Many video sites recommend videos related to the one a user is watching. These recommendations have been shown to influence what users end up exploring and are an important part of a recommender system. Plenty of methods have been proposed to recommend related videos, but there has been relatively little work that compares competing strategies. We describe a field study of related video recommendations, where we deploy algorithms to recommend related videos in a movie trailer viewing interface. Our results show that non-personalized algorithms yield the highest click-through rates, while the algorithm prioritizing recency is the strongest in leading to trailer-level user engagement. Our findings suggest the potential to design non-personalized yet effective related item recommendation strategies.

Full text in ACM Digital Library

The overwhelming advances in mobile technologies allow recommender systems to be highly contextualized and able to deliver recommendation without an explicit request. However, it is no longer enough for a recommender system to determine what to recommend according to the users’ needs, but it also has to deal with the risk of disturbing the user during recommendation. We believe that mobile technologies along with contextual information may help alleviate this issue. In this paper, we address intrusiveness as a probabilistic approach that makes use of the several embedded applications within the user’s device and the user’s contextual information in order to figure out intrusive recommendations that are subject to rejection. The experiments that we conducted have shown that the proposed approach yields promising results.

Full text in ACM Digital Library

We propose a multi-modal content-based movie recommender system that replaces human-generated metadata by content descriptions automatically extracted from the visual and audio channels of a video.

Content descriptors improve over traditional metadata in terms of both richness (it is possible to extract hundreds of meaningful features covering various modalities) and quality (content features are consistent across different systems and immune to human errors). Our recommender system integrates state-of-the-art aesthetic and deep visual features as well as block-level and i-vector audio features. For fusing the different modalities, we propose a rank aggregation strategy extending the Borda count approach.

We evaluate the proposed multi-modal recommender system comprehensively against metadata-based baselines. To this end, we conduct two empirical studies: (i) a system-centric study to measure the offline quality of recommendations in terms of accuracy-related and beyond-accuracy performance measures (novelty, diversity, and coverage), and (ii) a user-centric online experiment, measuring different subjective metrics, including relevance, satisfaction, and diversity. In both studies, we use a dataset of more than 4,000 movie trailers, which makes our approach versatile. Our results shed light on the accuracy and beyond-accuracy performance of audio, visual, and textual features in content-based movie recommender systems.

Full text in ACM Digital Library

The location-based social networks (LBSN) (e.g., Facebook.com, etc.) have been explored heavily in the past decade for Point-of-Interest (POI) recommendation. Many of the existing recommenders focus on recommending a single location or an arbitrary list of locations. In this paper, we propose a model termed CLoSe (Contextualized Location Sequence Recommender) that generates contextually coherent POI sequences relevant to user preferences. The POI sequence recommenders are helpful in many day-to-day activities, for e.g., itinerary planning, etc. To the best of our knowledge, this paper is the first to formulate contextual POI sequence recommendation by exploiting Recurrent Neural Network (RNN). We incorporate check-in contexts to the hidden layer and global context to the hidden and output layers of RNN. We also demonstrate the efficiency of extended Long-short term memory (LSTM) in POI sequence generation. The main contributions of this paper are: (i) it exploits multi-context and personalized user preferences to formulate contextual POI sequence generation, (ii) it presents contextual extensions of RNN and LSTM that incorporate different contexts applicable to a POI and POI sequence generation, and (iii) it evaluates the proposed models with two real-world data sets.

Full text in ACM Digital Library

Recommender systems are an important component in the retail industry, but the constantly renewed inventory of many companies makes it di cult to aggregate enough data to fully harness the bene ts of such systems. In this paper, we describe a technique that significantly improves the accuracy of the recommendations, validated on real store transaction history, by performing a time translation that maps out-of-stock items to similar items that are currently in stock using deep features of the products. This reduces greatly the dimension of the item–item interactions matrix while preserving all the dataset entries, which mitigates the sparsity of the dataset, and provides an original solution to the cold-start problem. We also improve the coverage at no accuracy cost by favouring less popular items within a small radius in the feature space while applying the time translation mapping. Finally, by modelling item–item rather that user–item correlations, we are able to update item recommendations for a given user in real-time, without re-training, as the user’s history receives new entries.

Full text in ACM Digital Library

The low-rank structure is one of the most prominent features in modern recommendation problems. In this paper, we consider an online learning problem with a low-rank expected reward matrix where both row features and column features are unknown a priori, and the agent aims to learn to choose the best row-column pair (i.e. the maximum entry) in the matrix. We develop a novel online recommendation algorithm based on ensemble sampling, a recently developed computationally efficient approximation of Thompson sampling. Our computational results show that our algorithm consistently achieves order-of-magnitude improvements over the baselines in both synthetic and real-world experiments.

Full text in ACM Digital Library

For Click-Through Rate (CTR) prediction, Field-aware Factorization Machines (FFM) have exhibited great effectiveness by considering field information. However, it is also observed that FFM suffers from the overfitting problem in many practical scenarios. In this paper, we propose a Field-aware Probabilistic Embedding Neural Network (FPENN) model with both good generalization ability and high accuracy. FPENN estimates the probability distribution of the field-aware embedding rather than using the single point estimation (the maximum a posteriori estimation) to prevent overfitting. Both low-order and high-order feature interactions are considered to improve the accuracy. FPENN consists of three components, i.e., FPE component, Quadratic component and Deep component. FPE component outputs probabilistic embedding to the other two components, where various confidence levels for feature embeddings are incorporated to enhance the robustness and the accuracy. Quadratic component is designed for extracting low-order feature interactions, while Deep component aims at capturing high-order feature interactions. Experiments are conducted on two benchmark datasets, Avazu and Criteo. The results confirm that our model alleviates the overfitting problem while has a higher accuracy.

Full text in ACM Digital Library

Recommender systems are vital ingredients for many e-commerce services. In the literature, two of the most popular approaches are based on factorization and graph-based models; the former approach captures user preferences by factorizing the observed direct interactions between users and items, and the latter extracts indirect preferences from the graphs constructed by user-item interactions. In this paper we present HOP-Rec, a unified and efficient method that incorporates the two approaches. The proposed method involves random surfing on a graph to harvest high-order information among neighborhood items for each user. Instead of factorizing a transition matrix, our method introduces a confidence weighting parameter to simulate all high-order information simultaneously, for which we maintain a sparse user-item interaction matrix and enrich the matrix for each user using random walks. Experimental results show that our approach significantly outperforms the state of the art on a range of large-scale real-world datasets.

Full text in ACM Digital Library

Matrix Factorization (MF) techniques have already shown its strong foundation in collaborative filtering (CF), particularly for rating prediction problem. MF models mainly work as low-rank matrix completion problem by mapping the users and items into same low dimensional latent space. In this direction, now-a-days, a majority of the studies have focused on using additional information such as social network, item tags along with rating to mitigate different issues in the basic recommendation. This results in making the model more complex with a very specific target. However, there are very few studies in recent years which use only users rating information for the recommendation. In this paper, we present a new finding on exploiting Projected User and Item Graph in the setting of Kernelized Probabilistic Matrix Factorization (KPMF), which uses different graph kernel from the projected graphs. KPMF, here, works with its latent vector spanning over all users (and items) with Gaussian process priors and tries to capture the covariance structure across users and items from the projected graphs. We also explore the ways of building these projected graphs maintaining some properties to maximize the prediction accuracy. We implement the model in four real-world datasets and compare the results with state-of-the-art MF techniques. Using projected graph in KPMF, we achieve significant improvement in RMSE using only rating information of users.

Full text in ACM Digital Library

User-Generated Content (UGC) is at the core of web applications where users can both produce and consume content. This differs from traditional e-Commerce domains where content producers and consumers are usually from two separate groups. In this work, we propose a method CPRec (consumer and producer based recommendation), for recommending content on UGC-based platforms. Specifically, we learn a core embedding for each user and two transformation matrices to project the user’s core embedding into two ‘role’ embeddings (i.e., a producer and consumer role). We model each interaction by the ternary relation between the consumer, the consumed item, and its producer. Empirical studies on two large-scale UGC applications show that our method outperforms standard collaborative filtering methods as well as recent methods that model producer information via item features.

Full text in ACM Digital Library

Building price- and budget-aware recommender systems is critical in settings where one wishes to produce recommendations that balance users’ preferences (what they like) with a model of purchase likelihood (what they will buy). A trivial solution consists of learning global budget terms for each user based on their past expenditure. To more accurately model user budgets, we also consider a user’s within-session budget, which may deviate from their global budget depending on their shopping context. In this paper, we find that users implicitly reveal their session-specific budgets through the sequence of items they browse within that session. Specifically, we find that some users browse down, by purchasing the cheapest item among alternatives under consideration, others browse up(selecting the most expensive), and others ultimately purchase items around the middle. Surprisingly, this mixture of behaviors is difficult to observe globally, but individual users tend to belong firmly to one of the three segments. To model this behavior, we develop an interpretable budget model that combines a clustering component to detect different user segments, with a model of segment-specific purchase profiles. We apply our model on a production dataset of browsing and purchasing sessions from a large e-commerce website focused on handmade and vintage goods, where it outperforms strong baselines and existing production systems.

Full text in ACM Digital Library

Data sparsity and cold start are two major problems that collaborative filtering based recommender systems confront. In many modern Internet applications, we have a social network over the users of recommender systems, from which social information can be utilized to improve the accuracy of recommendation. In this paper, we propose a novel trust-based matrix factorization model. Unlike most existing social recommender systems which use social information in form of a regularizer on parameters of recommendation algorithms, we utilize the social information to densify the training data set by filling certain missing values (handle the data sparsity problem). In addition, by employing different pseudo rating generating criteria on cold start users and normal users, we can also partially solve the cold start problem effectively. Experiment results on real-world data sets demonstrated the superiority of our method over state-of-art approaches.

Full text in ACM Digital Library

Large pharmaceutical companies have a wealth of reaction and chemical structure data, but face a new problem: analyzing that corpus to yield project insights and future directions. One straightforward approach would be to have a recommendation system to match drug structures with similar research endeavors across geographically- or organizationally-separated groups. We developed and deployed Chem Recommender, a system that suggests similar, related work to experiments that chemists have recently started. The goal of the system is to accelerate the drug discovery process by ensuring that chemists are aware of each other’s work. To date, we have sent more than 8500 recommendations to over 800 medicinal chemists in our organization. The results have been positive, with several chemists reporting that the recommendations have aided their molecular syntheses.

Full text in ACM Digital Library

The two main tasks in the Recommender Systems domain are the selection and prediction tasks. The prediction task aims at predicting to what extent a user would like any given item, which would enable to recommend the items with the highest predicted scores. The selection task on the other hand directly aims at recommending the most valuable items for the user. Several Multitask Learning approaches have been proposed to learn user and item representations that optimize both tasks simultaneously. In this work, we propose a novel framework that exploits the fact that a user first decides to interact with an item (selection task) and afterward to rate it (prediction task). We evaluated our framework on 2 benchmark datasets, on 2 different configurations and show its superiority over state-of-the-art methods.

Full text in ACM Digital Library

News is one of the earliest application domains of recommender systems, and recommending items from a virtually endless stream of news is still a relevant problem today. News recommendation is different from other application domains in a variety of ways, e.g., because new items constantly become available for recommendation. To be effective, news recommenders therefore have to continuously consider the latest items in the incoming stream of news in their recommendation models. However, today’s public software libraries for algorithm benchmarking mostly do not consider these particularities of the domain. As a result, authors often rely on proprietary protocols, which hampers the comparability of the obtained results. In this paper, we present StreamingRec as a framework for evaluating streaming-based news recommenders in a replicable way. The open-source framework implements a replay-based evaluation protocol that allows algorithms to update the underlying models in real-time when new events are recorded and new articles are available for recommendation. Furthermore, a variety of baseline algorithms for session-based recommendation are part of StreamingRec. For these, we also report a number of performance results for two datasets, which confirm the importance of immediate model updates.

Full text in ACM Digital Library

User-based Collaborative Filtering (CF) is one of the most popular approaches to create recommender systems. This approach is based on finding the most relevant k users from whose rating history we can extract items to recommend. CF, however, suffers from data sparsity and the cold-start problem since users often rate only a small fraction of available items. One solution is to incorporate additional information into the recommendation process such as explicit trust scores that are assigned by users to others or implicit trust relationships that result from social connections between users. Such relationships typically form a very sparse trust network, which can be utilized to generate recommendations for users based on people they trust. In our work, we explore the use of a measure from network science, i.e. regular equivalence, applied to a trust network to generate a similarity matrix that is used to select the k-nearest neighbors for recommending items. We evaluate our approach on Epinions and we find that we can outperform related methods for tackling cold-start users in terms of recommendation accuracy.

Full text in ACM Digital Library

Recommender System (RS) has been an essential component of many businesses, especially in e-commerce domain. RS exploits and processes the preference history (rating, purchase, review, etc.) of users in order to provide the recommendations. A user in traditional RS can provide only one rating value about an item. Deep Neural Networks have been used in this single rating system to improve recommendation accuracy in the recent times. However, the single rating systems are inadequate to understand the users’ preferences about an item. On the other hand, business enterprises such as tourism, e-learning, etc. facilitate users to provide multiple criteria ratings about an item, thus it becomes easier to understand users’ preference over single rating system. In this paper, we propose an extended Stacked Autoencoders (a Deep Neural Network technique) to utilize the multi-criteria ratings. The proposed network is designed to learn the relationship between each user’s criteria ratings and overall rating efficiently. Experimental results on real world datasets (Yahoo! Movies and TripAdvisor) demonstrate that the proposed approach outperforms state-of-the-art single rating systems and multi-criteria approaches on various performance metrics.

Full text in ACM Digital Library

Recent works in the area of academic recommender systems have demonstrated the effectiveness of co-citation and citation closeness in related-document recommendations. However, documents recommended from such systems may drift away from the main concept of the query document. In this work, we investigate whether incorporating the textual information in close proximity to a citation as well as the citation position could reduce such drifting and further increase the performance of the recommender system. To investigate this, we run experiments with several recommendation methods on a newly created and now publicly available dataset containing 53 million unique citation based records. We then conduct a user-based evaluation with domain-knowledgeable participants. Our results show that a new method based on the combination of Citation Proximity Analysis (CPA), topic modelling and word embeddings achieve more than 20% improvement in Normalised Discounted Cumulative Gain (nDCG) compared to CPA.

Full text in ACM Digital Library

Skip-gram with negative sampling, a popular variant of Word2vec originally designed and tuned to create word embeddings for Natural Language Processing, has been used to create item embeddings with successful applications in recommendation. While these fields do not share the same type of data, neither evaluate on the same tasks, recommendation applications tend to use the same already tuned hyperparameters values, even if optimal hyperparameters values are often known to be data and task dependent. We thus investigate the marginal importance of each hyperparameter in a recommendation setting through large hyperparameter grid searches on various datasets. Results reveal that optimizing neglected hyperparameters, namely negative sampling distribution, number of epochs, subsampling parameter and window-size, significantly improves performance on a recommendation task, and can increase it by an order of magnitude. Importantly, we find that optimal hyperparameters configurations for Natural Language Processing tasks and Recommendation tasks are noticeably different.

Full text in ACM Digital Library