Showing papers on "Recommender system published in 2015"

Collaborative Deep Learning for Recommender Systems

Abstract: Collaborative filtering (CF) is a successful approach commonly used by many recommender systems. Conventional CF-based methods use the ratings given to items by users as the sole source of information for learning to make recommendation. However, the ratings are often very sparse in many applications, causing CF-based methods to degrade significantly in their recommendation performance. To address this sparsity problem, auxiliary information such as item content information may be utilized. Collaborative topic regression (CTR) is an appealing recent method taking this approach which tightly couples the two components that learn from two different sources of information. Nevertheless, the latent representation learned by CTR may not be very effective when the auxiliary information is very sparse. To address this problem, we generalize recently advances in deep learning from i.i.d. input to non-i.i.d. (CF-based) input and propose in this paper a hierarchical Bayesian model called collaborative deep learning (CDL), which jointly performs deep representation learning for the content information and collaborative filtering for the ratings (feedback) matrix. Extensive experiments on three real-world datasets from different domains show that CDL can significantly advance the state of the art.

Recommender system application developments

Abstract: A recommender system aims to provide users with personalized online product or service recommendations to handle the increasing online information overload problem and improve customer relationship management. Various recommender system techniques have been proposed since the mid-1990s, and many sorts of recommender system software have been developed recently for a variety of applications. Researchers and managers recognize that recommender systems offer great opportunities and challenges for business, government, education, and other domains, with more recent successful developments of recommender systems for real-world applications becoming apparent. It is thus vital that a high quality, instructive review of current trends should be conducted, not only of the theoretical research results but more importantly of the practical developments in recommender systems. This paper therefore reviews up-to-date application developments of recommender systems, clusters their applications into eight main categories: e-government, e-business, e-commerce/e-shopping, e-library, e-learning, e-tourism, e-resource services and e-group activities, and summarizes the related recommendation techniques used in each category. It systematically examines the reported recommender systems through four dimensions: recommendation methods (such as CF), recommender systems software (such as BizSeeker), real-world application domains (such as e-business) and application platforms (such as mobile-based platforms). Some significant new topics are identified and listed as new directions. By providing a state-of-the-art knowledge, this survey will directly support researchers and practical professionals in their understanding of developments in recommender system applications. Research papers on various recommender system applications are summarized.The recommender systems are examined systematically through four dimensions.The recommender system applications are classified into eight categories.Related recommendation techniques in each category are identified.Several new recommendation techniques and application areas are uncovered.

AutoRec: Autoencoders Meet Collaborative Filtering

Abstract: This paper proposes AutoRec, a novel autoencoder framework for collaborative filtering (CF). Empirically, AutoRec's compact and efficiently trainable model outperforms state-of-the-art CF techniques (biased matrix factorization, RBM-CF and LLORMA) on the Movielens and Netflix datasets.

Session-based Recommendations with Recurrent Neural Networks

Abstract: We apply recurrent neural networks (RNN) on a new domain, namely recommender systems. Real-life recommender systems often face the problem of having to base recommendations only on short session-based data (e.g. a small sportsware website) instead of long user histories (as in the case of Netflix). In this situation the frequently praised matrix factorization approaches are not accurate. This problem is usually overcome in practice by resorting to item-to-item recommendations, i.e. recommending similar items. We argue that by modeling the whole session, more accurate recommendations can be provided. We therefore propose an RNN-based approach for session-based recommendations. Our approach also considers practical aspects of the task and introduces several modifications to classic RNNs such as a ranking loss function that make it more viable for this specific problem. Experimental results on two data-sets show marked improvements over widely used approaches.

The Netflix Recommender System: Algorithms, Business Value, and Innovation

Abstract: This article discusses the various algorithms that make up the Netflix recommender system, and describes its business purpose. We also describe the role of search and related algorithms, which for us turns into a recommendations problem as well. We explain the motivations behind and review the approach that we use to improve the recommendation algorithms, combining A/B testing focused on improving member retention and medium term engagement, as well as offline experimentation using historical member engagement data. We discuss some of the issues in designing and interpreting A/B tests. Finally, we describe some current areas of focused innovation, which include making our recommender system global and language aware.

Recommender Systems: Introduction and Challenges

Abstract: Recommender Systems (RSs) are software tools and techniques that provide suggestions for items that are most likely of interest to a particular user. In this introductory chapter, we briefly discuss basic RS ideas and concepts. Our main goal is to delineate, in a coherent and structured way, the chapters included in this handbook. Additionally, we aim to help the reader navigate the rich and detailed content that this handbook offers.

A Comprehensive Survey of Neighborhood-based Recommendation Methods

Abstract: Among collaborative recommendation approaches, methods based on nearest-neighbors still enjoy a huge amount of popularity, due to their simplicity, their efficiency, and their ability to produce accurate and personalized recommendations. This chapter presents a comprehensive survey of neighborhood-based methods for the item recommendation problem. In particular, the main benefits of such methods, as well as their principal characteristics, are described. Furthermore, this document addresses the essential decisions that are required while implementing a neighborhood-based recommender system, and gives practical information on how to make such decisions. Finally, the problems of sparsity and limited coverage, often observed in large commercial recommender systems, are discussed, and a few solutions to overcome these problems are presented.

A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems

Abstract: Recent online services rely heavily on automatic personalization to recommend relevant content to a large number of users. This requires systems to scale promptly to accommodate the stream of new users visiting the online services for the first time. In this work, we propose a content-based recommendation system to address both the recommendation quality and the system scalability. We propose to use a rich feature set to represent users, according to their web browsing history and search queries. We use a Deep Learning approach to map users and items to a latent space where the similarity between users and their preferred items is maximized. We extend the model to jointly learn from features of items from different domains and user features by introducing a multi-view Deep Learning model. We show how to make this rich-feature based user representation scalable by reducing the dimension of the inputs and the amount of training data. The rich user feature representation allows the model to learn relevant user behavior patterns and give useful recommendations for users who do not have any interaction with the service, given that they have adequate search and browsing history. The combination of different domains into a single model for learning helps improve the recommendation quality across all the domains, as well as having a more compact and a semantically richer user latent feature vector. We experiment with our approach on three real-world recommendation systems acquired from different sources of Microsoft products: Windows Apps recommendation, News recommendation, and Movie/TV recommendation. Results indicate that our approach is significantly better than the state-of-the-art algorithms (up to 49% enhancement on existing users and 115% enhancement on new users). In addition, experiments on a publicly open data set also indicate the superiority of our method in comparison with transitional generative topic models, for modeling cross-domain recommender systems. Scalability analysis show that our multi-view DNN model can easily scale to encompass millions of users and billions of item entries. Experimental results also confirm that combining features from all domains produces much better performance than building separate models for each domain.

Recommendations in location-based social networks: a survey

Abstract: Recent advances in localization techniques have fundamentally enhanced social networking services, allowing users to share their locations and location-related contents, such as geo-tagged photos and notes. We refer to these social networks as location-based social networks (LBSNs). Location data bridges the gap between the physical and digital worlds and enables a deeper understanding of users' preferences and behavior. This addition of vast geo-spatial datasets has stimulated research into novel recommender systems that seek to facilitate users' travels and social interactions. In this paper, we offer a systematic review of this research, summarizing the contributions of individual efforts and exploring their relations. We discuss the new properties and challenges that location brings to recommender systems for LBSNs. We present a comprehensive survey analyzing 1) the data source used, 2) the methodology employed to generate a recommendation, and 3) the objective of the recommendation. We propose three taxonomies that partition the recommender systems according to the properties listed above. First, we categorize the recommender systems by the objective of the recommendation, which can include locations, users, activities, or social media. Second, we categorize the recommender systems by the methodologies employed, including content-based, link analysis-based, and collaborative filtering-based methodologies. Third, we categorize the systems by the data sources used, including user profiles, user online histories, and user location histories. For each category, we summarize the goals and contributions of each system and highlight the representative research effort. Further, we provide comparative analysis of the recommender systems within each category. Finally, we discuss the available data-sets and the popular methods used to evaluate the performance of recommender systems. Finally, we point out promising research topics for future work. This article presents a panorama of the recommender systems in location-based social networks with a balanced depth, facilitating research into this important research theme.

TrustSVD: collaborative filtering with both the explicit and implicit influence of user trust and of item ratings

Abstract: Collaborative filtering suffers from the problems of data sparsity and cold start, which dramatically degrade recommendation performance. To help resolve these issues, we propose TrustSVD, a trust-based matrix factorization technique. By analyzing the social trust data from four real-world data sets, we conclude that not only the explicit but also the implicit influence of both ratings and trust should be taken into consideration in a recommendation model. Hence, we build on top of a state-of-the-art recommendation algorithm SVD++ which inherently involves the explicit and implicit influence of rated items, by further incorporating both the explicit and implicit influence of trusted users on the prediction of items for an active user. To our knowledge, the work reported is the first to extend SVD++ with social trust information. Experimental results on the four data sets demonstrate that our approach TrustSVD achieves better accuracy than other ten counterparts, and can better handle the concerned issues.

TriRank: Review-aware Explainable Recommendation by Modeling Aspects

Abstract: Most existing collaborative filtering techniques have focused on modeling the binary relation of users to items by extracting from user ratings. Aside from users' ratings, their affiliated reviews often provide the rationale for their ratings and identify what aspects of the item they cared most about. We explore the rich evidence source of aspects in user reviews to improve top-N recommendation. By extracting aspects (i.e., the specific properties of items) from textual reviews, we enrich the user--item binary relation to a user--item--aspect ternary relation. We model the ternary relation as a heterogeneous tripartite graph, casting the recommendation task as one of vertex ranking. We devise a generic algorithm for ranking on tripartite graphs -- TriRank -- and specialize it for personalized recommendation. Experiments on two public review datasets show that it consistently outperforms state-of-the-art methods. Most importantly, TriRank endows the recommender system with a higher degree of explainability and transparency by modeling aspects in reviews. It allows users to interact with the system through their aspect preferences, assisting users in making informed decisions.

Deep Collaborative Filtering via Marginalized Denoising Auto-encoder

Abstract: Collaborative filtering (CF) has been widely employed within recommender systems to solve many real-world problems. Learning effective latent factors plays the most important role in collaborative filtering. Traditional CF methods based upon matrix factorization techniques learn the latent factors from the user-item ratings and suffer from the cold start problem as well as the sparsity problem. Some improved CF methods enrich the priors on the latent factors by incorporating side information as regularization. However, the learned latent factors may not be very effective due to the sparse nature of the ratings and the side information. To tackle this problem, we learn effective latent representations via deep learning. Deep learning models have emerged as very appealing in learning effective representations in many applications. In particular, we propose a general deep architecture for CF by integrating matrix factorization with deep feature learning. We provide a natural instantiations of our architecture by combining probabilistic matrix factorization with marginalized denoising stacked auto-encoders. The combined framework leads to a parsimonious fit over the latent features as indicated by its improved performance in comparison to prior state-of-art models over four large datasets for the tasks of movie/book recommendation and response prediction.

The Use of Machine Learning Algorithms in Recommender Systems: A Systematic Review

Abstract: Recommender systems use algorithms to provide users with product or service recommendations. Recently, these systems have been using machine learning algorithms from the field of artificial intelligence. However, choosing a suitable machine learning algorithm for a recommender system is difficult because of the number of algorithms described in the literature. Researchers and practitioners developing recommender systems are left with little information about the current approaches in algorithm usage. Moreover, the development of a recommender system using a machine learning algorithm often has problems and open questions that must be evaluated, so software engineers know where to focus research efforts. This paper presents a systematic review of the literature that analyzes the use of machine learning algorithms in recommender systems and identifies research opportunities for software engineering research. The study concludes that Bayesian and decision tree algorithms are widely used in recommender systems because of their relative simplicity, and that requirement and design phases of recommender system development appear to offer opportunities for further research.

Recommender systems based on user reviews: the state of the art

Abstract: In recent years, a variety of review-based recommender systems have been developed, with the goal of incorporating the valuable information in user-generated textual reviews into the user modeling and recommending process. Advanced text analysis and opinion mining techniques enable the extraction of various types of review elements, such as the discussed topics, the multi-faceted nature of opinions, contextual information, comparative opinions, and reviewers' emotions. In this article, we provide a comprehensive overview of how the review elements have been exploited to improve standard content-based recommending, collaborative filtering, and preference-based product ranking techniques. The review-based recommender system's ability to alleviate the well-known rating sparsity and cold-start problems is emphasized. This survey classifies state-of-the-art studies into two principal branches: review-based user profile building and review-based product profile building. In the user profile sub-branch, the reviews are not only used to create term-based profiles, but also to infer or enhance ratings. Multi-faceted opinions can further be exploited to derive the weight/value preferences that users place on particular features. In another sub-branch, the product profile can be enriched with feature opinions or comparative opinions to better reflect its assessment quality. The merit of each branch of work is discussed in terms of both algorithm development and the way in which the proposed algorithms are evaluated. In addition, we discuss several future trends based on the survey, which may inspire investigators to pursue additional studies in this area.

Social Network and Tag Sources Based Augmenting Collaborative Recommender System

Abstract: Recommender systems, which provide users with recommendations of content suited to their needs, have received great attention in today’s online business world. However, most recommendation approaches exploit only a single source of input data and suffer from the data sparsity problem and the cold start problem. To improve recommendation accuracy in this situation, additional sources of information, such as friend relationship and user-generated tags, should be incorporated in recommendation systems. In this paper, we revise the user-based collaborative filtering (CF) technique, and propose two recommendation approaches fusing usergenerated tags and social relations in a novel way. In order to evaluate the performance of our approaches, we compare experimental results with two baseline methods: user-based CF and user-based CF with weighted friendship similarity using the real datasets (Last.fm and Movielens). Our experimental results show that our methods get higher accuracy. We also verify our methods in cold-start settings, and our methods achieve more precise recommendations than the compared approaches. key words: recommender system, collaborative filtering, social tagging, social network

Multi-Criteria Recommender Systems

Abstract: This chapter aims to provide an overview of the class of multi-criteria recommender systems, i.e., the category of recommender systems that use multi-criteria preference ratings. Traditionally, the vast majority of recommender systems literature has focused on providing recommendations by modelling a user’s utility (or preference) for an item as a single preference rating. However, where possible, capturing richer user preferences along several dimensions—for example, capturing not only the user’s overall preference for a given movie but also her preferences for specific movie aspects (such as acting, story, or visual effects)—can provide opportunities for further improvements in recommendation quality. As a result, a number of recommendation techniques that attempt to take advantage of such multi-criteria preference information have been developed in recent years. A review of current algorithms that use multi-criteria ratings for calculating predictions and generating recommendations is provided. The chapter concludes with a discussion on open issues and future challenges for the class of multi-criteria rating recommenders.

Semantic Path based Personalized Recommendation on Weighted Heterogeneous Information Networks

Abstract: Recently heterogeneous information network (HIN) analysis has attracted a lot of attention, and many data mining tasks have been exploited on HIN. As an important data mining task, recommender system includes a lot of object types (e.g., users, movies, actors, and interest groups in movie recommendation) and the rich relations among object types, which naturally constitute a HIN. The comprehensive information integration and rich semantic information of HIN make it promising to generate better recommendations. However, conventional HINs do not consider the attribute values on links, and the widely used meta path in HIN may fail to accurately capture semantic relations among objects, due to the existence of rating scores (usually ranging from 1 to 5) between users and items in recommender system. In this paper, we are the first to propose the weighted HIN and weighted meta path concepts to subtly depict the path semantics through distinguishing different link attribute values. Furthermore, we propose a semantic path based personalized recommendation method SemRec to predict the rating scores of users on items. Through setting meta paths, SemRec not only flexibly integrates heterogeneous information but also obtains prioritized and personalized weights representing user preferences on paths. Experiments on two real datasets illustrate that SemRec achieves better recommendation performance through flexibly integrating information with the help of weighted meta paths.

Novelty and Diversity in Recommender Systems

Abstract: Novelty and diversity have been identified, along with accuracy, as foremost properties of useful recommendations. Considerable progress has been made in the field in terms of the definition of methods to enhance such properties, as well as methodologies and metrics to assess how well such methods work. In this chapter we give an overview of the main contributions to this area in the field of recommender systems, and seek to relate them together in a unified view, analyzing the common elements underneath the different forms under which novelty and diversity have been addressed, and identifying connections to closely related work on diversity in other fields.

Explaining Recommendations: Design and Evaluation

Abstract: This chapter gives an overview of the area of explanations in recommender systems. We approach the literature from the angle of evaluation: that is, we are interested in what makes an explanation “good”. The chapter starts by describing how explanations can be affected by how recommendations are presented, and the role the interaction with the recommender system plays w.r.t. explanations. Next, we introduce a number of explanation styles, and how they are related to the underlying algorithms. We identify seven benefits that explanations may contribute to a recommender system, and relate them to criteria used in evaluations of explanations in existing recommender systems. We conclude the chapter with outstanding research questions and future work, including current recommender systems topics such as social recommendations and serendipity. Examples of explanations in existing systems are mentioned throughout.

Evaluating Recommender Systems

Abstract: Recommender systems are now popular both commercially and in the research community, where many approaches have been suggested for providing recommendations. In many cases a system designer that wishes to employ a recommendater system must choose between a set of candidate approaches. A first step towards selecting an appropriate algorithm is to decide which properties of the application to focus upon when making this choice. Indeed, recommender systems have a variety of properties that may affect user experience, such as accuracy, robustness, scalability, and so forth. In this paper we discuss how to compare recommenders based on a set of properties that are relevant for the application. We focus on comparative studies, where a few algorithms are compared using some evaluation metric, rather than absolute benchmarking of algorithms. We describe experimental settings appropriate for making choices between algorithms. We review three types of experiments, starting with an offline setting, where recommendation approaches are compared without user interaction, then reviewing user studies, where a small group of subjects experiment with the system and report on the experience, and finally describe large scale online experiments, where real user populations interact with the system. In each of these cases we describe types of questions that can be answered, and suggest protocols for experimentation. We also discuss how to draw trustworthy conclusions from the conducted experiments. We then review a large set of properties, and explain how to evaluate systems given relevant properties. We also survey a large set of evaluation metrics in the context of the property that they evaluate.

Friendbook: A Semantic-Based Friend Recommendation System for Social Networks

Abstract: Existing social networking services recommend friends to users based on their social graphs, which may not be the most appropriate to reflect a user’s preferences on friend selection in real life. In this paper, we present Friendbook, a novel semantic-based friend recommendation system for social networks, which recommends friends to users based on their life styles instead of social graphs. By taking advantage of sensor-rich smartphones, Friendbook discovers life styles of users from user-centric sensor data, measures the similarity of life styles between users, and recommends friends to users if their life styles have high similarity. Inspired by text mining, we model a user’s daily life as life documents , from which his/her life styles are extracted by using the Latent Dirichlet Allocation algorithm. We further propose a similarity metric to measure the similarity of life styles between users, and calculate users’ impact in terms of life styles with a friend-matching graph . Upon receiving a request, Friendbook returns a list of people with highest recommendation scores to the query user. Finally, Friendbook integrates a feedback mechanism to further improve the recommendation accuracy. We have implemented Friendbook on the Android-based smartphones, and evaluated its performance on both small-scale experiments and large-scale simulations. The results show that the recommendations accurately reflect the preferences of users in choosing friends.

MyBehavior: automatic personalized health feedback from user behaviors and preferences using smartphones

Abstract: Mobile sensing systems have made significant advances in tracking human behavior. However, the development of personalized mobile health feedback systems is still in its infancy. This paper introduces MyBehavior, a smartphone application that takes a novel approach to generate deeply personalized health feedback. It combines state-of-the-art behavior tracking with algorithms that are used in recommendation systems. MyBehavior automatically learns a user's physical activity and dietary behavior and strategically suggests changes to those behaviors for a healthier lifestyle. The system uses a sequential decision making algorithm, Multi-armed Bandit, to generate suggestions that maximize calorie loss and are easy for the user to adopt. In addition, the system takes into account user's preferences to encourage adoption using the pareto-frontier algorithm. In a 14-week study, results show statistically significant increases in physical activity and decreases in food calorie when using MyBehavior compared to a control condition.

A new similarity measure using Bhattacharyya coefficient for collaborative filtering in sparse data

Abstract: Collaborative filtering (CF) is the most successful approach for personalized product or service recommendations Neighborhood based collaborative filtering is an important class of CF, which is simple, intuitive and efficient product recommender system widely used in commercial domain Typically, neighborhood-based CF uses a similarity measure for finding similar users to an active user or similar products on which she rated Traditional similarity measures utilize ratings of only co-rated items while computing similarity between a pair of users Therefore, these measures are not suitable in a sparse data In this paper, we propose a similarity measure for neighborhood based CF, which uses all ratings made by a pair of users Proposed measure finds importance of each pair of rated items by exploiting Bhattacharyya similarity To show effectiveness of the measure, we compared performances of neighborhood based CFs using state-of-the-art similarity measures with the proposed measured based CF Recommendation results on a set of real data show that proposed measure based CF outperforms existing measures based CFs in various evaluation metrics

Author Topic Model-Based Collaborative Filtering for Personalized POI Recommendations

Abstract: From social media has emerged continuous needs for automatic travel recommendations. Collaborative filtering (CF) is the most well-known approach. However, existing approaches generally suffer from various weaknesses. For example , sparsity can significantly degrade the performance of traditional CF. If a user only visits very few locations, accurate similar user identification becomes very challenging due to lack of sufficient information for effective inference. Moreover, existing recommendation approaches often ignore rich user information like textual descriptions of photos which can reflect users’ travel preferences. The topic model (TM) method is an effective way to solve the “sparsity problem,” but is still far from satisfactory. In this paper, an author topic model-based collaborative filtering (ATCF) method is proposed to facilitate comprehensive points of interest (POIs) recommendations for social users. In our approach, user preference topics, such as cultural, cityscape, or landmark, are extracted from the geo-tag constrained textual description of photos via the author topic model instead of only from the geo-tags (GPS locations). Advantages and superior performance of our approach are demonstrated by extensive experiments on a large collection of data.

Panorama of Recommender Systems to Support Learning

Abstract: This chapter presents an analysis of recommender systems in Technology-Enhanced Learning along their 15 years existence (2000–2014). All recommender systems considered for the review aim to support educational stakeholders by personalising the learning process. In this meta-review 82 recommender systems from 35 different countries have been investigated and categorised according to a given classification framework. The reviewed systems have been classified into seven clusters according to their characteristics and analysed for their contribution to the evolution of the RecSysTEL research field. Current challenges have been identified to lead the work of the forthcoming years.

Librec: a Java library for recommender systems

Abstract: The large array of recommendation algorithms proposed over the years brings a challenge in reproducing and comparing their performance. This paper introduces an open-source Java library that implements a suite of state-of-the-art algorithms as well as a series of evaluation metrics. We empirically find that LibRec performs faster than other such libraries, while achieving competitive evaluative performance.

What recommenders recommend: an analysis of recommendation biases and possible countermeasures

Abstract: Most real-world recommender systems are deployed in a commercial context or designed to represent a value-adding service, eg, on shopping or Social Web platforms, and typical success indicators for such systems include conversion rates, customer loyalty or sales numbers In academic research, in contrast, the evaluation and comparison of different recommendation algorithms is mostly based on offline experimental designs and accuracy or rank measures which are used as proxies to assess an algorithm's recommendation quality In this paper, we show that popular recommendation techniques--despite often being similar when compared with the help of accuracy measures--can be quite different with respect to which items they recommend We report the results of an in-depth analysis in which we compare several recommendations strategies from different perspectives, including accuracy, catalog coverage and their bias to recommend popular items Our analyses reveal that some recent techniques that perform well with respect to accuracy measures focus their recommendations on a tiny fraction of the item spectrum or recommend mostly top sellers We analyze the reasons for some of these biases in terms of algorithmic design and parameterization and show how the characteristics of the recommendations can be altered by hyperparameter tuning Finally, we propose two novel algorithmic schemes to counter these popularity biases

Semantics-Aware Content-Based Recommender Systems.

Abstract: Content-based recommender systems (CBRSs) rely on item and user descriptions (content) to build item representations and user profiles that can be effectively exploited to suggest items similar to those a target user already liked in the past. Most content-based recommender systems use textual features to represent items and user profiles, hence they suffer from the classical problems of natural language ambiguity. This chapter presents a comprehensive survey of semantic representations of items and user profiles that attempt to overcome the main problems of the simpler approaches based on keywords. We propose a classification of semantic approaches into top-down and bottom-up. The former rely on the integration of external knowledge sources, such as ontologies, encyclopedic knowledge and data from the Linked Data cloud, while the latter rely on a lightweight semantic representation based on the hypothesis that the meaning of words depends on their use in large corpora of textual documents. The chapter shows how to make recommender systems aware of semantics to realize a new generation of content-based recommenders.