[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

Predicting users' actions based on anonymous sessions is a challenging problem in web-based behavioral modeling research, mainly due to the uncertainty of user behavior and the limited information. Recent advances in recurrent neural networks have led to promising approaches to solving this problem, with long short-term memory model proving effective in capturing users' general interests from previous clicks. However, none of the existing approaches explicitly take the effects of users' current actions on their next moves into account. In this study, we argue that a long-term memory model may be insufficient for modeling long sessions that usually contain user interests drift caused by unintended clicks. A novel short-term attention/memory priority model is proposed as a remedy, which is capable of capturing users' general interests from the long-term memory of a session context, whilst taking into account users' current interests from the short-term memory of the last-clicks. The validity and efficacy of the proposed attention mechanism is extensively evaluated on three benchmark data sets from the RecSys Challenge 2015 and CIKM Cup 2016. The numerical results show that our model achieves state-of-the-art performance in all the tests.

STAMP: Short-Term Attention/Memory Priority Model for Session-based Recommendation

Deep learning methods have led to substantial progress in various application fields of AI, and in recent years a number of proposals were made to improve recommender systems with artificial neural networks. For the problem of making session-based recommendations, i.e., for recommending the next item in an anonymous session, Hidasi et al.~recently investigated the application of recurrent neural networks with Gated Recurrent Units (GRU4REC). Assessing the true effectiveness of such novel approaches based only on what is reported in the literature is however difficult when no standard evaluation protocols are applied and when the strength of the baselines used in the performance comparison is not clear. In this work we show based on a comprehensive empirical evaluation that a heuristics-based nearest neighbor (kNN) scheme for sessions outperforms GRU4REC in the large majority of the tested configurations and datasets. Neighborhood sampling and efficient in-memory data structures ensure the scalability of the kNN method. The best results in the end were often achieved when we combine the kNN approach with GRU4REC, which shows that RNNs can leverage sequential signals in the data that cannot be detected by the co-occurrence-based kNN method.

https://dl.acm.org/doi/pdf/10.1145/3109859.3109872

When Recurrent Neural Networks meet the Neighborhood for Session-Based Recommendation

Recently, Recurrent Neural Network (RNN) solutions for recommender systems (RS) are becoming increasingly popular. The insight is that, there exist some intrinsic patterns in the sequence of users’ actions, and RNN has been proved to perform excellently when modeling sequential data. In traditional tasks such as language modeling, RNN solutions usually only consider the sequential order of objects without the notion of interval. However, in RS, time intervals between users’ actions are of significant importance in capturing the relations of users’ actions and the traditional RNN architectures are not good at modeling them. In this paper, we propose a new LSTM variant, i.e. Time-LSTM, to model users’ sequential actions. Time-LSTM equips LSTM with time gates to model time intervals. These time gates are specifically designed, so that compared to the traditional RNN solutions, Time-LSTM better captures both of users’ shortterm and long-term interests, so as to improve the recommendation performance. Experimental results on two real-world datasets show the superiority of the recommendation method using TimeLSTM over the traditional methods.

/pdf/what-to-do-next-modeling-user-behaviors-by-time-lstm-3rfbnvdv6t.pdf

What to Do Next: Modeling User Behaviors by Time-LSTM.

Recommender systems are one of the most successful applications of data mining and machine-learning technology in practice. Academic research in the field is historically often based on the matrix completion problem formulation, where for each user-item-pair only one interaction (e.g., a rating) is considered. In many application domains, however, multiple user-item interactions of different types can be recorded over time. And, a number of recent works have shown that this information can be used to build richer individual user models and to discover additional behavioral patterns that can be leveraged in the recommendation process.In this work, we review existing works that consider information from such sequentially ordered user-item interaction logs in the recommendation process. Based on this review, we propose a categorization of the corresponding recommendation tasks and goals, summarize existing algorithmic solutions, discuss methodological approaches when benchmarking what we call sequence-aware recommender systems, and outline open challenges in the area.

/pdf/sequence-aware-recommender-systems-2i004vozij.pdf

Sequence-Aware Recommender Systems

More and more people read the news online, e.g., by visiting the websites of their favorite newspapers or by navigating the sites of news aggregators. However, the abundance of news information that is published online every day through different channels can make it challenging for readers to locate the content they are interested in. The goal of News Recommender Systems (NRS) is to make reading suggestions to users in a personalized way. Due to their practical relevance, a variety of technical approaches to build such systems have been proposed over the last two decades. In this work, we review the state-of-the-art of designing and evaluating news recommender systems over the last ten years. One main goal of the work is to analyze which particular challenges of news recommendation (e.g., short item life times and recency aspects) have been well explored and which areas still require more work. Furthermore, in contrast to previous surveys, the paper specifically discusses methodological questions and today’s academic practice of evaluating and comparing different algorithmic news recommendation approaches based on accuracy measures.

News recommender systems – Survey and roads ahead

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

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

Automated recommendations have become a ubiquitous part of today’s online user experience. These systems point us to additional items to purchase in online shops, they make suggestions to us on movies to watch, or recommend us people to connect with on social websites. In many of today’s applications, however, the only way for users to interact with the system is to inspect the recommended items. Often, no mechanisms are implemented for users to give the system feedback on the recommendations or to explicitly specify preferences, which can limit the potential overall value of the system for its users. Academic research in recommender systems is largely focused on algorithmic approaches for item selection and ranking. Nonetheless, over the years a variety of proposals were made on how to design more interactive recommenders. This work provides a comprehensive overview on the existing literature on user interaction aspects in recommender systems. We cover existing approaches for preference elicitation and result presentation, as well as proposals that consider recommendation as an interactive process. Throughout the work, we furthermore discuss examples of real-world systems and outline possible directions for future works.

Interacting with Recommenders—Overview and Research Directions

Recommender Systems are nowadays successfully used by all major web sites—from e-commerce to social media—to filter content and make suggestions in a personalized way. Academic research largely focuses on the value of recommenders for consumers, e.g., in terms of reduced information overload. To what extent and in which ways recommender systems create business value is, however, much less clear, and the literature on the topic is scattered. In this research commentary, we review existing publications on field tests of recommender systems and report which business-related performance measures were used in such real-world deployments. We summarize common challenges of measuring the business value in practice and critically discuss the value of algorithmic improvements and offline experiments as commonly done in academic environments. Overall, our review indicates that various open questions remain both regarding the realistic quantification of the business effects of recommenders and the performance assessment of recommendation algorithms in academia.

Measuring the Business Value of Recommender Systems

An essential characteristic in many e-commerce settings is that website visitors can have very specific short-term shopping goals when they browse the site. Relying solely on long-term user models that are pre-trained on historical data can therefore be insufficient for a suitable next-basket recommendation. Simple "real-time" recommendation approaches based, e.g., on unpersonalized co-occurrence patterns, on the other hand do not fully exploit the available information about the user's long-term preference profile. In this work, we aim to explore and quantify the effectiveness of using and combining long-term models and short-term adaptation strategies. We conducted an empirical evaluation based on a novel evaluation design and two real-world datasets. The results indicate that maintaining short-term content-based and recency-based profiles of the visitors can lead to significant accuracy increases. At the same time, the experiments show that the choice of the algorithm for learning the long-term preferences is particularly important at the beginning of new shopping sessions.

Michael Jugovac

Papers

News recommender systems – Survey and roads ahead

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

Interacting with Recommenders—Overview and Research Directions

Measuring the Business Value of Recommender Systems

Adaptation and Evaluation of Recommendations for Short-term Shopping Goals