Showing papers on "User modeling published in 2019"

Generative Adversarial User Model for Reinforcement Learning Based Recommendation System

Abstract: There are great interests as well as many challenges in applying reinforcement learning (RL) to recommendation systems. In this setting, an online user is the environment; neither the reward function nor the environment dynamics are clearly defined, making the application of RL challenging. In this paper, we propose a novel model-based reinforcement learning framework for recommendation systems, where we develop a generative adversarial network to imitate user behavior dynamics and learn her reward function. Using this user model as the simulation environment, we develop a novel Cascading DQN algorithm to obtain a combinatorial recommendation policy which can handle a large number of candidate items efficiently. In our experiments with real data, we show this generative adversarial user model can better explain user behavior than alternatives, and the RL policy based on this model can lead to a better long-term reward for the user and higher click rate for the system.

Analyzing large-scale human mobility data: a survey of machine learning methods and applications

Abstract: Human mobility patterns reflect many aspects of life, from the global spread of infectious diseases to urban planning and daily commute patterns. In recent years, the prevalence of positioning methods and technologies, such as the global positioning system, cellular radio tower geo-positioning, and WiFi positioning systems, has driven efforts to collect human mobility data and to mine patterns of interest within these data in order to promote the development of location-based services and applications. The efforts to mine significant patterns within large-scale, high-dimensional mobility data have solicited use of advanced analysis techniques, usually based on machine learning methods, and therefore, in this paper, we survey and assess different approaches and models that analyze and learn human mobility patterns using mainly machine learning methods. We categorize these approaches and models in a taxonomy based on their positioning characteristics, the scale of analysis, the properties of the modeling approach, and the class of applications they can serve. We find that these applications can be categorized into three classes: user modeling, place modeling, and trajectory modeling, each class with its characteristics. Finally, we analyze the short-term trends and future challenges of human mobility analysis.

Adaptive user modeling with long and short-term preferences for personalized recommendation

Abstract: User modeling is an essential task for online recommender systems. In the past few decades, collaborative filtering (CF) techniques have been well studied to model users' long term preferences. Recently, recurrent neural networks (RNN) have shown a great advantage in modeling users' short term preference. A natural way to improve the recommender is to combine both long-term and short-term modeling. Previous approaches neglect the importance of dynamically integrating these two user modeling paradigms. Moreover, users' behaviors are much more complex than sentences in language modeling or images in visual computing, thus the classical structures of RNN such as Long Short-Term Memory (LSTM) need to be upgraded for better user modeling. In this paper, we improve the traditional RNN structure by proposing a time-aware controller and a content-aware controller, so that contextual information can be well considered to control the state transition. We further propose an attention-based framework to combine users' long-term and short-term preferences, thus users' representation can be generated adaptively according to the specific context. We conduct extensive experiments on both public and industrial datasets. The results demonstrate that our proposed method outperforms several state-of-art methods consistently.

Dynamic Explainable Recommendation Based on Neural Attentive Models

Abstract: Providing explanations in a recommender system is getting more and more attention in both industry and research communities. Most existing explainable recommender models regard user preferences as invariant to generate static explanations. However, in real scenarios, a user’s preference is always dynamic, and she may be interested in different product features at different states. The mismatching between the explanation and user preference may degrade costumers’ satisfaction, confidence and trust for the recommender system. With the desire to fill up this gap, in this paper, we build a novel Dynamic Explainable Recommender (called DER) for more accurate user modeling and explanations. In specific, we design a time-aware gated recurrent unit (GRU) to model user dynamic preferences, and profile an item by its review information based on sentence-level convolutional neural network (CNN). By attentively learning the important review information according to the user current state, we are not only able to improve the recommendation performance, but also can provide explanations tailored for the users’ current preferences. We conduct extensive experiments to demonstrate the superiority of our model for improving recommendation performance. And to evaluate the explainability of our model, we first present examples to provide intuitive analysis on the highlighted review information, and then crowd-sourcing based evaluations are conducted to quantitatively verify our model’s superiority.

Transparent, Scrutable and Explainable User Models for Personalized Recommendation

Abstract: Most recommender systems base their recommendations on implicit or explicit item-level feedback provided by users. These item ratings are combined into a complex user model, which then predicts the suitability of other items. While effective, such methods have limited scrutability and transparency. For instance, if a user's interests change, then many item ratings would usually need to be modified to significantly shift the user's recommendations. Similarly, explaining how the system characterizes the user is impossible, short of presenting the entire list of known item ratings. In this paper, we present a new set-based recommendation technique that permits the user model to be explicitly presented to users in natural language, empowering users to understand recommendations made and improve the recommendations dynamically. While performing comparably to traditional collaborative filtering techniques in a standard static setting, our approach allows users to efficiently improve recommendations. Further, it makes it easier for the model to be validated and adjusted, building user trust and understanding.

Social Attentional Memory Network: Modeling Aspect- and Friend-Level Differences in Recommendation

Abstract: Social connections are known to be helpful for modeling users' potential preferences and improving the performance of recommender systems. However, in social-aware recommendations, there are two issues which influence the inference of users' preferences, and haven't been well-studied in most existing methods: First, the preferences of a user may only partially match that of his friends in certain aspects, especially when considering a user with diverse interests. Second, for an individual, the influence strength of his friends might be different, as not all friends are equally helpful for modeling his preferences in the system. To address the above issues, in this paper, we propose a novel Social Attentional Memory Network (SAMN) for social-aware recommendation. Specifically, we first design an attention-based memory module to learn user-friend relation vectors, which can capture the varying aspect attentions that a user share with his different friends. Then we build a friend-level attention component to adaptively select informative friends for user modeling. The two components are fused together to mutually enhance each other and lead to a finer extended model. Experimental results on three publicly available datasets show that the proposed SAMN model consistently and significantly outperforms the state-of-the-art recommendation methods. Furthermore, qualitative studies have been made to explore what the proposed attention-based memory module and friend-level attention have learnt, which provide insights into the model's learning process.

Lifelong Sequential Modeling with Personalized Memorization for User Response Prediction

Abstract: User response prediction, which models the user preference w.r.t. the presented items, plays a key role in online services. With two-decade rapid development, nowadays the cumulated user behavior sequences on mature Internet service platforms have become extremely long since the user's first registration. Each user not only has intrinsic tastes, but also keeps changing her personal interests during lifetime. Hence, it is challenging to handle such lifelong sequential modeling for each individual user. Existing methodologies for sequential modeling are only capable of dealing with relatively recent user behaviors, which leaves huge space for modeling long-term especially lifelong sequential patterns to facilitate user modeling. Moreover, one user's behavior may be accounted for various previous behaviors within her whole online activity history, i.e., long-term dependency with multi-scale sequential patterns. In order to tackle these challenges, in this paper, we propose a Hierarchical Periodic Memory Network for lifelong sequential modeling with personalized memorization of sequential patterns for each user. The model also adopts a hierarchical and periodical updating mechanism to capture multi-scale sequential patterns of user interests while supporting the evolving user behavior logs. The experimental results over three large-scale real-world datasets have demonstrated the advantages of our proposed model with significant improvement in user response prediction performance against the state-of-the-arts.

Privacy-aware eye tracking using differential privacy

Abstract: With eye tracking being increasingly integrated into virtual and augmented reality (VR/AR) head-mounted displays, preserving users' privacy is an ever more important, yet under-explored, topic in the eye tracking community. We report a large-scale online survey (N=124) on privacy aspects of eye tracking that provides the first comprehensive account of with whom, for which services, and to what extent users are willing to share their gaze data. Using these insights, we design a privacy-aware VR interface that uses differential privacy, which we evaluate on a new 20-participant dataset for two privacy sensitive tasks: We show that our method can prevent user re-identification and protect gender information while maintaining high performance for gaze-based document type classification. Our results highlight the privacy challenges particular to gaze data and demonstrate that differential privacy is a potential means to address them. Thus, this paper lays important foundations for future research on privacy-aware gaze interfaces.

Explainable Interaction-driven User Modeling over Knowledge Graph for Sequential Recommendation

Abstract: Compared with the traditional recommendation system, sequential recommendation holds the ability of capturing the evolution of users' dynamic interests. Many previous studies in sequential recommendation focus on the accuracy of predicting the next item that a user might interact with, while generally ignore providing explanations why the item is recommended to the user. Appropriate explanations are critical to help users adopt the recommended item, and thus improve the transparency and trustworthiness of the recommendation system. In this paper, we propose a novel Explainable Interaction-driven User Modeling (EIUM) algorithm to exploit Knowledge Graph (KG) for constructing an effective and explainable sequential recommender. Qualified semantic paths between specific user-item pair are extracted from KG. Encoding those semantic paths and learning the importance scores for each path provides the path-wise explanation for the recommendation system. Different from traditional item- level sequential modeling methods, we capture the interaction-level user dynamic preferences by modeling the sequential interactions. It is a high- level representation which contains auxiliary semantic information from KG. Furthermore, we adopt a joint learning manner for better representation learning by employing multi-modal fusion, which benefits from the structural constraints in KG and involves three kinds of modalities. Extensive experiments on the large-scale dataset show the better performance of our approach in making sequential recommendations in terms of both accuracy and explainability.

A systematic review of data-driven approaches in player modeling of educational games

Abstract: Recent years have seen growing interest in open-ended interactive educational tools such as games. One of the most crucial aspects of developing games lies in modeling and predicting individual behavior, the study of computational models of players in games. Although model-based approaches have been considered standard for this purpose, their application is often extremely difficult due to the huge space of actions that can be created by educational games. For this reason, data-driven approaches have shown promise, in part because they are not completely reliant on expert knowledge. This study seeks to systematically review the existing research on the use of data-driven approaches in player modeling of educational games. The primary objectives of this study are to identify, classify, and bring together the relevant approaches. We have carefully surveyed a 10-year sample (2008–2017) of research studies conducted on data-driven approaches in player modeling of educational games, and thereby found 67 significant research works. However, our criteria for inclusion reduced the sample to 21 studies that addressed four primary research questions, and so we analyzed and classified the questions, methods, and findings of these published works, which we evaluated and from which we drew conclusions based on non-statistical methods. We found that there are three primary avenues along which data-driven approaches have been studied in educational games research: first, the objective of data-driven approaches in player modeling of educational games, namely behavior modeling, goal recognition, and procedural content generation; second, approaches employed in such modeling; finally, current challenges of using data-driven approaches in player modeling of educational games, namely game data, temporal forecasting in player models, statistical techniques, algorithmic efficiency, knowledge engineering, problem of generalizability, and data sparsity problem. In conclusion we addressed four critical future challenges in the area, namely, the lack of proper and rich data publicly available to the researchers, the lack of a data-driven method to identify conceptual features from log data, hybrid player modeling approaches, and data mining techniques for individual prediction.

Towards Neural Mixture Recommender for Long Range Dependent User Sequences

Abstract: Understanding temporal dynamics has proved to be highly valuable for accurate recommendation. Sequential recommenders have been successful in modeling the dynamics of users and items over time. However, while different model architectures excel at capturing various temporal ranges or dynamics, distinct application contexts require adapting to diverse behaviors. In this paper we examine how to build a model that can make use of different temporal ranges and dynamics depending on the request context. We begin with the analysis of an anonymized Youtube dataset comprising millions of user sequences. We quantify the degree of long-range dependence in these sequences and demonstrate that both short-term and long-term dependent behavioral patterns co-exist. We then propose a neural Multi-temporal-range Mixture Model (M3) as a tailored solution to deal with both short-term and long-term dependencies. Our approach employs a mixture of models, each with a different temporal range. These models are combined by a learned gating mechanism capable of exerting different model combinations given different contextual information. In empirical evaluations on a public dataset and our own anonymized YouTube dataset, M3 consistently outperforms state-of-the-art sequential recommendation methods.

A comparative analysis of recommender systems based on item aspect opinions extracted from user reviews

Abstract: In popular applications such as e-commerce sites and social media, users provide online reviews giving personal opinions about a wide array of items, such as products, services and people. These reviews are usually in the form of free text, and represent a rich source of information about the users’ preferences. Among the information elements that can be extracted from reviews, opinions about particular item aspects (i.e., characteristics, attributes or components) have been shown to be effective for user modeling and personalized recommendation. In this paper, we investigate the aspect-based top-N recommendation problem by separately addressing three tasks, namely identifying references to item aspects in user reviews, classifying the sentiment orientation of the opinions about such aspects in the reviews, and exploiting the extracted aspect opinion information to provide enhanced recommendations. Differently to previous work, we integrate and empirically evaluate several state-of-the-art and novel methods for each of the above tasks. We conduct extensive experiments on standard datasets and several domains, analyzing distinct recommendation quality metrics and characteristics of the datasets, domains and extracted aspects. As a result of our investigation, we not only derive conclusions about which combination of methods is most appropriate according to the above issues, but also provide a number of valuable resources for opinion mining and recommendation purposes, such as domain aspect vocabularies and domain-dependent, aspect-level lexicons.

Neural Demographic Prediction using Search Query

Abstract: Demographics of online users such as age and gender play an important role in personalized web applications. However, it is difficult to directly obtain the demographic information of online users. Luckily, search queries can cover many online users and the search queries from users with different demographics usually have some difference in contents and writing styles. Thus, search queries can provide useful clues for demographic prediction. In this paper, we study predicting users' demographics based on their search queries, and propose a neural approach for this task. Since search queries can be very noisy and many of them are not useful, instead of combining all queries together for user representation, in our approach we propose a hierarchical user representation with attention (HURA) model to learn informative user representations from their search queries. Our HURA model first learns representations for search queries from words using a word encoder, which consists of a CNN network and a word-level attention network to select important words. Then we learn representations of users based on the representations of their search queries using a query encoder, which contains a CNN network to capture the local contexts of search queries and a query-level attention network to select informative search queries for demographic prediction. Experiments on two real-world datasets validate that our approach can effectively improve the performance of search query based age and gender prediction and consistently outperform many baseline methods.

Noise Contrastive Estimation for One-Class Collaborative Filtering

Abstract: Previous highly scalable One-Class Collaborative Filtering (OC-CF) methods such as Projected Linear Recommendation (PLRec) have advocated using fast randomized SVD to embed items into a latent space, followed by linear regression methods to learn personalized recommendation models per user. However, naive SVD embedding methods often exhibit a strong popularity bias that prevents them from accurately embedding less popular items, which is exacerbated by the extreme sparsity of implicit feedback matrices in the OC-CF setting. To address this deficiency, we leverage insights from Noise Contrastive Estimation (NCE) to derive a closed-form, efficiently computable "depopularized" embedding. We show that NCE item embeddings combined with a personalized user model from PLRec produces superior recommendations that adequately account for popularity bias. Further analysis of the popularity distribution of recommended items demonstrates that NCE-PLRec uniformly distributes recommendations over the popularity spectrum while other methods exhibit distinct biases towards specific popularity subranges. Empirically, NCE-PLRec produces highly competitive performance with run-times an order of magnitude faster than existing state-of-the-art approaches for OC-CF.

Leveraging post-click feedback for content recommendations

Abstract: Implicit feedback (e.g., clicks) is widely used in content recommendations. However, clicks only reflect user preferences according to their first impressions. They do not capture the extent to which users continue to engage with the content. Our analysis shows that more than half of the clicks on music and short videos are followed by skips from two real-world datasets. In this paper, we leverage post-click feedback, e.g. skips and completions, to improve the training and evaluation of content recommenders. Specifically, we experiment with existing collaborative filtering algorithms and find that they perform poorly against post-click-aware ranking metrics. Based on these insights, we develop a generic probabilistic framework to fuse click and post-click signals. We show how our framework can be applied to improve pointwise and pairwise recommendation models. Our approach is shown to outperform existing methods by 18.3% and 2.5% respectively in terms of Area Under the Curve (AUC) on the short-video and music dataset. We discuss the effectiveness of our approach across content domains and trade-offs in weighting various user feedback signals.

From data to personal user models for life-long, life-wide learners

Abstract: As technology has become ubiquitous in learning contexts, there has been an explosion in the amount of learning data. This creates opportunities to draw on the decades of learner modelling research from Artificial Intelligence in Education and more recent research on Personal Informatics. We use these bodies of research to introduce a conceptual model for a Personal User Model for Life‐long, Life‐wide Learners (PUMLs). We use this to define a core set of system competency questions. A successful PUML and its interface must enable a learner to answer these by scrutinising their PUML, aided by its scaffolding interfaces. We aim to give learners both control over their own learning data and the means to harness that data for the important metacognitive processes of self‐monitoring, reflection and planning. We conclude with a set of design guidelines for creating PUMLs. Our core contribution is a way to think about the design and evaluation of learning data and applications so that they give learner control and agency beyond simple data access and algorithmic transparency. Practitioner NotesWhat is already known about this topic There is decades of Artificial Intelligence in Education (AIED) research on learner modelling, personalisation and Open Learner Models (OLMs).There is a growing body of work on Personal Informatics.What this paper adds Drawing on the above research, we present a conceptual model showing how learning applications and data repositories relate to a Personal User Model for Life‐long, Life‐wide Learners (PUMLs).A set of competency questions to inform design and evaluation of PUMLs.Guidelines for designing interfaces that enable learners to scrutinise and control their learning data and models.Implications for practice and/or policy As universities create institutional repositories of learning data, our work takes a complementary, learner‐centred perspective of learning data, applications and repositories.PUMLs offer a mechanism to support student's meta‐cognitive processes.PUMLs go beyond simplistic views of data access and transparency of algorithmic processes—empowering learners to scrutinise their long‐term data and its use. [ABSTRACT FROM AUTHOR]

User preferences modeling using dirichlet process mixture model for a content-based recommender system

Abstract: Recommender systems have been developed to assist users in retrieving relevant resources. Collaborative and content-based filtering are two basic approaches that are used in recommender systems. The former employs the feedback of users with similar interests, while the latter is based on the feature of the selected resources by each user. Recommender systems can consider users’ behavior to more accurately estimate their preferences via a list of recommendations. However, the existing approaches rarely consider both interests and preferences of the users. Also, the dynamic nature of user behavior poses an additional challenge for recommender systems. In this paper, we consider the interactions of each individual user, and analyze them to propose a user model and capture user’s interests. We construct the user model based on a Bayesian nonparametric framework, called the Dirichlet Process Mixture Model. The proposed model evolves following the dynamic nature of user behavior to adapt both the user interests and preferences. We implemented the proposed model and evaluated it using both the MovieLens dataset, and a real-world dataset that contains news tweets from five news channels (New York Times, BBC, CNN, Reuters and Associated Press). The experimental results and comparisons with several recently developed approaches show the superiority in accuracy of the proposed approach, and its ability to adapt with user behavior over time.

Adapting robot task planning to user preferences: an assistive shoe dressing example

Abstract: Healthcare robots will be the next big advance in humans’ domestic welfare, with robots able to assist elderly people and users with disabilities. However, each user has his/her own preferences, needs and abilities. Therefore, robotic assistants will need to adapt to them, behaving accordingly. Towards this goal, we propose a method to perform behavior adaptation to the user preferences, using symbolic task planning. A user model is built from the user’s answers to simple questions with a fuzzy inference system, and it is then integrated into the planning domain. We describe an adaptation method based on both the user satisfaction and the execution outcome, depending on which penalizations are applied to the planner’s rules. We demonstrate the application of the adaptation method in a simple shoe-fitting scenario, with experiments performed in a simulated user environment. The results show quick behavior adaptation, even when the user behavior changes, as well as robustness to wrong inference of the initial user model. Finally, some insights in a non-simulated world shoe-fitting setup are also provided.

Personalization in long-term human-robot interaction

Abstract: For practical reasons, most human-robot interaction (HRI) studies focus on short-term interactions between humans and robots. However, such studies do not capture the difficulty of sustaining engagement and interaction quality across long-term interactions. Many real-world robot applications will require repeated interactions and relationship-building over the long term, and personalization and adaptation to users will be necessary to maintain user engagement and to build rapport and trust between the user and the robot. This full-day workshop brings together perspectives from a variety of research areas, including companion robots, elderly care, and educational robots, in order to provide a forum for sharing and discussing innovations, experiences, works-in-progress, and best practices which address the challenges of personalization in long-term HRI.

Personalized Capsule Wardrobe Creation with Garment and User Modeling

Abstract: Recent years have witnessed a growing trend of building the capsule wardrobe by minimizing and diversifying the garments in their messy wardrobes. Thanks to the recent advances in multimedia techniques, many researches have promoted the automatic creation of capsule wardrobes by the garment modeling. Nevertheless, most capsule wardrobes generated by existing methods fail to consider the user profile, including the user preferences, body shapes and consumption habits, which indeed largely affects the wardrobe creation. To this end, we introduce a combinatorial optimization-based personalized capsule wardrobe creation framework, named PCW-DC, which jointly integrates both garment modeling (\textiti.e., wardrobe compatibility) and user modeling (\textiti.e., preferences, body shapes). To justify our model, we construct a dataset, named bodyFashion, which consists of $116,532$ user-item purchase records on Amazon involving 11,784 users and 75,695 fashion items. Extensive experiments on bodyFashion have demonstrated the effectiveness of our proposed model. As a byproduct, we have released the codes and the data to facilitate the research community.

Real World User Model: Evolution of User Modeling Triggered by Advances in Wearable and Ubiquitous Computing: State of the Art and Future Directions

Abstract: Over the last few years, user modeling scenery is changing. With the recent advancements in ubiquitous and wearables technologies, the amount and type of data that can be gathered about users and used to build user models is expanding. User Model can now be enriched with data regarding different aspects of people’s everyday lives. All these changes bring forth new research questions about the kinds of services which could be provided, the ways for effectively conveying new forms of personalisation and recommendation, and how traditional user modeling should change to exploit ubiquitous and wearable technology to provide these services. In this paper we follow the evolution of user modeling process, starting from the traditional User Model and progressing to RWUM - Real World User Model, which contains data from a person’s everyday life. We tried to answer the above questions and to present a conceptual framework that represents the RWUM process, which might be used as a reference model for designing RWUM-based systems. Finally, we propose some inspiring usage scenarios and design directions that can guide researchers in designing novel, robust and versatile services based on RWUM.

Online User Representation Learning Across Heterogeneous Social Networks

Abstract: Accurate user representation learning has been proven fundamental for many social media applications, including community detection, recommendation, etc. A major challenge lies in that, the available data in a single social network are usually very limited and sparse. In real life, many people are members of several social networks in the same time. Constrained by the features and design of each, any single social platform offers only a partial view of a user from a particular perspective. In this paper, we propose MV-URL, a multi-view user representation learning model to enhance user modeling by integrating the knowledge from various networks. Different from the traditional network embedding frameworks where either the whole framework is single-network based or each network involved is a homogeneous network, we focus on multiple social networks and each network in our task is a heterogeneous network. It's very challenging to effectively fuse knowledge in this setting as the fusion depends upon not only the varying relatedness of information sources, but also the target application tasks. MV-URL focuses on two tasks: user account linkage (i.e., to predict the missing true user account linkage across social media) and user attribute prediction. Extensive evaluations have been conducted on two real-world collections of linked social networks, and the experimental results show the superiority of MV-URL compared with existing state-of-art embedding methods. It can be learned online, and is trivially parallelizable. These qualities make it suitable for real world applications.

Lifelong Sequential Modeling with Personalized Memorization for User Response Prediction

Abstract: User response prediction, which models the user preference w.r.t. the presented items, plays a key role in online services. With two-decade rapid development, nowadays the cumulated user behavior sequences on mature Internet service platforms have become extremely long since the user's first registration. Each user not only has intrinsic tastes, but also keeps changing her personal interests during lifetime. Hence, it is challenging to handle such lifelong sequential modeling for each individual user. Existing methodologies for sequential modeling are only capable of dealing with relatively recent user behaviors, which leaves huge space for modeling long-term especially lifelong sequential patterns to facilitate user modeling. Moreover, one user's behavior may be accounted for various previous behaviors within her whole online activity history, i.e., long-term dependency with multi-scale sequential patterns. In order to tackle these challenges, in this paper, we propose a Hierarchical Periodic Memory Network for lifelong sequential modeling with personalized memorization of sequential patterns for each user. The model also adopts a hierarchical and periodical updating mechanism to capture multi-scale sequential patterns of user interests while supporting the evolving user behavior logs. The experimental results over three large-scale real-world datasets have demonstrated the advantages of our proposed model with significant improvement in user response prediction performance against the state-of-the-arts.

User-Controlled Privacy-Preserving User Profile Data Sharing based on Blockchain.

Abstract: The tremendous technological advancement in the last few decades has brought many enterprises to collaborate in a better way while making intelligent decisions. The use of Information Technology tools in obtaining data of people's everyday life from various autonomous data sources allowing unrestricted access to user data has emerged as an important practical issue and has given rise to legal implications. Various innovative models for data sharing and management have privacy and centrality issues. To alleviate these limitations, we have incorporated blockchain in user modeling. In this paper, we constructed a decentralized data sharing architecture with MultiChain blockchain in the travel domain, which is also applicable to other similar domains including education, health, and sports. Businesses that operate in the tourism industries including travel and tour agencies, hotels and resorts, shopping malls are connected to the MultiChain and they share their user profile data via stream in the MultiChain. The paper presents the hotel booking service for an imaginary hotel as one of the enterprise nodes, which collects user profile data with proper validation and will allow users to decide which of their data to be shared thus ensuring user control over their data and the preservation of privacy. The data from the repository is converted into an open data format while sharing via stream in the blockchain so that other enterprise nodes, after receiving the data, can easily convert them and store into their own repositories. The paper presents an evaluation of the performance of the model by measuring the latency and memory consumption with three test scenarios that mostly affect the user experience. The node responded quickly in all of these cases.

User Modeling for Churn Prediction in E-Commerce

Abstract: In the domain of e-commerce, acquiring a new customer is generally more expensive than keeping the existing ones. A successful prediction of churn of a specific customer provides an opportunity to change his/her decision to leave. In this paper, we propose a novel complex user model focused on the user churn intent prediction. The idea of our model is based on composing of multiple sets of features representing user's interaction with the web application. The performance of our model is evaluated indirectly by the prediction of churn, using real data from online retailers. The results show that the prediction using the proposed model outperforms the churn prediction based on baseline models across two domains.

TiSSA: A Time Slice Self-Attention Approach for Modeling Sequential User Behaviors

Abstract: Modeling user behaviors as sequences provides critical advantages in predicting future user actions, such as predicting the next product to purchase or the next song to listen to, for personalized search and recommendation. Recently, recurrent neural networks (RNNs) have been adopted to leverage their power in modeling sequences. However, most of the previous RNN-based work suffers from the complex dependency problem, which may lose the integrity of highly correlated behaviors and may introduce noises derived from unrelated behaviors. In this paper, we propose to integrate a novel Time Slice Self-Attention (TiSSA) mechanism into RNNs for better modeling sequential user behaviors, which utilizes the time-interval-based gated recurrent units to exploit the temporal dimension when encoding user actions, and has a specially designed time slice hierarchical self-attention function to characterize both local and global dependency of user actions, while the final context-aware user representations can be used for downstream applications. We have performed experiments on a huge dataset collected from one of the largest e-commerce platforms in the world. Experimental results show that the proposed TiSSA achieves significant improvement over the state-of-the-art. TiSSA is also adopted in this large e-commerce platform, and the results of online A/B test further indicate its practical value.