Abstract: Amazon is well-known for personalization and recommendations, which help customers discover items they might otherwise not have found. In this update to their original paper, the authors discuss some of the changes as Amazon has grown.

Abstract: Diversification has become one of the leading topics of recommender system research not only as a way to solve the over-fitting problem but also an approach to increasing the quality of the users experience with the recommender system. This article aims to provide an overview of research done on this topic from one of the first mentions of diversity in 2001 until now. The articles ,and research, have been divided into three sub-topics for a better overview of the work done in the field of recommendation diversification: the definition and evaluation of diversity; the impact of diversification on the quality of recommendation results and the development of diversification algorithms themselves. In this way, the article aims both to offer a good overview to a researcher looking for the state-of-the-art on this topic and to help a new developer get familiar with the topic.

Abstract: Although mass customization, which utilizes modularization to simultaneously increase product variety and maintain mass production (MP) efficiency, has become a trend in recent times, there are some limitations to mass customization. Firstly, customers do not participate wholeheartedly in the design phase. Secondly, potential combinations are predetermined by designers. Thirdly, the concept of mass customization is not necessary to satisfy individual requirements and is not capable of providing personalized services and goods. Industry 4.0 is a collective term for technologies and concepts of value chain organization. Based on the technological concepts of radio frequency identification, cyber-physical system, the Internet of things, Internet of service, and data mining, Industry 4.0 will enable novel forms of personalization. Direct customer input to design will enable companies to increasingly produce customized products with shorter cycle-times and lower costs than those associated with standardization and MP. The producer and the customer will share in the new value created. To overcome the gaps between mass customization and mass personalization, this paper presents a framework for mass personalization production based on the concepts of Industry 4.0. Several industrial practices and a lab demonstration show how we can realize mass personalization.

Abstract: This article addresses questions of ideological polarization and the filter bubble in social media. It develops a theoretical analysis of ideological polarization on social media by considering a range of relevant factors. Over recent years, fake news and the effect of the social media filter bubble have become of increasing importance both in academic and general discourse. The article reviews the assumption that algorithmic curation and personalization systems place users in a filter bubble of content that decreases their likelihood of encountering ideologically cross-cutting news content. At the intersection of new media, politics and behavioural science, the article establishes a theoretical framework for further research and future actions by society, policymakers and industries.

Abstract: Web search is an integral part of our daily lives. Recently, there has been a trend of personalization in Web search, where different users receive different results for the same search query. The increasing level of personalization is leading to concerns about Filter Bubble effects, where certain users are simply unable to access information that the search engines' algorithm decides is irrelevant. Despite these concerns, there has been little quantification of the extent of personalization in Web search today, or the user attributes that cause it. In light of this situation, we make three contributions. First, we develop a methodology for measuring personalization in Web search results. While conceptually simple, there are numerous details that our methodology must handle in order to accurately attribute differences in search results to personalization. Second, we apply our methodology to 200 users on Google Web Search and 100 users on Bing. We find that, on average, 11.7% of results show differences due to personalization on Google, while 15.8% of results are personalized on Bing, but that this varies widely by search query and by result ranking. Third, we investigate the user features used to personalize on Google Web Search and Bing. Surprisingly, we only find measurable personalization as a result of searching with a logged in account and the IP address of the searching user. Our results are a first step towards understanding the extent and effects of personalization on Web search engines today.

Abstract: The ability to predict future user activity is invaluable when it comes to content recommendation and personalization. For instance, knowing when users will return to an online music service and what they will listen to increases user satisfaction and therefore user retention. We present a model based on Long-Short Term Memory to estimate when a user will return to a site and what their future listening behavior will be. In doing so, we aim to solve the problem of Just-In-Time recommendation, that is, to recommend the right items at the right time. We use tools from survival analysis for return time prediction and exponential families for future activity analysis. We show that the resulting multitask problem can be solved accurately, when applied to two real-world datasets.

Abstract: Digital services need access to consumers’ data to improve service quality and to generate revenues. However, it remains unclear how such services should be configured to facilitate consumers’ willingness to share personal information. Prior studies discuss an influence of selected individual traits or service configurations, including transparency features and service personalization. This study aims at uncovering how interactions among individuals’ privacy valuation, transparency features, and service personalization influence their willingness to disclose information. Building on information boundary theory, we conducted an experimental study with 286 participants on a data-intense digital service. In contrast to our expectation, we found no indication that providing transparency features facilitates individuals’ information disclosure. Relative to the personalization–privacy paradox, individuals’ privacy valuation is a strong inhibitor of information provision in general, not only for personal...

Abstract: Our life is characterized by the presence of a multitude of interactive devices and smart objects exploited for disparate goals in different contexts of use. Thus, it is impossible for application developers to predict at design time the devices and objects users will exploit, how they will be arranged, and in which situations and for which objectives they will be used. For such reasons, it is important to make end users able to easily and autonomously personalize the behaviour of their Internet of Things applications, so that they can better comply with their specific expectations. In this paper, we present a method and a set of tools that allow end users without programming experience to customize the context-dependent behaviour of their Web applications through the specification of trigger-action rules. The environment is able to support end-user specification of more flexible behaviour than what can be done with existing commercial tools, and it also includes an underlying infrastructure able to detect the possible contextual changes in order to achieve the desired behaviour. The resulting set of tools is able to support the dynamic creation and execution of personalized application versions more suitable for users’ needs in specific contexts of use. Thus, it represents a contribution to obtaining low threshold/high ceiling environments. We also report on an example application in the home automation domain, and a user study that has provided useful positive feedback.

Abstract: Product search is an important part of online shopping. In contrast to many search tasks, the objectives of product search are not confined to retrieving relevant products. Instead, it focuses on finding items that satisfy the needs of individuals and lead to a user purchase. The unique characteristics of product search make search personalization essential for both customers and e-shopping companies. Purchase behavior is highly personal in online shopping and users often provide rich feedback about their decisions (e.g. product reviews). However, the severe mismatch found in the language of queries, products and users make traditional retrieval models based on bag-of-words assumptions less suitable for personalization in product search. In this paper, we propose a hierarchical embedding model to learn semantic representations for entities (i.e. words, products, users and queries) from different levels with their associated language data. Our contributions are three-fold: (1) our work is one of the initial studies on personalized product search; (2) our hierarchical embedding model is the first latent space model that jointly learns distributed representations for queries, products and users with a deep neural network; (3) each component of our network is designed as a generative model so that the whole structure is explainable and extendable. Following the methodology of previous studies, we constructed personalized product search benchmarks with Amazon product data. Experiments show that our hierarchical embedding model significantly outperforms existing product search baselines on multiple benchmark datasets.

Abstract: Key frames are playing a very important role for many video applications, such as on-line movie preview and video information retrieval. Although a number of key frame selection methods have been proposed in the past, existing technologies mainly focus on how to precisely summarize the video content, but seldom take the user preferences into consideration. However, in real scenarios, people may cast diverse interests on the contents even for the same video, and thus they may be attracted by quite different key frames, which makes the selection of key frames an inherently personalized process. In this paper, we propose and investigate the problem of personalized key frame recommendation to bridge the above gap. To do so, we make use of video images and user time-synchronized comments to design a novel key frame recommender that can simultaneously model visual and textual features in a unified framework. By user personalization based on her/his previously reviewed frames and posted comments, we are able to encode different user interests in a unified multi-modal space, and can thus select key frames in a personalized manner, which, to the best of our knowledge, is the first time in the research field of video content analysis. Experimental results show that our method performs better than its competitors on various measures.

Abstract: Traditional e-Learning environments are based on static contents considering that all learners are similar, so they are not able to respond to each learner's needs. These systems are less adaptive and once a system that supports a particular strategy has been designed and implemented, it is less likely to change according to student's interactions and preferences. New educational systems should appear to ensure the personalization of learning contents. This work aims to develop a new personalization approach that provides to students the best learning materials according to their preferences, interests, background knowledge, and their memory capacity to store information. A new recommendation approach based on collaborative and content-based filtering is presented: NPR_eL (New multi-Personalized Recommender for e Learning). This approach was integrated in a learning environment in order to deliver personalized learning material. We demonstrate the effectiveness of our approach through the design, implementation, analysis and evaluation of a personal learning environment.

Abstract: Customized/personalized products are gaining more shares in today's product market. Such products need collective efforts from consumers, manufacturers and third parties. This requirement has not been well addressed due to both market and technology factors. On the other hand, the Internet of Things (IoT) provides real-time sensing/actuating ability and fast transmission capability of data/information, so that remote operation of manufacturing activities and efficient collaboration among stakeholders are greatly facilitated. This provides great opportunities to address the requirement mentioned above. Thus we propose a full-connection model of product design and manufacturing in the IoT-enabled cloud manufacturing environment. The proposed model uses social networks to connect multiple parties and facilitate open innovations, and use IoT to glue physical space to cyber space and cloud manufacturing to provide various elastic services, so that the on-demand workspace, interaction, information sharing or collective problem solving are enabled. We also propose a supporting infrastructure for this model using the latest information and communication technologies. Finally, we present a case study of an RFID enabled production system for customized and personalized product with the ability to enable a new paradigm of "dynamic processes and close collaborations among different roles" and ensure robust production.

Abstract: Purpose Banks and financial services providers are increasingly delivering their services via electronic banking, also known as e-banking. Yet even though this type of delivery is now common, the degree of personalization in the services provided via this channel exhibit considerable variation. The purpose of this paper is to examine the impact of service personalization on consumer reaction to the e-banking service. Based on research of information and communication technology (ICT) service innovation and the Unified Theory of Acceptance and Use of Technology (UTAUT) model, this study further examines one contingent factor, compatibility with previous experience with e-banking. This study focuses on the interactions effect of personalization and technology compatibility on customer e-banking service usage. Design/methodology/approach A survey was conducted to investigate the impacts of personalization on e-banking usage decision process and the interactions between personalization and compatibility with past e-banking experience. Quota sampling was applied and different type of customers were approached in 30 branches of the commercial bank. Data were collected from a sample of 181 banking customers in a metropolitan region in southern China. Findings The results indicated that personalization leads to increased performance expectancy and decreased effort expectancy, which in turn lead to increasing intention to continue to use e-banking services. In addition, compatibility with previous e-banking experience and personalization produces an interaction effect on both performance expectancy and effort expectancy. Research limitations/implications The theoretical contribution of this study is to demonstrate how the contingent factor of compatibility moderates the impact of personalization, thus extending the UTAUT model in the area of e-banking service adoption. Implications are twofold: personalization influences evaluations of both utility and ease of use, and the effect is magnified when compatibility with prior e-banking experience is factored into the model. This is an important extension and future research should examine whether the same relationship holds in other industries using new technologies to deliver services. The UTAUT model, after extension by including the moderating impact of compatibility, works well in demonstrating the impact of various factors on the adoption of a new technological delivery system for a service. Practical implications This study has two significant implications for managerial practices. First, the study sheds lights on the segmentation of e-banking customers. Modern marketers know that the best way to engage with consumers is through personal messaging strategies and should make great efforts to identify customers before trying to reach them. In the e-banking realm, consumer banking preferences keep changing. With a clear understanding of the different consumer banker segments, financial institutions can identify which channels appeal to them. For example, some users are more likely than average to use e-banking. Second, this study helps e-banking service provider design different personalized e-banking service for different customers. Social implications This study sheds light on social value of personalization, particularly among those new to a delivery platform. Originality/value This study provides evidence demonstrating that personalization increases customer perceptions of performance expectancy and decreases effort expectancy, and that the effect is most profound for customers with limited level of perceived compatibility with past experience with e-banking. This paper extended the UTAUT model and research on ICT service innovation by providing more insights on the impacts of e-banking service personalization and the contingency impact of user’s background in e-banking context.

Abstract: Despite the explosion of interest in big data in higher education and the ensuing rush for catch-all predictive algorithms, there has been relatively little focus on the pedagogical and pastoral contexts of learning. The provision of personalized feedback and support to students is often generalized and decontextualized, and examples of systems that enable contextualized support are notably absent from the learning analytics landscape. In this chapter we discuss the design and deployment of the Student Relationship Engagement System (SRES), a learning analytics system that is grounded primarily within the unique contexts of individual courses. The SRES, currently in use by teachers from 19 departments, takes a holistic and more human-centric view of data—one that puts the relationship between teacher and student at the center. Our approach means that teachers’ pedagogical expertise in recognizing meaningful data, identifying subgroups of students for a range of support actions, and designing and deploying these actions, is facilitated by a customizable technology platform. We describe a case study of the application of this human-centric approach to learning analytics, including its impacts on improving student engagement and outcomes, and debate the cultural, pedagogical, and technical aspects of learning analytics implementation.

Abstract: The field of advanced driver assistance systems (ADAS) has matured towards more and more complex assistance functions, applied with wider scope and a strongly increasing number of possible users due to wider market penetration. To deal with such a large variety of use conditions and usage patterns, personalization methods have been developed to ensure optimal user experience and supplied system function. In this paper we review personalization approaches for ADAS systems that target an adaptation to the drivers' preferences, driving styles, skills and driving patterns. We discuss the general assumptions on which personalization in the automotive context is based, the general design of personalized ADAS, the current approaches, and their practical realization and point out open issues in the design and implementation of a personalized driving experience.

Abstract: Mobile in-store advertising is becoming increasingly important, as it offers new options for retailers to communicate with customers at the point of sale. This study investigates how mobile in-store advertising should be designed in order to be most effective. The authors identify three value drivers (price promotion, location, and personalization) and examine their effect on customers’ purchase intention. The influence of the three value drivers was tested in a large-scale representative study with a laboratory experimental design. The findings indicate that all three value drivers increase purchase intention. Surprisingly, the authors find that price promotions are the least important value driver, whereas the location of receiving a mobile ad is the strongest driver of purchase intention. An interaction effect between location and personalization was also found to be significant. Personalization close to the product has little impact on purchase intention. The findings have important implications for researchers and retail managers, particularly when designing mobile in-store advertising campaigns.

Abstract: This research develops and tests a theoretical model of customer persuasion in personalized online shopping, building on information processing theory, and addressing cognitive and affective stages of the persuasion process. Data from 582 experienced online customers were used to validate the proposed model through structural equation modeling and multigroup analysis. Results show that quality of personalization, message quality, and benefits of the personalized recommendations are important in the persuasion process. Positive emotions increase the effect of persuasion on purchase intentions, contrary to negative emotions. The study extends online personalization theory, offers an in-depth analysis of the persuasion process in online shopping, and provides valuable recommendations for personalized online marketing.

Abstract: Query-based search is commonly used by many businesses to help consumers find information/products on their websites. Examples include search engines (Google, Bing), online retailers (Amazon, Macy's), and entertainment sites (Hulu, YouTube). Nevertheless, a significant portion of search sessions are unsuccessful, i.e., do not provide information that the user was looking for. We present a machine learning framework that improves the quality of search results through automated personalization based on a user's search history. Our framework consists of three modules -- (a) Feature generation, (b) NDCG-based LambdaMART algorithm, and (c) Feature selection wrapper. We estimate our framework on large-scale data from a leading search engine using Amazon EC2 servers. We show that our framework offers a significant improvement in search quality compared to non-personalized results. We also show that the returns to personalization are monotonically, but concavely increasing with the length of user history. Next, we find that personalization based on short-term history or "within-session" behavior is less valuable than long-term or "across-session" personalization. We also derive the value of different feature sets -- user-specific features contribute over 50% of the improvement and click-specific over 28%. Finally, we demonstrate scalability to big data and derive the set of optimal features that maximize accuracy while minimizing computing speed.

Abstract: Cold start remains a prominent problem in recommender systems. While rich content information is often available for both users and items few existing models can fully exploit it for personalization. Slow progress in this area can be partially attributed to the lack of publicly available benchmarks to validate and compare models. This year's ACM Recommender Systems Challenge' 17 aimed to address this gap by providing a standardized framework to benchmark cold start models. The challenge organizer XING released a large scaled data collection of user-job interactions from their career oriented social network. Unlike other competitions, here the participating teams were evaluated in two phases -- offline and online. Models were first evaluated on the held-out offline test set. Top models were then A/B tested in the online phase where new target users and items were released daily and recommendations were pushed into XING's live production system. In this paper we present our approach to this challenge, we used a combination of content and neighbor-based models winning both offline and online phases. Our model produced the most consistent online performance wining four of the five online weeks, and showed excellent generalization in the live A/B setting.

Abstract: Research for the generation of reliable recommendations has been the main goal focused by many researchers in recent years. Though many recommendation approaches have been developed to assist users in the selection of their interesting items in the online world, still the personalization problem exists. In this paper, we present a new recommendation approach to address the problems such as scalability, sparsity, and cold-start in a collective way. We have developed a knowledge-based domain specific ontology for the generation of personalized recommendations. We have also introduced two different ontology-based predictive models as minion representation model and prominent representation model for the effective generation of recommendations to all types of users. The prediction models are induced by data mining algorithms by correlating the user preferences and features of items for user modeling. We have proposed a new variant of KNN algorithm as Adaptive KNN for the collaborative filtering based recommender system. The proposed recommendation approach is validated with standard MovieLens dataset and obtained results are evaluated with Precision, Recall, F-Measure, and Accuracy. The experimental results had proved the better performance of our proposed AKNN algorithm over other algorithms with the highly sparse data taken for the recommendation generation.

Abstract: An efficient post-processing scheme for recommendation lists is proposed.It can adjust quality factors, like diversity, of a list to match user tendencies.Compromises on accuracy are kept low.The method is compared with other post-processing algorithms from the literature.It can be used to build novel fine-grained personalization approaches. Recommender systems are among the most visible applications of intelligent systems technology in practice and are used to help users find items of interest, for example on e-commerce sites, in a personalized way. While past research has focused mainly on accurately predicting the relevance of items that are unknown to the user, other quality criteria for recommendations have been investigated in recent years, including diversity, novelty, or serendipity. Considering these additional factors, however, often leads to the following two challenges. First, in many application domains, trade-offs like diversity vs.accuracy have to be balanced. Second, it is not always clear how much diversity or novelty is desirable in practice.In this work, we propose a novel parameterizable optimization scheme that re-ranks accuracy-optimized recommendation lists in order to cope with these challenges. Our method is both capable of considering multiple optimization goals at the same time and designed to consider individual user tendencies regarding the different quality factors, like diversity. In contrast to previous work, the method is not restricted to a specific underlying item ranking algorithm and its generic design allows the algorithm to be parameterized according to the requirements of the application domain. Experimental evaluations with different datasets show that balancing the quality factors with our method can be done with a marginal or no loss in ranking accuracy. Given that our method can be applied in various domains and within the narrow time constraints of online recommendation, our work opens new opportunities to design novel finer-grained personalization approaches in practical applications.

Abstract: We study the problem of learning to choose from m discrete treatment options (e.g., news item or medical drug) the one with best causal effect for a particular instance (e.g., user or patient) where the training data consists of passive observations of covariates, treatment, and the outcome of the treatment. The standard approach to this problem is regress and compare: split the training data by treatment, fit a regression model in each split, and, for a new instance, predict all m outcomes and pick the best. By reformulating the problem as a single learning task rather than m separate ones, we propose a new approach based on recursively partitioning the data into regimes where different treatments are optimal. We extend this approach to an optimal partitioning approach that finds a globally optimal partition, achieving a compact, interpretable, and impactful personalization model. We develop new tools for validating and evaluating personalization models on observational data and use these to demonstrate the power of our novel approaches in a personalized medicine and a job training application.

Abstract: Gamification has been used in a variety of application domains to promote behaviour change. Nevertheless, the mechanisms behind it are still not fully understood. Recent empirical results have shown that personalized approaches can potentially achieve better results than generic approaches. However, we still lack a general framework for building personalized gameful applications. To address this gap, we present a novel general framework for personalized gameful applications using recommender systems (i.e., software tools and technologies to recommend suggestions to users that they might enjoy). This framework contributes to understanding and building effective persuasive and gameful applications by describing the different building blocks of a recommender system (users, items, and transactions) in a personalized gamification context.