criteria rating reflects the user appreciation of an item in terms of many aspects. On the another hand, deep learning techniques achieve promising performance in many research areas such as image processing, computer vision, pattern recognition and natural language processing. Recently, the application of deep learning in recommender systems have been frequently explored with encouraging results. Accordingly, this paper proposes a deep learning based algorithm for multi-criteria recommender systems in which deep autoencoders are employed to exploit the non-trivial, nonlinear and hidden relations between users with regard to multi-criteria preferences, and generate more accurate recommendations. Experiments on the Yahoo! Movies and TripAdvisor multi-criteria datasets show that the proposed algorithm prove to be very effective in terms of producing more accurate predictions compared with the state-of-the-art recommendation algorithms

Bi-MARS: A Bi-clustering based Memetic Algorithm for Recommender Systems

Context:With the expansion of e-business, availability of items on the web is profuse as compared to the previous era. The task of finding relevant items from this pool of items available online is a time-consuming task. Collaborative Filtering (CF) is the foremost productive recommendation algorithm that helps the user find relevant items and thus increase the user’s engagement. However, several drawbacks of CF, especially data sparsity, scalability, and relevance of items recommended to users are open research issues that pose serious challenges to precision of the algorithm. Objective:We proposed a novel Bi-clustering based Memetic Algorithm for Recommender Systems (Bi-MARS) based on the collaborative behavior of memes. Method:Bi-clusters are created for discovering precise and localized neighborhood of the target user. Further, a novel local search to refine similarity values associated with neighborhood users and prediction score function for unrated items are formulated. Results:We evaluated the performance of Bi-MARS on MovieLens dataset of three different sizes. Additionally, results are compared with eight other approaches namely, traditional CF, Probabilistic Latent Semantic Analysis, Non-negative Matrix Factorization, Entropy-based CF, Jaccard Coefficient-based Bi-clustering and Fusion, Combined Bi-clustering and Entropy-based CF (CBE-CF), and evolutionary approaches: Genetic Algorithm based Recommender System and Memetic Algorithm based Recommender System (MARS). Experimental results depict that Bi-MARS outperforms all above-said approaches. The precision of MARS is improved by 66.3% on Movielens dataset of size 100K, which is the most precise algorithm after Bi-MARS among all evolutionary algorithms considered. Further, CPU Time of CBE-CF, which portrays least mean absolute error, among all clustering techniques considered, is improved by 53.8% with Bi-MARS. Conclusion:Bi-MARS generates recommendations by finding the closest similarity vector of the target user, which contributes to the computational accuracy of the algorithm and thus the relevance of items.

A user-knowledge crowdsourcing task assignment model and heuristic algorithm for Expert Knowledge Recommendation Systems

Expert Knowledge Recommendation System (EKRS) is a scientific research assistant system that actively provides experts with the latest domain knowledge according to their professional knowledge background. This paper applies the crowdsourcing task assignment method, taking experts as users and recommending corresponding professional knowledge as tasks. To solve the problems of inaccurate user-knowledge matching and low assignments in EKRS, a user-knowledge task assignment model is established. To maximize the number of global task assignments, the model first applies an improved greedy assignment algorithm to convert the user-knowledge task maximum assignment problem into the maximum weight problem in bipartite graphs. Based on the matching value between a task and a user, a task is assigned to the user with a high matching value. Then, the assigned tasks are sorted with the tree decomposition technique to obtain the optimal task scheduling scheme. The heuristic depth-first search algorithm (DFS+HA) is used to update the boundaries of the heuristic function quickly, and the assignment scheme of the optimal solution can be obtained efficiently through the upper and lower bounds of the search process. Finally, the algorithm was experimentally verified with artificial data sets and the real data extracted from EKRS. The experimental results indicated that the algorithm proposed in this paper can improve the amount of user-knowledge task assignment in EKRS, find the optimal assignment scheme to maximize the number of global task assignments, and improve the search efficiency.

Designing Hybrid Intelligence based Recommendation Algorithms: An Experience through Machine Learning Metaphor

This article presents a summarization of the doctoral thesis which proposes efficient hybrid intelligent algorithms in recommendation systems. Development of effective recommendation algorithms for ensuring quality recommendation in timely manner is a tricky task. Moreover, traditional recommendation system is inadequate to cope up with the new technological trends. In order to overcome these issues, a batch of sophisticated recommendation systems has been discovered e.g. contextual recommendation, group recommendation, and social recommendation. The research work, investigates and analyzes new genres of recommenders using nature inspired algorithms, evolutionary algorithms, swarm intelligence algorithms, and machine learning techniques. The algorithms resolve some crucial problems of these recommenders. As a result, more precise personalized recommendation is ensured.

Capsmf: a novel product recommender system using deep learning based text analysis model

Researchers and data scientists have developed different Recommender System Algorithms such as Content-Based and Collaborative-Based in order to filter a large amount of information available on the internet and hence, recommend only the relevant and essential content based on the personalized interests of users. Information acquired explicitly by collecting users’ ratings for an item lead to the problem of data sparsity. Many researchers have been currently working towards the improvement of rating prediction accuracy by integrating the auxiliary information along with the ratings provided by the users. This paper proposes a novel product recommender system called as “CapsMF”, it applies the advanced neural network architecture Capsule Networks (Caps) for document representation, and MF represents Matrix factorization. In the proposed approach, we have enhanced a deep neural network text analysis model by adding a newly discovered neural network architecture; Capsule Networks stacked on bi-directional Recurrent Neural Network (Bi-RNN) for the robust representation of textual descriptions of items and users. The Deep Neural Network text analysis model is integrated with the Probabilistic Matrix Factorization to generate improved recommendations. The experiment has been performed on two real amazon datasets resulting in the enhancement of rating prediction accuracy, the recall, and the precision of top-n recommendations, in comparison to the basic and hybrid Recommendation System Algorithms. Also, text analysis model involving Capsule Networks stacked with Recurrent Neural Networks (RNNs) have outperformed the baseline models that have single Convolutional Neural Networks (CNN) or CNN combined with Bi-RNN in text analysis.

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.

P-MOIA-RS: a multi-objective optimization and decision-making algorithm for recommendation systems

Besides accuracy, diversity of recommendation list is also important for users. Hence, the optimization of the recommendation system can be abstracted as a multi-objective problem because accuracy and diversity are contradictory goals. Available multi-objective optimization based recommendation schemes return the Pareto set for the target users. However, the scale of Pareto solutions is uncontrollable. If a Pareto set contains too many solutions, it will not be quite useful for users to make the final decision. In this paper, multi-objective immune algorithm is used to improve recommendation accuracy and diversity, then we can get the pareto set. Further, we introduce PROMETHEE into the recommendation system to get a more precise evaluation of Pareto solutions. By combining PROMETHEE with Pareto, we redefine recommendation as Top-n PROMETHEE Pareto optimization problem and a multi-objective immune optimization and decision-making algorithm is presented. The experimental results show that the proposed algorithm, compared with other existing algorithms, can generate more diverse and accurate recommendation list and provide more precise decision-making for the user.

Automated Product Recommendations with Preference-Based Explanations

Many online retailers, such as Amazon, use automated product recommender systems to encourage customer loyalty and cross-sell products. Despite significant improvements to the predictive accuracy of contemporary recommender system algorithms, they remain prone to errors. Erroneous recommendations pose potential threats to online retailers in particular, because they diminish customers’ trust in, acceptance of, satisfaction with, and loyalty to a recommender system. Explanations of the reasoning that lead to recommendations might mitigate these negative effects. That is, a recommendation algorithm ideally would provide both accurate recommendations and explanations of the reasoning for those recommendations. This article proposes a novel method to balance these concurrent objectives. The application of this method, using a combination of content-based and collaborative filtering, to two real-world data sets with more than 100 million product ratings reveals that the proposed method outperforms established recommender approaches in terms of predictive accuracy (more than five percent better than the Netflix Prize winner algorithm according to normalized root mean squared error) and its ability to provide actionable explanations, which is also an ethical requirement of artificial intelligence systems.

Social recommender systems: techniques, domains, metrics, datasets and future scope

With the evolution of social media, an enormous amount of information is shared every day. Recommender systems contribute significantly in handling big data and presenting relevant information, services and items to people. A substantial number of recommender system algorithms based on social media data have been proposed and applied to numerous domains in the literature. This paper presents a state-of-the-art survey of existing techniques of social recommender systems. We present different domains where the existing systems have been experimented. We also present a tabular representation of different metrics used by these papers. We discuss some frequently used datasets of these systems. Lastly, we discuss some of the future works in this area. The main aim of this paper is to provide a concise review of published papers to assist potential researchers in this field to devise new techniques.

High Order Profile Expansion to tackle the new user problem on recommender systems.

Collaborative Filtering algorithms provide users with recommendations based on their opinions, that is, on the ratings given by the user for some items. They are the most popular and widely implemented algorithms in Recommender Systems, especially in e-commerce, considering their good results. However, when the information is extremely sparse, independently of the domain nature, they do not present such good results. In particular, it is difficult to offer recommendations which are accurate enough to a user who has just arrived to a system or who has rated few items. This is the well-known new user problem, a type of cold-start. Profile Expansion techniques had been already presented as a method to alleviate this situation. These techniques increase the size of the user profile, by obtaining information about user tastes in distinct ways. Therefore, recommender algorithms have more information at their disposal, and results improve. In this paper, we present the High Order Profile Expansion techniques, which combine in different ways the Profile Expansion methods. The results show 110% improvement in precision over the algorithm without Profile Expansion, and 10% improvement over Profile Expansion techniques.

Extracting Subset of Relevant Features for Breast Cancer to Improve Accuracy of Classifier

Data mining is the essential step which identifies hidden patterns from large repositories. Medical diagnosis became a major area of current research in data mining. Machine learning technique which use statistical methods to enable machine to improve with experiences and identify hidden patterns in data like regression algorithms, clustering algorithms, classification algorithms, neural networks(ANN,CNN,DL),recommender system algorithms, Apriori algorithms, page ranking algorithms, text search and NLP(natural language processing) etc.., but due to lack of evaluation, these algorithms are unsuccessful in finding a better classifier for images to estimate accuracy of classification in medical image processing. Classification is an supervised learning which predicts the future class for an unknown object. The main purpose is to identify an unknown class by consulting with the neighbor class characteristics. Clustering can be known as unsupervised learning as it label the objects based on the scale of similar characteristics without consulting its class label. Main principle of clustering is find the distance like nearby and faraway based on their similarities and dissimilarities and groups the objects and hence can be used to identify outliers (which are far away from from the object). Feature extraction, variable selection is a method of obtaining a subset of relevant characteristics from large dataset. Too many features of a class may affect the accuracy of classifier. Therefore, feature extraction technique can be used to eliminate irrelevant attributes and increases the accuracy of classifier. In this paper we performed an induction to increase the accuracy of classifier by applying mining techniques in WEKA tool. Breast Cancer dataset is chosen from learning repository to analyze and an experimental analysis was conducted with WEKA tool using training dataset by applying naïve bayes, bayesnet, and PART, ZeroR, J48 and Random Forest techniques on the Wisconsin's dataset on Breast cancer. Finally presented the best classifier where the accuracy is more

Predicting circRNA-Disease Associations Based on Improved Collaboration Filtering Recommendation System With Multiple Data.

With the development of high-throughput techniques, various biological molecules are discovered, which includes the circular RNAs (circRNAs). Circular RNA is a novel endogenous noncoding RNA that plays significant roles in regulating gene expression, moderating the microRNAs transcription as sponges, diagnosing diseases, and so on. Based on the circRNA particular molecular structures that are closed-loop structures with neither 5′-3′ polarities nor polyadenylated tails, circRNAs are more stable and conservative than the normal linear coding or noncoding RNAs, which makes circRNAs a biomarker of various diseases. Although some conventional experiments are used to identify the associations between circRNAs and diseases, almost the techniques and experiments are time-consuming and expensive. In this study, we propose a collaboration filtering recommendation system–based computational method, which handles the “cold start” problem to predict the potential circRNA–disease associations, which is named ICFCDA. All the known circRNA–disease associations data are downloaded from circR2Disease database (http://bioinfo.snnu.edu.cn/CircR2Disease/). Based on these data, multiple data are extracted from different databases to calculate the circRNA similarity networks and the disease similarity networks. The collaboration filtering recommendation system algorithm is first employed to predict circRNA–disease associations. Then, the leave-one-out cross validation mechanism is adopted to measure the performance of our proposed computational method. ICFCDA achieves the areas under the curve of 0.946, which is better than other existing methods. In order to further illustrate the performance of ICFCDA, case studies of some common diseases are made, and the results are confirmed by other databases. The experimental results show that ICFCDA is competent in predicting the circRNA–disease associations.

Genomic Biomarkers to Predict Resistance to Hypomethylating Agents in Patients With Myelodysplastic Syndromes Using Artificial Intelligence.

PURPOSEWe developed an unbiased framework to study the association of several mutations in predicting resistance to hypomethylating agents (HMAs) in patients with myelodysplastic syndromes (MDS), analogous to consumer and commercial recommender systems in which customers who bought products A and B are likely to buy C: patients who have a mutation in gene A and gene B are likely to respond or not respond to HMAs.METHODSWe screened a cohort of 433 patients with MDS who received HMAs for the presence of common myeloid mutations in 29 genes that were obtained before the patients started therapy. The association between mutations and response was evaluated by the Apriori market basket analysis algorithm. Rules with the highest confidence (confidence that the association exists) and the highest lift (strength of the association) were chosen. We validated our biomarkers in samples from patients enrolled in the S1117 trial.RESULTSAmong 433 patients, 193 (45%) received azacitidine, 176 (40%) received decitabine, and 64 (15%) received HMA alone or in combination. The median age was 70 years (range, 31 to 100 years), and 28% were female. The median number of mutations per sample was three (range, zero to nine), and 176 patients (41%) had three or more mutations per sample. Association rules identified several genomic combinations as being highly associated with no response. These molecular signatures were present in 30% of patients with three or more mutations/sample with an accuracy rate of 87% in the training cohort and 93% in the validation cohort.CONCLUSIONGenomic biomarkers can identify, with high accuracy, approximately one third of patients with MDS who will not respond to HMAs. This study highlights the importance of machine learning technologies such as the recommender system algorithm in translating genomic data into useful clinical tools.

COMPUTER MODEL OF VIRTUAL SOCIAL NETWORK WITH RECOMMENDATION SYSTEM

The subject matter of the article is the process of modeling social networks. The goal is to develop a computer model of a social network with a recommendation system. The tasks to be solved are to research the methods of generating social networks, to realize the computer model of a social network with a recommender system. The methods used are graph theory, theory of algorithms, statistics theory, probability theory, object-oriented programming. The following results: the research of existing methods for modeling social networks was conducted, in particular, such social network models as the Barabasi-Albert model, the Erdős-Renyi model and the Bollobаs-Riordan model were considered. The concept of complex networks was considered. The research of the basic properties of graphs of social networks was considered. The social network computer model with a recommender system based on the modified Barabasi-Albert model with using graph database Neo4j and programming language Python was developed. The developed model allows to model a network with users and text posts and may contain following connections friends, follower, published, viewed, like, similar, recommended, and also allows testing of algorithms of recommender systems and conduct research to changes in a social network after creating and proposing recommendations. The testing of the developed computer model of virtual social network with a recommender system was conducted. Conclusions. The research of various methods of modeling social networks was conducted. The concept of complex networks was investigated. The main properties of social network graphs are considered. The computer model of a social network with a recommendation system that contains various types of nodes and connections that allow testing a recommender system algorithm has been developed. The developed model of a social network with a recommender system was tested to check its similarity with real social networks. The developed computer model of a social network has the values of network graph parameters corresponding to the values characteristic of real social networks, which allows using the developed model to research the processes that can occur in real social networks.

DETECTION AND HANDLING OF DIFFERENT TYPES OF CONCEPT DRIFT IN NEWS RECOMMENDATION SYSTEMS

To address the increase in volume of data streams online users interact with, there are a growing number of tools and models to summarize and extract information. These tools use prediction models to personalize and extract useful information. However, data streams are highly prone to the phenomena of concept drift, in which the data distribution changes over time. To maintain the performance level of these models, models should adapt to handle the existence of adrift. In this work, we present the Incremental Knowledge Concept Drift (IKCD) algorithm, an adaptive unsupervised learning algorithm for recommendation systems in news data stream. Data modelling in IKCD uses k-means clustering to determine the occurrence of a drift while avoiding the dependency on the availability of data labels. Once a drift is detected, new retraining data is composed from the old and new concept. IKCD is tested using synthetic and real benchmark datasets from various domains, which demonstrate the different drift types and with different rate of change. Experimental results illustrate an enhanced performance with respect to (a) reducing model sensitivity to noise, (b) reducing model rebuilding frequency up to 50% in case of re-occurring drift and (c) increasing accuracy of the model by about 10% with respect the accuracy of confidence distribution batch detection algorithm.

Collaborative Filtering Based on Gaussian Mixture Model and Improved Jaccard Similarity

The recommender systems play an important role in our lives, since it can quickly help users find what they are interested in. Collaborative filtering has become one of the most widely used algorithms in recommender systems due to its simplicity and efficiency. However, when the user's rating data is sparse, the accuracy of the collaborative filtering algorithm for predictive rating is badly reduced. In addition, the similarity calculation method is another important factor that affects the accuracy of the collaborative filtering algorithm recommendation. Faced with these problems, we propose a new collaborative filtering algorithm which based on Gaussian mixture model and improved Jaccard similarity. The proposed model uses Gaussian mixture model to cluster users and items respectively and extracts new features to build a new interaction matrix, which effectively solves the impact of rating data sparsity on collaborative filtering algorithms. Meanwhile, a new similarity calculation method is proposed, which is combined by triangle similarity and Jaccard similarity. Compare our proposed model with four models based on collaborative filtering algorithms on three public datasets. The experimental results show that the proposed model not only mitigates the sparseness of the data, but also improves the accuracy of the rating prediction.