Note:

隨着在線電子商務網站，音樂視頻網站和社會性共享推薦網站的迅速發展，網站用戶面臨爆炸性增長的選擇。前所未見的大量選擇導致信息過載問題。信息過載問題是指由於存在數量巨大的信息，用戶不能有效的理解並做出選擇的問題。推薦系統是解決信息過載問題的一個關鍵組成部分。過去數十年，推薦系統技術有了長足的進步。研究重點又基於臨近用戶的方法向基於模型的方法過度。然而，推薦系統仍然不夠成熟完善。在本論文中，我們基於真實生活中遇到的問題提出改善推薦系統的方法。 / 首先，我們提出推薦系統的在線學習算法。傳統推薦系統使用批量式學習算法進行訓練。這些方法容易理解並且容易實現。然而批量式學習算法不能有效應對當今推薦系統所面臨的動態情況。新的用戶和新的物品不斷加入推薦系統。在批量式學習算法框架下，要將這些新用戶新物品納入系統，需要對所有數據進行重新學習。另外，在批量式學習算法的每一個步驟中，我們需要處理所有的數據。在現今推薦系統規模下，這通常是非常耗時的。在線學習算法可以通過對每一個數據點調整模型而解決上述兩個問題。 / 其次，我們深入調查大量推薦系統所作的一個假設。該假設默認推薦系統蒐集的打分數據的分佈和未蒐集到的打分數據的分佈是完全一致的。我們使用在真實推薦系統中蒐集的數據證明這個假設極不可能爲真。使用失數據理論的方法，我們提出一個不基於改假設的模型。我們的模型放棄了這個假設並且能夠得到公正的推薦。 / 再次，我們詳細調研推薦系統中的垃圾用戶問題。垃圾用戶的打分會污染正常用戶的數據並導致正常用戶的體驗受到影響。我們提出使用用戶聲譽系統去記錄用戶的聲譽並利用用戶的聲譽去區分垃圾用戶和正常用戶。我們提出一個聲譽生成系統的框架。許多聲譽生成系統是我們聲譽生成系統框架的一個實做。基於該框架，我們還提出一個基於矩陣分解的用戶聲譽生成系統。該系統擁有出衆的分辨垃圾用戶的能力。 / 最後，我們將基於內容的推薦和協同過濾推薦有機結合以便減輕乃至解決冷啓動問題。冷啓動問題是指推薦系統中關於某個用戶或物品的信息是如此之少以至於系統不能對該用戶或改物品做出有效的推薦。用戶的文字性評價中通常包含大量用戶喜好和物品屬性信息。但用戶的文字性評價通常都被直接棄。我們提出一個同時使用基於內容的方法去處理用戶文字性評價信息，使用協同過濾方法處理用戶打分的整合式推薦模型。我們的模型能有效減輕冷啓動問題的影響並且對黑盒協同過濾算法提供可理解的詞彙標籤。這些標籤有助於幫助推薦系統提供推薦的原因。 / 綜上所述，在本論文中我們解決了推薦系統面臨的實際問題並從各個方面對傳統推薦系統進行改進。大量真實數據上的實驗驗證我們提出方法的有效性和高效性。 / With the rapid development of e-commerce websites, music and video streaming websites and social sharing websites, users are facing an explosion of choices nowadays. The presence of unprecedentedly large amount of choices leads to the information overload problem, which refers to the difficulty a user faces in understanding an issue and making decisions that are caused by the presence of too much information. Recommender systems learn users’ preferences based on past behaviors and make suggestions for them. These systems are the key component to alleviate and solve the information overload problem. Encouraging progress has been achieved in the research of recommender systems from neighborhood-based methods to model-based methods. However, recommender systems employed today are far from perfect. In this thesis, we propose to improve the recommender systems from four perspectives motivated by real life problems. / First and foremost, we develop online algorithms for collaborative filtering methods, which are widely applicable to recommender systems. Traditionally batch-training algorithms are developed for collaborative filtering methods. They enjoy the advantage of easy to understand and simple to implement. However, the batch-training algorithms fail to consider the dynamic scenario where new users and new items join the system constantly. In order to make recommendations for these new users and on these new items, batchtraining algorithms need to re-train the model from scratch. During the training process of batch-training algorithms, all the data have to be processed in each iteration. This is prohibitively slow given the sheer size of users and items faced by a real recommender system. Online learning algorithms can solve both of the problems by updating the model incrementally based on a rating point. / Secondly, we question an assumption made implicitly by most recommender systems. Most existing recommender systems assume that the rating distribution of collected ratings and that of the unobserved ratings are the same. Using data collected from a real life recommender system, we show that this assumption is unlikely to be true. By employing the powerful missing data theory, we develop a model that drops this unrealistic assumption and makes unbiased predictions. / Thirdly we examine the spam problem confronted by recommender systems. The ratings assigned by spam users contaminate the data of a recommender system and lead to deteriorated experience for normal users. We propose to use a reputation estimation system to keep track of users’ reputations and identify spam users based on their reputations. We develop a unified framework for reputation estimation that subsumes a number of existing reputation estimation methods. Based on the framework, we also develop a matrix factorization based method that demonstrates outstanding discrimination ability. / Lastly, we integrate content-based filtering with collaborative filtering to alleviate the cold-start problem. The cold-start problem refers to the situation where a system has too little information concerning a user or an item to make accurate recommendations. With the readily available rich information embedded in review comments, which are generally discarded, we can alleviate the cold-start problem. Additionally, we can tag the black box collaborative filtering algorithm with interpretable tags that help a recommender system to provide reasons on why items are being recommended. / In summary, we solve some of the major problems faced by recommender systems and improve them from various perspectives in this thesis. Extensive experiments on real life large-scale datasets confirm the effectiveness and efficiency of proposed models. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Detailed summary in vernacular field only. / Ling, Guang. / Thesis (Ph.D.) Chinese University of Hong Kong, 2015. / Includes bibliographical references (leaves 169-184). / Abstracts also in Chinese. / Ling, Guang.

Thesis (M.S.)--Worcester Polytechnic Institute. / Keywords: Data recency problem; Recommender system; Time-based forgetting function; Time-based forgetting strategy; Collaborative filtering system. Includes bibliographical references (p. 73-74).

Many consumer facing companies have large scale data sets that they use to create recommendations for their users. These recommendations are usually based off information the company has on the user and on the item in question. Based on these two sets of features, models are created and tuned to produce the best possible recommendations. A third set of data that exists in most cases is the presence of past interactions a user may have had with other items. The relationships that a model can identify between this information and the other two types of data, we believe, can improve the prediction of how a user may interact with the given item. We propose a method that can inform the model of these relationships during the training phase while only relying on the user and item data during the prediction phase. Using ideas from convolutional neural networks (CNN) and collaborative filtering approaches, our method manipulated the weights in the first layer of our network design in a way that achieves this goal.

As interest in family history research increases, greater numbers of amateurs are participating in genealogy. However, finding sources that provide useful information on individuals in genealogical research is often an overwhelming task, even for experts. Many tools assist genealogists in their work, including many computer-based systems. Prior to this work, recommender systems had not yet been applied to genealogy, though their ability to navigate patterns in large amounts of data holds great promise for the genealogical domain. We create the Family History Source Recommender System to mimic human behavior in locating sources of genealogical information. The recommender system is seeded with existing source data from the FamilySearch database. The typical recommender systems algorithms are not designed for family history work, so we adjust them to fit the problem. In particular, recommendations are created for deceased individuals, with multiple users being able to consume the same recommendations. Additionally, our similarity computation takes into account as much information about individuals as possible in order to create connections that would otherwise not exist. We use offline n-fold cross-validation to validate the results. The system provides results with high accuracy.

Recommender systems have gained a lot of popularity in recent times dueto their application in the wide range of fields. Recommender systems areintended to support users in finding the relevant items based on their interestsand preferences. Recommender algorithms proposed by researchersevolved over time from simple matching recommendations to machine learningalgorithms. One such class of algorithms with increasing focus is oncalled streaming recommender systems, these algorithms treat input data asa stream of events and make recommendations. To evaluate the algorithmsthat work with continuous data streams, stream-based evaluation techniquesare needed. So far, less interest is shown in the research so far on the evaluationof recommender systems in streaming environments.In this thesis, a simple evaluation framework named StreamER that evaluatesrecommender algorithms that work on streaming data is proposed.StreamER is intended for the rapid prototyping and evaluation of incrementalalgorithms. StreamER is designed and implemented using object-orientedarchitecture to make it more flexible and expandable. StreamER can beconfigured via a configuration file, which can configure algorithms, metricsand other properties individually. StreamER has inbuilt support for calculatingaccuracy metrics, namely click-through rate, precision, and recall.The popular-seller and random recommender are two algorithms supportedout of the box with StreamER. Evaluation of StreamER is performed via acombination of hypothesis and manual evaluation. Results have matched theproposed hypothesis, thereby successfully evaluating the proposed frameworkStreamER.

Identification based recommender systems make no distinction between users and accounts; all the data collected during account sessions are attributed to a single user. In reality this is not necessarily true for all accounts; several different users who have distinct, and possibly very different, preferences may access the same account. Such accounts are identified as multi-user accounts. Strangely, no serious study considering the existence of multi-user accounts in recommender systems has been undertaken. This report quantifies the affect multi-user accounts have on the predictive capabilities of recommender system, focusing on two popular collaborative filtering algorithms, the kNN user-based and item-based models. The results indicate that while the item-based model is largely resistant to multi-user account corruption the quality of predictions generated by the user-based model is significantly degraded. / text

This thesis describes work on using content to improve recommendation systems. Personalised recommendations help potential buyers filter information and identify products that they might be interested in. Current recommender systems are based mainly on collaborative filtering (CF) methods, which suffer from two main problems: (1) the ramp-up problem, where items that do not have a sufficient amount of meta-data associated with them cannot be recommended; and (2) lack of transparency due to the fact that recommendations produced by the system are not clearly explained. In this thesis we tackle both of these problems. We outline a framework for generating more accurate recommendations that are based solely on available textual content or in combination with rating information. In particular, we show how content in the form of social tags can help improve recommendations in the book and movie domains. We address the ramp-up problem and show how in cases where they do not exist, social tags can be automatically predicted from available textual content, such as the full texts of books. We evaluate our methods using two sets of data that differ in product type and size. Finally we show how once products are selected to be recommended, social tags can be used to explain the recommendations. We conduct a web-based study to evaluate different styles of explanations and demonstrate how tag-based explanations outperform a common CF-based explanation and how a textual review-like explanation yields the best results in helping users predict how much they will like the recommended items.

As recommender systems have increasingly become prevalent to guide consumers to find their desired products in many industries, understanding the impact of recommender systems on consumer choices is critical to the business performance and raises important policy implications. In this thesis, we examine the role of different recommendation schemes, spanning from interpersonal recommendations in social environment given by peers to product display recommendations in physical shopping environment given by sellers on consumers’ switching and search behavior in two distinct case studies. In the first study, we look at the effect of peer recommendations on subscriber churn in a large mobile network. We find that consumers’ propensity to churn increases with the number of friends that churn and in particular with the number of strong friends that churn. In the second study, we implement an in-vivo randomized field experiment to measure the effect of product display recommendations as book placement on shopper behavior in a physical bookstore. We leverage video tracking technologies to monitor how shoppers respond to random book placement, which induces random search costs. We find that books recommended at the edge of the table are more likely to be picked and taken than those placed at the center of the table. More interestingly, we also find that conditional on being picked, shoppers are equally likely to take books placed at the edge and at the center of the table, suggesting that display recommendations positively affect consumer choice mainly through its effect on the search process and not through its effect on the consideration process. Therefore, we empirically show that provision of recommendations, although in different schemes, may generally help to reduce consumers’ search costs in product or service discovery process, relative to what they would do without such an intervention. Moreover, we perform a comparative analysis between offline and online applications of recommender systems to systematically investigate the current practices, future prospects and policy perspectives when applying recommender systems in physical retailing. All these issues highlight opportunities for physical retailers to design, implement and evaluate their recommender systems that offer convenience benefits and appropriate protection to consumers.

(1) Relational fusion of multiple features for the classical regression task (single measure and dimension). Originally, the task of recommender systems is formulated as a regression task. Many CF algorithms and fusion methods have been proposed. The limitation of previous fusion methods is that only local features are utilized and the global relational dependency is ignored, which would impair the performance of CF. We propose a relational fusion approach based on conditional random fields (CRF) to improve traditional fusion methods by incorporating global relational dependency. / (2) Fusion of regression-oriented and ranking-oriented algorithms for multi-measure adaption. Beyond the level of classical regression, ranking the items directly is another important task for recommender systems. A good algorithm should adapt to both regression-oriented and ranking-oriented measures. Traditionally, algorithms separately adapt to a single one, thus they cannot adapt to the other. We propose methods to combine them to improve the performances in both measures. / (3) Fusion of quality-based and relevance-based algorithms for multi-dimensional adaption. Recommender systems should consider the performances of multiple dimensions, such as quality and relevance. Traditional algorithms, however, only recommend either high-quality or high-relevance items. But they cannot adapt to the other dimension. We propose both fusion metrics and fusion approaches to effectively combine multiple dimensions for better performance in multi-dimensional recommendations. / (4) Investigation of impression efficiency optimization in recommendation. Besides performance, impression efficiency, which describes how much profit can be obtained per impression of recommendation, is also a very important issue. From recent study, over-quantity recommendation impression is intrusive to users. Thus the impression efficiency should be formulated and optimized. But this issue has rarely been investigated. We formulate the issue under the classical secretary problem framework and extend an online secretary algorithm to solve it. / Recommender systems are important nowadays. With the explosive growth of resources on the Web, users encounter information overload problem. The research issue of recommender systems is a kind of information filtering technique that suggests user-interested items (e.g., movies, books, products, etc.) to solve this problem. Collaborative filtering (CF) is the key approach. Over the decades, recommender systems have been demonstrated important in E-business. Thus designing accurate algorithms for recommender systems has attracted much attention. / This thesis is to investigate effective fusion-based approaches for recommender systems. Effective fusion of various features and algorithms becomes important along with the development of recommendation techniques. Because each feature/algorithm has its own advantages and disadvantages. A combination to get the best performance is desired in applications. The fusion-based approaches investigated are from the following four levels. / Xin, Xin. / Advisers: Wai Lam; Irwin Kuo Chin King; Michael Rung Tsong Lyu. / Source: Dissertation Abstracts International, Volume: 73-06, Section: B, page: . / Thesis (Ph.D.)--Chinese University of Hong Kong, 2011. / Includes bibliographical references (leaves 152-172). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. [Ann Arbor, MI] : ProQuest Information and Learning, [201-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstract also in Chinese.