This master thesis is focused on business environment in China from the perspective of Czech companies. The theoretical part represents basic informations that are good to know for every entrepreneur who is thinking about exporting to China. First, it introduces chinese economic situation from historical and contemporary perspective and its cooperation with the Czech Republic. Subsequently there is a describtion of industries, which still bring opportunities for Czech companies. At the end this part maps the participation of Czech companies in the Chinese market.The second part of the theory focuses on describing the opportunities to enter the Chinese market and also on how to deal with Chinese enterpreneurs. From European perspective is Chinese market still very different and it could lead to misunderstandings and business problems. Practical part of the work is to focus on a few Czech companies to describe their experience with the Chinese market and highlight the advice for other companies. Final part includes selected recommendations for enterpreneurs, which are based on interviews and questionnaires of Czech export managers dealing with China.

Today, commercial industry spends huge amount of resources in advertisement campaigns, new marketing strategies, and promotional deals to introduce their product to public and attract a large number of customers. These massive investments by a company are worthwhile because marketing tactics greatly influence the consumer behavior. Alternatively, these advertising campaigns have a discernible impact on recommendation systems which tend to promote popular items by ranking them at the top, resulting in biased and unfair decision making and loss of customers’ trust. The biasing impact of popularity of items on recommendations, however, is not fixed, and varies with time. Therefore, it is important to build a bias-aware recommendation system that can rank or predict items based on their true merit at given time frame. This thesis proposes a framework that can model the temporal bias of individual items defined by their characteristic contents, and provides a simple process for bias correction. Bias correction is done either by cleaning the bias from historical training data that is used for building predictive model, or by ignoring the estimated bias from the predictions of a standard predictor. Evaluated on two real world datasets, NetFlix and MovieLens, our framework is shown to be able to estimate and remove the bias as a result of adopted marketing techniques from the predicted popularity of items at a given time.

L'exploitation, a posteriori, des données médicales accumulées par les praticiens représente un enjeu majeur pour la recherche clinique comme pour le suivi personnalisé du patient. Toutefois les professionnels de santé manquent d'outils adaptés leur permettant d'explorer, comprendre et manipuler aisément leur données. Dans ce but, nous proposons un algorithme de structuration d'éléments par similarité et représentativité. Cette méthode permet de regrouper les individus d'un jeu de données autour de membres représentatifs et génériques aptes à subsumer les éléments et résumer les données. Cette méthode, procédant dimension par dimension avant d'agréger les résultats, est adaptée aux données en haute dimension et propose de plus des résultats transparents, interprétables et explicables. Les résultats obtenus favorisent l'analyse exploratoire et le raisonnement par analogie via une navigation de proche en proche : la structure obtenue est en effet similaire à l'organisation des connaissances utilisée par les experts lors du processus décisionnel qu'ils emploient. Nous proposons ensuite un algorithme de détection d'anomalies qui permet de détecter des anomalies complexes et en haute dimensionnalité en analysant des projections sur deux dimensions. Cette approche propose elle aussi des résultats interprétables. Nous évaluons ensuite ces deux algorithmes sur des données réelles et simulées dont les éléments sont décrits par de nombreuses variables : de quelques dizaines à plusieurs milliers. Nous analysant particulièrement les propriétés du graphe résultant de la structuration des éléments. Nous décrivons par la suite un outil de prétraitement de données médicales ainsi qu'une plateforme web destinée aux médecins. Via cet outil à l'utilisation intuitif nous proposons de structurer de manière visuelle les éléments pour faciliter leur exploration. Ce prototype fournit une aide à la décision et au diagnostique médical en permettant au médecin de naviguer au sein des données et d'explorer des patients similaires. Cela peut aussi permettre de vérifier des hypothèses cliniques sur une cohorte de patients. / A posteriori use of medical data accumulated by practitioners represents a major challenge for clinical research as well as for personalized patient follow-up. However, health professionals lack the appropriate tools to easily explore, understand and manipulate their data. To solve this, we propose an algorithm to structure elements by similarity and representativeness. This method allows individuals in a dataset to be grouped around representative and generic members who are able to subsume the elements and summarize the data. This approach processes each dimension individually before aggregating the results and is adapted to high-dimensional data and also offers transparent, interpretable and explainable results. The results we obtain are suitable for exploratory analysis and reasoning by analogy: the structure is similar to the organization of knowledge and decision-making process used by experts. We then propose an anomaly detection algorithm that allows complex and high-dimensional anomalies to be detected by analyzing two-dimensional projections. This approach also provides interpretable results. We evaluate these two algorithms on real and simulated high-dimensional data with up to thousands of dimensions. We analyze the properties of graphs resulting from the structuring of elements. We then describe a medical data pre-processing tool and a web application for physicians. Through this intuitive tool, we propose a visual structure of the elements to ease the exploration. This decision support prototype assists medical diagnosis by allowing the physician to navigate through the data and explore similar patients. It can also be used to test clinical hypotheses on a cohort of patients.

Autism spectrum disorder (ASD) is a long-standing mental condition characterized by hindered mental growth and development. In 2018, 168 out of 10,000 children are said to be affected with Autism in the USA. As these children move to adulthood, they have difficulty in communicating with others, expressing themselves, maintaining eye contact, developing a well-functioning motor skill or sensory sensitivity, and paying attention for longer period. Some of these abnormalities, however, can be gradually improved if they are treated appropriately during their adulthood. Studies have shown that people with ASD can enhance their social-interactive skills by playing video games. During the past decades, however, educational games have been primarily developed for autistic children, but not for autistic adults. We have developed a gaming and recommendation system that suggests therapeutic games to autistic adults which can improve their social-interactive skills. The gaming system maintains the entertainment value of the games, to make sure people are interested in playing them, whereas the recommendation system suggests appropriate games for autistic adults to play. Customizable games are designed and implemented in Minecraft such that each game focuses on enhancing different weakness areas in autistic adults based on games that the users have not explored in the past. The effectiveness of the gaming and recommendation system is backed up by an empirical study which shows that recommending therapeutic games can aid in the improvement of social-interactive skills of adults with ASD so that they can live a better life in the years to come.

Spotify is currently the worlds leading music streaming ser-vice. As the leader in music streaming the task of providing listeners with music recommendations is vital for Spotify. Listening to playlists is a popular way of consuming music, but traditional recommender systems tend to fo-cus on suggesting songs, albums or artists rather than pro-viding consumers with playlists generated for their needs. This thesis presents a scalable and generalizeable approach to music recommendation that performs song selection for the problem of playlist generation. The approach selects tracks related to a playlist theme by finding the charac-terizing variance for a seed playlist and projects candidate songs into the corresponding subspace. Quantitative re-sults shows that the model outperforms a baseline which is taking the full variance into account. By qualitative results the model is also shown to outperform professionally curated playlists in some cases.

This thesis report describes an attempt to build a recommender system for recommending sporting goods in an e-commerce setting, using the customer purchase history as the input dataset. Two input datasets were considered, the item purchases dataset and the item-category dataset. Both the datasets are implicit, that is not explicitly rated by the customer. The data is also very sparse that very few users have purchased more than a handful of the items featured in the dataset. The report describes a method for dealing with both the implicit datasets as well as addressing the problem of sparsity. The report introduces SVD (Single Value Decomposition) with matrix factorization as a implementation for recommendation systems. Specifically implementations in the Apache Mahout machine learning framework. / Denna rapport beskriver ett tillvägagångssätt för att med kundernas köphistorik bygga ett rekommendationssystem för rekommendation av sportprodukter på en e-handelsplats. Två olika datamängder behandlas, köphistorik per produkt och kund, samt köpfrekvensen per produktkategori per kund i köphistoriken. Båda är implicita datamängder, vilket betyder att kunderna inte har explicit uttryckt en åsikt för eller emot produkten, utan implicit uttrycker preferens genom sitt köp. Datan är även mycket gles, vilket betyder att den enskilda kunden generellt bara köpt en liten del av den totala mängden av sålda varor. Rapporten behandlar en metod som behandlar både den implicita karaktären av data och gleshets problemet. Rapporten introducerar SVD (Single Value Decomposition) med matrisfaktorisering som en metod för att implementera rekommendationssystem. Specifikt implementerat med hjälp av maskininlärningsbiblioteket Apache Mahout.

Indiana University-Purdue University Indianapolis (IUPUI) / This dissertation proposes a framework (TruSStReMark - Trust-based Service Selection and Recommendation for Online Software Marketplaces) to model, quantify, and monitor trust of software services and to perform trust-based service selection and recommendations. It provides methods to analyze and aggregate external reviews, pertaining to specific QoS attributes, of software services by performing subjective logic-based operations. This framework, first, defines trust of a software service using theory of belief and extends the multi-level software specifications to represent the trust-based attributes. It, then, proposes enhancements to two prevalent algorithms for selecting and recommending software services from a marketplace. Finally, the performances of the enhanced selection and recommendation algorithms are improved by parallelizing them. When compared with the prevalent Content-based and Collaborative filtering-based approaches, the results show that, the TruSStReMark is able to produce better results in terms of quality measured using HR (Hit Ratio) and ARHR (Average Reciprocal Hit-Rank) metrics. In addition, the parallelized versions of the trust-based selection and recommendation algorithms improve the end-to-end runtime. The TruSStReMark will enable users to select services, which are trustworthy, from online software marketplaces and use them in composing quality-aware distributed systems.

Indiana University-Purdue University Indianapolis (IUPUI) / As the amount of information grows, the desire to efficiently filter out unnecessary information and retain relevant or interested information for people is increasing. To extract the information that will be of interest to people efficiently, we can utilize recommender systems. Recommender systems are information filtering systems that predict the preference of a user to an item. Based on historical data of users, recommender systems are able to make relevant recommendations to users. Due to its usefulness, Recommender systems have been widely used in many applications, including e-commerce and healthcare information systems. However, existing recommender systems suffer from several issues, including data sparsity and user/item heterogeneity. In this thesis, a hybrid dynamic and multi-collaborative filtering based recommendation technique has been developed to recommend search terms for physicians when physicians review a large number of patients’ information. Besides, a local sparse linear method ensemble has been developed to tackle the issues of data sparsity and user/item heterogeneity. In health information technology systems, most physicians suffer from information overload when they review patient information. A novel hybrid dynamic and multi-collaborative filtering method has been developed to improve information retrieval from electronic health records. We tackle the problem of recommending the next search term to a physician while the physician is searching for information about a patient. In this method, I have combined first-order Markov Chain and multi-collaborative filtering methods. For multi-collaborative filtering methods, I have developed the physician-patient collaborative filtering and transition-involved collaborative filtering methods. The developed method is tested using electronic health record data from the Indiana Network for Patient Care. The experimental results demonstrate that for 46.7% of test cases, this new method is able to correctly prioritize relevant information among top-5 recommendations that physicians are truly interested in. The local sparse linear model ensemble has been developed to tackle both the data sparsity and the user/item heterogeneity issues for the top-n recommendation. Multiple local sparse linear models are learned for all the users and items in the system. I have developed similarity-based and popularity-based methods to determine the local training data for each local model. Each local model is trained on Sparse Linear Method (SLIM) which is a powerful recommendation technique for top-n recommendation. These learned models are then combined in various ways to produce top-N recommendations. I have developed model results combination and model combination methods to combine all learned local models. The developed methods are tested on a benchmark dataset and its sparsified datasets. The experiments demonstrate 18.4% improvement from such ensemble models, particularly on sparse datasets.

Recommendation systems are primarily used in e-commerce and retail to guide the user in a vast space of available items by providing personalized recommendations that fit the user's interests and need. Numerous types of recommendation systems have been introduced over the years. The most recent development in the field is the sequential recommendation system. Sequential recommenders account for the order in which the user has interacted with items to infer the user's intent, allowing them to provide recommendations accordingly. The data analytic company Siftlab AB has already developed such a recommendation system; however, its application has been limited to transaction data(data depicting only purchases). As a result, the model cannot take advantage of the predictive values of different event types. This thesis introduces a weighted multi-type technique that allows Siftlab's recommendation model to leverage page views alongside purchases in data from an interior design store. We also developed tools and techniques, such as correlation and angle separation analysis, to enhance our examination of user-item behavior. Our research findings indicate that including page view events in training hurts recall, while their inclusion in the prediction stage yields slight improvements. We discovered a rapid decline in correlation between purchases and page views as we considered page views occurring relatively further back in time. Performing a time-based correlation analysis, it became evident that there is a robust time dependency between purchases and page views. Utilizing this time dependency, we enforced a time-dependent threshold on the page views we included in the prediction stage to eliminate irrelevant page view events, further enhancing the model's predictions. We also captured seasonalities phenomena distinctive for an interior design store. Although the result of this work might only be valid for a single data set, we anticipate our work to be the first step in the right direction since the technique we introduce here can be effortlessly adapted to analyze other event types in other data, thus uncovering patterns that can further elevate the model's performance.

Reading is a fundamental skill that each person needs to develop during early childhood and continue to enhance into adulthood. While children/teenagers depend on this skill to advance academically and become educated individuals, adults are expected to acquire a certain level of proficiency in reading so that they can engage in social/civic activities and successfully participate in the workforce. A step towards assisting individuals to become lifelong readers is to provide them adequate reading selections which can cultivate their intellectual and emotional growth. Turning to (web) search engines for such reading choices can be overwhelming, given the huge volume of reading materials offered as a result of a search. An alternative is to rely on reading materials suggested by existing recommendation systems, which unfortunately are not capable of simultaneously matching the information needs, preferences, and reading abilities of individual readers. In this dissertation, we present novel recommendation strategies which identify appealing reading materials that the readers can comprehend, which in turn can motivate them to read. In accomplishing this task, we have examined used-defined data, in addition to information retrieved/inferred from reputable and freely-accessible online sources. We have incorporated the concept of “social trust” when making recommendations for advanced readers and suggested fiction books that match the reading ability of individual K-12 readers using our readability-analysis tool for books. Furthermore, we have emulated the readers' advisory service offered at school/public libraries in making recommendations for K-12 readers, which can be applied to advanced readers as well. A major contribution of our work is in the development of unsupervised recommendation strategies for advanced readers which suggest reading materials for both entertainment and learning acquisition purposes. Unlike their counterparts, these recommendation strategies are unaffected by the cold-start or long-tail problems, since they exploit user-defined data (if available) while taking advantage of alternative publicly-available metadata. Our readability-analysis tool is innovative, which can predict the readability-levels of books on-the-fly, even in the absence of excerpts from books, a task that cannot be accomplished by any of the well-known readability tools/strategies. Moreover, our multi-dimensional recommendation strategy is novel, since it simultaneously analyzes the reading abilities of K-12 readers, which books readers enjoy, why the books are appealing to them, and what subject matters the readers favor. Besides assisting K-12 readers, our recommender can be used by parents/teachers/librarians in locating reading materials to be suggested to their (K-12) children/students/patrons. We have validated the performance of each methodology presented in this dissertation using existing benchmark datasets or datasets we created for the evaluation purpose (which is another contribution we make to the research community). We have also compared the performance of our proposed methodologies with their corresponding baselines and state-of-the-art counterparts, which further verifies the correctness of the proposed methodologies.