Utility elicitation is an important component of many applications, such as decision support systems and recommender systems. Such systems query users about their preferences and offer recommendations based on the system's belief about the user's utility function. We analyze the connection between the problem of generating optimal recommendation sets and the problem of generating optimal choice queries, considering both Bayesian and regret-based elicitation. Our results show that, somewhat surprisingly, under very general circumstances, the optimal recommendation set coincides with the optimal query.

Advanced e-applications require comprehensive knowledge about their users’ preferences in order to provide accurate personalized services. In this paper, we propose to learn users’ preferences to product brands from their implicit feedbacks such as their searching and browsing behaviors in user Web browsing log data. The user brand preference learning problem is challenge since (1) the users’ implicit feedbacks are extremely sparse in various product domains; and (2) we can only observe positive feedbacks from users’ behaviors. In this paper, we propose a latent factor model to collaboratively mine users’ brand preferences across multiple domains simultaneously. By collective learning, the learning processes in all the domains are mutually enhanced and hence the problem of data scarcity in each single domain can be effectively addressed. On the other hand, we learn our model with an adaption of the Bayesian personalized ranking (BPR) optimization criterion which is a general learning framework for collaborative filtering from implicit feedbacks. Experiments with both synthetic and real world datasets show that our proposed model significantly outperforms the baselines.

In real-world recommender systems, some users are easily influenced by new products and whereas others are unwilling to change their minds. So the preference varying speeds for users are different. Based on this observation, we propose a dynamic nonlinear matrix factorization model for collaborative filtering, aimed to improve the rating prediction performance as well as track the preference varying speeds for different users. We assume that user-preference changes smoothly over time, and the preference varying speeds for users are different. These two assumptions are incorporated into the proposed model as prior knowledge on user feature vectors, which can be learned efficiently by MAP estimation. The experimental results show that our method not only achieves state-of-the-art performance in the rating prediction task, but also provides an effective way to track user-preference varying speed.

Fashion magazines contain a number of photographs of fashion models, and their clothing coordinates serve as useful references. In this paper, we propose a recommender system for clothing coordinates using full-body photographs from fashion magazines. The task is that, given a photograph of a fashion item (e.g. tops) as a query, to recommend a photograph of other fashion items (e.g. bottoms) that is appropriate to the query. With the proposed method, we use a probabilistic topic model for learning information about coordinates from visual features in each fashion item region. We demonstrate the effectiveness of the proposed method using real photographs from a fashion magazine and two fashion style sharing services with the task of making top (bottom) recommendations given bottom (top) photographs.

We present a new recommender system for online dating. Using a large dataset from a major online dating website, we first show that similar people, as defined by a set of personal attributes, like and dislike similar people and are liked and disliked by similar people. This analysis provides the foundation for our Content-Collaborative Reciprocal (CCR) recommender approach. The content-based part uses selected user profile features and similarity measure to generate a set of similar users. The collaborative filtering part uses the interactions of the similar users, including the people they like/dislike and are liked/disliked by, to produce reciprocal recommendations. CCR addresses the cold start problem of new users joining the site by being able to provide recommendations immediately, based on their profiles. Evaluation results show that the success rate of the recommendations is 69.26% compared with a baseline of 35.19% for the top 10 ranked recommendations.

Most of the existing personalization systems such as content recommenders or targeted ads focus on individual users and ignore the social situation in which the services are consumed. However, many human activities are social and involve several in-dividuals whose tastes and expectations must be taken into account by the system. When a group profile is not available, different profile aggrega-tion strategies can be applied to recommend ade-quate items to a group of users based on their indi-vidual profiles. We consider an approach intended to determine the factors that influence the choice of an aggregation strategy. We present evaluations made on a large-scale dataset of TV viewings, where real group interests are compared to the pre-dictions obtained by combining individual user profiles according to different strategies.

Recent research has highlighted the benefits of completeness as a retrieval criterion in recommender systems. In complete retrieval, any subset of the constraints in a given query that can be satisfied must be satisfied by at least one of the retrieved products. Minimal completeness (i.e., always retrieving the smallest set of products needed for completeness) is also beginning to attract research interest as a way to minimize cognitive load in the approach. Other important features of a retrieval algorithm’s behavior include the diversity of the retrieved products and the order in which they are presented to the user. In this paper, we present a new algorithm for minimally complete retrieval (MCR) in which the ranking of retrieved products is primarily based on the number of constraints that they satisfy, but other measures such as similarity or utility can also be used to inform the retrieval process. We also present theoretical and empirical results that demonstrate our algorithm’s ability to minimize cognitive load while ensuring the completeness and diversity of the retrieved products.

There are common intuitions about how social graphs are generated (for example, it is common to talk informally about nearby nodes sharing a link). There are also common heuristics for predicting whether two currently unlinked nodes in a graph should be linked (e.g. for suggesting friends in an online social network or movies to customers in a recommendation network). This paper provides what we believe to be the first formal connection between these intuitions and these heuristics. We look at a familiar class of graph generation models in which nodes are associated with locations in a latent metric space and connections are more likely between closer nodes. We also look at popular linkprediction heuristics such as number-of-commonneighbors and its weighted variants [Adamic and Adar, 2003] which have proved successful in predicting missing links, but are not direct derivatives of latent space graph models. We provide theoretical justifications for the success of some measures as compared to others, as reported in previous empirical studies. In particular we present a sequence of formal results that show bounds related to the role that a node’s degree plays in its usefulness for link prediction, the relative importance of short paths versus long paths, and the effects of increasing non-determinism in the link generation process on link prediction quality. Our results can be generalized to any model as long as the latent space assumption holds.

Data sparsity due to missing ratings is a major challenge for collaborative filtering (CF) techniques in recommender systems. This is especially true for CF domains where the ratings are expressed numerically. We observe that, while we may lack the information in numerical ratings, we may have more data in the form of binary ratings.  This is especially true when users can easily express themselves with their likes and dislikes for certain items.  In this paper, we explore how to use the binary preference data expressed in the form of like/dislike to help reduce the impact of data sparsity of more expressive numerical ratings.  We do this by transferring the rating knowledge from some auxiliary data source in binary form (that is, likes or dislikes), to a target numerical rating matrix. Our solution is to model both numerical ratings and like/dislike in a principled way, using a novel framework of Transfer by Collective Factorization (TCF). In particular, we construct the shared latent space collectively and learn the data-dependent effect separately. A major advantage of the TCF approach over previous collective matrix factorization (or bi-factorization) methods is that we are able to capture the data-dependent effect when sharing the data-independent knowledge, so as to increase the overall quality of knowledge transfer. Experimental results demonstrate the effectiveness of TCF at various sparsity levels as compared to several state-of-the-art methods.

Subjective assessments (SAs) are assigned by users against items, such as ’elegant’ and ’gorgeous’, and are common in reviews/tags in many online-sites. However, previous studies fail to effectively use SAs for improving recommendations because few users rate the same items with the same SAs, which triggers the sparsity problem in collaborative filtering. We propose a novel algorithm that links a taxonomy of items to a taxonomy of SAs to assess user interests in detail. That is, it merges the SAs assigned by users against an item into subjective classes (SCs) and reflects the SAs/SCs assigned to an item to its classes. Thus, it can measure the similarity of users from not only SAs/SCs assigned to items but also their classes, which overcomes the sparsity problem. Our evaluation, which uses data from a popular restaurant review site, shows that our method generates more accurate recommendations than previous methods. Furthermore, we find that SAs frequently assigned on a few item classes are more useful than those widely assigned against many item classes in terms of recommendation accuracy.