Submitted by Johnny Rodrigues (johnnyrodrigues@ufcg.edu.br) on 2018-05-01T13:20:15Z No. of bitstreams: 1 JANDERSON JASON BARBOSA AGUIAR - DISSERTAÇÃO PPGCC 2015..pdf: 4415910 bytes, checksum: f0d6a47b1a591745921f0dde35a45bb1 (MD5) / Made available in DSpace on 2018-05-01T13:20:15Z (GMT). No. of bitstreams: 1 JANDERSON JASON BARBOSA AGUIAR - DISSERTAÇÃO PPGCC 2015..pdf: 4415910 bytes, checksum: f0d6a47b1a591745921f0dde35a45bb1 (MD5) Previous issue date: 2015-08-25 / Capes / Os Objetos de Aprendizagem (OA) utilizados em cursos presenciais ou à distância são armazenados em ambientes computacionais usados no processo de ensino-aprendizagem com tendência de crescimento da sua quantidade com o passar do tempo. Apesar dos Sistemas de Recomendação (SR) serem atualmente utilizados com sucesso para recomendar itens em vários domínios, o contexto educacional possui particularidades (por exemplo, questões pedagógicas) que tornam ainda mais desafiadora a criação desses sistemas. A Personalidade — que pode ser definida como um padrão de comportamento consistente originado internamente no indivíduo — influencia o processo de tomada de decisão. Além disso, há a preocupação com os Estilos de Aprendizagem (EA), a partir dos quais os aprendizes percebem, processam e retêm as informações. Diante do exposto, a pesquisa ora descrita visa a propor um modelo de Sistema de Recomendação Educacional (SRE) utilizando os conceitos de EA e Personalidade na construção do perfil dos discentes, para realizar uma seleção personalizada de OA a serem recomendados. Embora ainda seja desafiador criar SRE envolvendo a extração e inserção dos conceitos psicológicos comentados, nesta dissertação é apresentado e avaliado um modelo que recomenda OA, seguindo o padrão IEEE LOM, a partir da extração dos EA via inventário ILS (Index of Learning Styles) e da extração dos Traços de Personalidade (TP) via Five Labs, ferramenta online de análise semântica de postagens do Facebook. Considerando métricas utilizadas em SR, um experimento realizado com alunos de Ciência da Computação indicou que o modelo proposto proporcionou resultados melhores ou similares, em comparação a outras abordagens de recomendação pesquisadas. Portanto, a abordagem proposta se mostra promissora para a recomendação personalizada de conteúdo no âmbito educacional. / Learning Objects (LO) used in on-site courses or distance learning are stored in computing environments used in the teaching-learning process, and tend to grow their numbers over time. Although Recommendation Systems (RS) are currently being used successfully to recommend items in various fields, the educational context has special features (for example, pedagogical issues) which make the creation of such systems even more challenging. The Personality — which can be defined as a consistent pattern of behavior originated internally in an individual — influences the decision-making process. In addition, there is concern with the Learning Styles (LS), through which learners perceive, process, and retain information. Based on the above considerations, this research aims to propose a model of RS for Learning (RSL) using the concepts of LS and Personality in building the profile of students, in order to make a custom selection of LO to be recommended. Although it is still challenging to create RSL involving the extraction and insertion of psychological concepts as previously mentioned, in this dissertation a model that recommends LO is presented and evaluated, following the IEEE LOM standard, based on the extraction of LS via Index of Learning Styles and of Personality Traits (PT) via Five Labs, an online tool for semantic analysis of Facebook posts. Considering metrics known in RS, an experiment with computer science students indicated that the proposed model provided similar or better results when compared to other recommendation approaches. Therefore, the proposed approach seems promising for personalized content recommendation in the education field.

Como os interagentes selecionam conteúdo sob a influência dos sistemas de recomendação digital é o problema de pesquisa apresentado nesta tese. A abundância de dados nos repositórios digitais exige sistemas de recuperação de informação eficazes para auxiliar o usuário na gestão e na seleção de itens de informação. Desta forma, o objetivo geral deste trabalho pretende investigar o comportamento dos interagentes na seleção de itens frente ao sistema de recomendação digital do website da loja virtual Amazon. O sistema de recomendação da Amazon foi investigado com a intenção de se compreender como o usuário utiliza um sistema automatizado de listas de referências em forma de recomendação de conteúdo. O funcionamento dos sistemas de recomendação é fundamentado com a proposta de conhecer suas características e funcionalidades. Como o problema de pesquisa tem em sua temática a recomendação de itens de informação, tornou-se necessário compreender como os usuários interagem com os sistemas para perceber como as recomendações são feitas. O aporte teórico desta pesquisa aproxima os estudos dos campos da Informação e da Comunicação. As técnicas de pesquisas aplicadas envolvem métodos de pesquisa qualitativa. Ao distinguir as recomendações a partir das interações reativas e mútuas dos usuários, propõe-se nesta tese a Matriz de Recomendações de Itens de Informação constituída pelos seguintes quadrantes: Recomendações Objetivas Digitais; Recomendações Subjetivas Digitais; Recomendações Objetivas Analógicas e Recomendações Subjetivas Analógicas. Digitais; Recomendações Objetivas Analógicas e Recomendações Subjetivas Analógicas. Para analisar o comportamento dos interagentes no uso dessas recomendações, a estratégia metodológica aplicou entrevista em profundidade e observação direta. Os resultados desta pesquisa consideram que o internauta recorre a mais de um tipo de recomendação quando a seleção envolve conteúdo significativo, enquanto segue passivamente sistemas de recomendações automatizados quando o custo pessoal diretamente aplicado é baixo ou inexistente. / As the interacting select content under the influence of digital recommender systems is the research problem presented in this thesis. The abundance of data in digital repositories recovery requires effective information systems to assist the user in the management and selection of information items. Thus, the objective of this study was to investigate the behavior of the interacting in the selection of digital items across the recommendation of the Amazon’s bookshop website. The Amazon's recommendation system was investigated with the aim of understanding how the user uses an automated reference lists in the form of content recommendation. The performance of recommender systems is founded with the purpose of knowing their characteristics and functionalities. As the research problem is in your subject to the recommendation of information items, it became necessary to understand how users interact with this system to understand how the recommendations are made. The theoretical contribution of this research approaches the fields of Information and Communication. The technique applied involves qualitative research methods. By distinguishing the recommendations from reactive and mutual interactions of users, is propos in this research the Model of Recommendation Information Items consist of the following quadrants: Digital Objective Recommendations; Digital Subjective Recommendations; Analog Subjective Recommendations and Analog Objective Recommendations. To analyze the behavior of interactors in the use of these recommendations, the methodological strategy applied in-depth interviews and direct observation. The results of this research consider that the Internet uses more than one type of recommendation when the selection involves significant content, while passively follows recommendations of automated systems when applied directly to the personal cost is low or nonexistent.

Submitted by Haroudo Xavier Filho (haroudo.xavierfo@ufpe.br) on 2016-03-11T15:25:20Z No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) dissertação_gava_cin.pdf: 1596983 bytes, checksum: 23245c1b65fe3416d3baeeac5e118845 (MD5) / Made available in DSpace on 2016-03-11T15:25:20Z (GMT). No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) dissertação_gava_cin.pdf: 1596983 bytes, checksum: 23245c1b65fe3416d3baeeac5e118845 (MD5) Previous issue date: 2015-08-06 / Sistemas de recomendação têm desempenhado um papel importante em diferentes contextos de aplicação (e.g recomendação de produtos, filmes, músicas, livros, dentre outros). Eles automaticamente sugerem a cada usuário itens que podem ser relevantes, evitando que o usuário tenha que analisar uma quantidade gigantesca de itens para realizar sua escolha. Filtragem colaborativa (FC) é a abordagem mais popular para a construção de sistemas de recomendação, embora sofra com problemas relacionados à esparsidade dos dados (e.g., usuários ou itens com poucas avaliações). Neste trabalho, investigamos a combinação de técnicas de FC, representada pela técnica de Fatoração de Matrizes, e técnicas de recomendação baseada em confiança (RBC) em redes sociais para aliviar o problema da esparsidade dos dados. Sistemas de RBC têm se mostrado de fato efetivos para aumentar a qualidade das recomendações, em especial para usuários com poucas avaliações realizadas (e.g., usuários novos). Entretanto, o desempenho relativo entre técnicas de FC e de RBC pode depender da quantidade de informação útil presente nas bases de dados. Na arquitetura proposta nesse trabalho, as predições geradas por técnicas de FC e de RBC são combinadas de forma ponderada através de medidas de esparsidade calculadas para usuários e itens. Para isso, definimos inicialmente um conjunto de medidas de esparsidade que serão calculadas sobre a matriz de avaliações usuários-itens e matriz de confiança usuários-usuários. Através de experimentos realizados utilizando a base de dados Epinions, observamos que a proposta de combinação trouxe uma melhoria nas taxas de erro e na cobertura em comparação com as técnicas isoladamente. / Recommender systems have played an important role in different application contexts (e.g recommendation of products, movies, music, books, among others). They automatically suggest each user items that may be relevant, preventing the user having to analyze a huge amount of items to make your choice. Collaborative filtering (CF) is the most popular approach for building recommendation systems, although suffering with sparsity of the data-related issues (eg, users or items with few evaluations). In this study, we investigated the combination of CF techniques represented by matrix factorization technique, and trust-based recommendation techniques (TBR) on social networks to alleviate the problem of data sparseness. TBR systems have in fact proven to be effective to increase the quality of the recommendations, especially for users with few assessments already carried out (e.g., cold start users). However, the relative performance between CF and TBR techniques may depend on the amount of useful information contained in the databases. In the proposed architecture in this work, the predictions generated by CF and TBR techniques are weighted combined through sparsity measures calculated to users and items. To do this, first we define a set of sparsity measures that will be calculated on the matrix of ratings users-items and matrix of trust users-users. Through experiments using Epinions database, we note that the proposed combination brought an improvement in error rates and coverage compared to combined techniques.

Submitted by Luciana Ferreira (lucgeral@gmail.com) on 2015-03-24T14:51:12Z No. of bitstreams: 2 Dissertação - Vinícius Rafael Lobo de Mendonça - 2014.pdf: 4110263 bytes, checksum: 2e2be342a6c3301f64fa41a675b85ba9 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Approved for entry into archive by Luciana Ferreira (lucgeral@gmail.com) on 2015-03-24T14:55:54Z (GMT) No. of bitstreams: 2 Dissertação - Vinícius Rafael Lobo de Mendonça - 2014.pdf: 4110263 bytes, checksum: 2e2be342a6c3301f64fa41a675b85ba9 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) / Made available in DSpace on 2015-03-24T14:55:54Z (GMT). No. of bitstreams: 2 Dissertação - Vinícius Rafael Lobo de Mendonça - 2014.pdf: 4110263 bytes, checksum: 2e2be342a6c3301f64fa41a675b85ba9 (MD5) license_rdf: 23148 bytes, checksum: 9da0b6dfac957114c6a7714714b86306 (MD5) Previous issue date: 2014-11-19 / Recommendation systems try to guide the user carrying out a task providing him with useful information about it. Considering the context of software development, programs are ever increasing, making it difficult to carry out a detailed verification of warnings generated by automatic static analyzers. In this work, we propose a recommendation system, called WarningsFIX, which aims at helping developers on handling the high number of warnings reported by automatic static analyzers. The back end of this system is composed of seven open-source static analysis tools collecting data, which subsequently are used for visualizing information through TreeMaps. The intention is to combine the outcomes of different static analyzers such that WarningsFIX recommends the analysis of warnings with highest chance to be a true positive. Therefore, the information related to warnings are displayed in four levels of detail: program, package, class, and line. The nodes may be classified in the first three levels: amount of warnings, number of tools and suspicions rate. An exploratory study was carried out and the limitations, advantages and disadvantages of the proposed approach were discussed. / O Sistema de Recomendação apoia um usuário na realização de uma tarefa. Considerando o atual contexto do desenvolvimento de software, programas estão cada vez maiores, tornando difícil a realização de uma avaliação detalhada dos avisos gerados pelos analisadores estáticos. Nesse trabalho, propõe-se um sistema de recomendação, chamado WarningsFIX, que tem objetivo de ajudar os desenvolvedores manipular o alto nível dos avisos emitidos pelos analisadores estáticos. O back end desse sistema é composto de sete ferramentas de análise estática de código aberto para coleta de dados, que são visualizados por meio de TreeMap. O objetivo é combinar os resultados de diferentes analisadores estáticos, assim recomendar a análise de avisos com alta chance de ser verdadeiro positivo. Portanto, a informações relacionadas ao nó são visualizadas em quatro níveis de visualização: programa, pacote, classe e linha. Além disso, os nós podem ser classificados em três tipos: quantidade de avisos, quantidade de ferramentas e taxa de suspeição. Um estudo exploratório foi realizado e as limitações, vantagens e desvantagens da abordagem proposta foram discutidas.

Como os interagentes selecionam conteúdo sob a influência dos sistemas de recomendação digital é o problema de pesquisa apresentado nesta tese. A abundância de dados nos repositórios digitais exige sistemas de recuperação de informação eficazes para auxiliar o usuário na gestão e na seleção de itens de informação. Desta forma, o objetivo geral deste trabalho pretende investigar o comportamento dos interagentes na seleção de itens frente ao sistema de recomendação digital do website da loja virtual Amazon. O sistema de recomendação da Amazon foi investigado com a intenção de se compreender como o usuário utiliza um sistema automatizado de listas de referências em forma de recomendação de conteúdo. O funcionamento dos sistemas de recomendação é fundamentado com a proposta de conhecer suas características e funcionalidades. Como o problema de pesquisa tem em sua temática a recomendação de itens de informação, tornou-se necessário compreender como os usuários interagem com os sistemas para perceber como as recomendações são feitas. O aporte teórico desta pesquisa aproxima os estudos dos campos da Informação e da Comunicação. As técnicas de pesquisas aplicadas envolvem métodos de pesquisa qualitativa. Ao distinguir as recomendações a partir das interações reativas e mútuas dos usuários, propõe-se nesta tese a Matriz de Recomendações de Itens de Informação constituída pelos seguintes quadrantes: Recomendações Objetivas Digitais; Recomendações Subjetivas Digitais; Recomendações Objetivas Analógicas e Recomendações Subjetivas Analógicas. Digitais; Recomendações Objetivas Analógicas e Recomendações Subjetivas Analógicas. Para analisar o comportamento dos interagentes no uso dessas recomendações, a estratégia metodológica aplicou entrevista em profundidade e observação direta. Os resultados desta pesquisa consideram que o internauta recorre a mais de um tipo de recomendação quando a seleção envolve conteúdo significativo, enquanto segue passivamente sistemas de recomendações automatizados quando o custo pessoal diretamente aplicado é baixo ou inexistente. / As the interacting select content under the influence of digital recommender systems is the research problem presented in this thesis. The abundance of data in digital repositories recovery requires effective information systems to assist the user in the management and selection of information items. Thus, the objective of this study was to investigate the behavior of the interacting in the selection of digital items across the recommendation of the Amazon’s bookshop website. The Amazon's recommendation system was investigated with the aim of understanding how the user uses an automated reference lists in the form of content recommendation. The performance of recommender systems is founded with the purpose of knowing their characteristics and functionalities. As the research problem is in your subject to the recommendation of information items, it became necessary to understand how users interact with this system to understand how the recommendations are made. The theoretical contribution of this research approaches the fields of Information and Communication. The technique applied involves qualitative research methods. By distinguishing the recommendations from reactive and mutual interactions of users, is propos in this research the Model of Recommendation Information Items consist of the following quadrants: Digital Objective Recommendations; Digital Subjective Recommendations; Analog Subjective Recommendations and Analog Objective Recommendations. To analyze the behavior of interactors in the use of these recommendations, the methodological strategy applied in-depth interviews and direct observation. The results of this research consider that the Internet uses more than one type of recommendation when the selection involves significant content, while passively follows recommendations of automated systems when applied directly to the personal cost is low or nonexistent.

Today, a modern and interesting research area is machine learning. Another new and exciting research area is quantum computation, which is the study of the information processing tasks accomplished by practising quantum mechanical systems. This master thesis will combine both areas, and investigate quantum machine learning. Kerenidis’ and Prakash’s quantum algorithm for recommendation systems, that offered exponential speedup over the best known classical algorithms at the time, will be examined together with Tang’s classical algorithm regarding recommendation systems, which operates in time only polynomial slower than the previously mentioned algorithm. The speedup in the quantum algorithm was achieved by assuming that the algorithm had quantum access to the data structure and that the mapping to the quantum state was performed in polylog(mn). The speedup in the classical algorithm was attained by assuming that the sampling could be performed in O(logn) and O(logmn) for vectors and matrices, respectively.

Alongside the evolution of the recruitment process, different types of recommendation systems have been developed. The purpose of this study is to investigate recommendation systems within educational contexts, successful implementations of recommendation system architecture patterns, and alternatives to previous experience when evaluating candidates. The study is conducted through two separate methods; A literature review with a qualitative approach and design science research methodology focused on design and development, demonstration and evaluation. The literature review shows that, for recommendation systems, a layered architecture built within a microservice ecosystem is successfully utilized and has multiple beneficial aspects such as improved scalability, maintainability and security. Through design science research methodology, this study shows a suggested approach to implementing a layered architecture in combination with KNN and hybrid filtering. To avoid the lapse of suitable candidates, caused by demanding previous experience, this study shows an alternative approach to recruitment, within an educational context, through the use of soft skills. Within the study, this approach is successfully used to evaluate and compare students, but the same approach could possibly be applied to evaluate and compare companies. Moving forward, this study could be further expanded by looking into possible biases arising as a result of using AI and choices made during this study, as well as weighting of student-attributes.

Background: Cloud computing’s rapid growth has highlighted the need for efficientresource allocation. While cloud platforms offer scalability and cost-effectiveness for a variety of applications, managing resources to match dynamic workloads remains a challenge. Auto-scaling, the dynamic allocation of resources in response to real-time demand and performance metrics, has emerged as a solution. Traditional rule-based methods struggle with the increasing complexity of cloud applications. Machine Learning models offer promising accuracy by learning from performance metrics and adapting resource allocations accordingly.  Objectives: This thesis addresses the topic of cloud environments auto-scaling recommendations emphasizing the integration of Machine Learning models and significant application metrics. Its primary objectives are determining the critical metrics for accurate recommendations and evaluating the best recommendation techniques for auto-scaling. Methods: The study initially identifies the crucial metrics—like CPU usage and memory consumption that have a substantial impact on auto-scaling selections through thorough experimentation and analysis. Machine Learning(ML) techniques are selected based on literature review, and then further evaluated through thorough experimentation and analysis. These findings establish a foundation for the subsequent evaluation of ML techniques for auto-scaling recommendations. Results: The performance of Random Forests (RF), K-Nearest Neighbors (KNN), and Support Vector Machines (SVM) are investigated in this research. The results show that RF have higher accuracy, precision, and recall which is consistent with the significance of the metrics which are identified earlier. Conclusions: This thesis enhances the understanding of auto-scaling recommendations by combining the findings from metric importance and recommendation technique performance. The findings show the complex interactions between metrics and recommendation methods, establishing the way for the development of adaptive auto-scaling systems that improve resource efficiency and application functionality.

Nowadays, with the ever growing availability of options in many areas of our lives, it is crucial to have good ways to navigate your choices. This is why recommendation engines’ role is growing more important. Recommenders are often based on user-item interaction. In many areas like news and podcasts, however, by the time there is enough interaction data for an item, the item has already become irrelevant. This is why incorporating content features is desirable, as the content does not depend on the popularity or novelty of an item. Very often, there is text describing an item, so text features are good candidates for features within recommender systems. Within Natural Language Processing (NLP), pre-trained language models based on the Transformer architecture have brought a revolution in recent years, achieving state-of-the-art performance on many language tasks. Because of this, it is natural to explore how such models can play a role within recommendation systems. The scope of this work is on the intersection between NLP and recommendation systems where we investigate what are the effects of adding BERT-based encodings of titles and descriptions of movies and books to a recommender system. The results show that even in off-the-shelf BERT-models there is a considerable amount of information on movie and book similarity. It also shows that BERT based representations could be used in a recommender system for user recommendation to combine the best of collaborative and content representations. In this thesis, it is shown that adding deep pre-trained language model representations could improve a recommender system’s capability to predict good items for users with up to 0.43 AUC-ROC score for a shallow model, and 0.017 AUC-ROC score for a deeper model. It is also shown that SBERT can be fine-tuned to encode item similarity with up to 0.03 nDCG and up to 0.05 nDCG@10 score improvement. / Med den ständigt växande tillgängligheten av val i många delar av våra liv har det blivit viktigt att enkelt kunna navigera kring olika alternativ. Det är därför rekommendationssystems har blivit viktigare. Rekommendationssystem baseras ofta på interaktion-historiken mellan användare och artikel. När tillräckligt mycket data inom nyheter och podcast har hunnits samlats in för att utföra en rekommendation så har artikeln hunnit bli irrelevant. Det är därför det är önskvärt att införa innehållsfunktioner till rekommenderaren, då innehållet inte är beroende av popularitet eller nymodigheten av artikeln. Väldigt ofta finns det text som beskriver en artikel vilket har lett till textfunktioner blivit bra kandidater som funktion för rekommendationssystem. Inom Naturlig Språkbehandling (NLP), har förtränande språkmodeller baserad på transformator arkitekturen revolutionerat området de senaste åren. Den nya arkitekturen har uppnått toppmoderna resultat på flertal språkuppgifter. Tack vare detta, har det blivit naturligt att utforska hur sådana modeller kan fungera inom rekommendationssystem. Det här arbetet är mellan två områden, NLP och rekommendationssystem. Arbetet utforskar effekten av att lägga till BERT-baserade kodningar av titel och beskrivning av filmer, samt böcker till ett rekommendationssystem. Resultaten visar att även i förpackade BERT modeller finns det mycket av information om likheter mellan film och böcker. Resultaten visar även att BERT representationer kan användas i rekommendationssystem för användarrekommendationer, i kombination med kollaborativa och artikel baserade representationer. Uppsatsen visar att lägga till förtränade djupspråkmodell representationer kan förbättra rekommendationssystemens förmåga att förutsäga bra artiklar för användare. Förbättringarna är upp till 0.43 AUC-ROC poäng för en grundmodell, samt 0.017 AUC-ROC poäng för en djupmodell. Uppsatsen visar även att SBERT kan bli finjusterad för att koda artikel likhet med upp till 0.03 nDCG och upp till 0.05 nDCG@10 poängs förbättring.

The model predicts the best flight order and recommend best flight to users. The thesis could be divided into the following three parts: Feature choosing, data-preprocessing, and various algorithms experiment. For feature choosing, besides the original information of flight itself, we add the user’s selection status into our model, which the flight class is, together with children or not. In the data preprocessing stage, data cleaning is used to process incomplete and repeated data. Then a normalization method removes the noise in the data. After various balancing processing, the class-imbalance data is corrected best with SMOTE method. Based on our existing data, I choose the classification model and Sequential ranking algorithm. Use price, direct flight or not, travel time, etc. as features, and click or not as label. The classification algorithms I used includes Logistic Regression, Gradient Boosting, KNN, Decision Tree, Random Forest, Gaussian Process Classifier, Gaussian NB Bayesian and Quadratic Discriminant Analysis. In addition, we also adopted Sequential ranking algorithm. The results show that Random Forest-SMOTE performs best with AUC of ROC=0.94, accuracy=0.8998. / Modellen förutsäger den bästa flygordern och rekommenderar bästa flyg till användarna. Avhandlingen kan delas in i följande tre delar: Funktionsval, databehandling och olika algoritms experiment. För funktionsval, förutom den ursprungliga informationen om själva flygningen, lägger vi till användarens urvalsstatus i vår modell, vilken flygklassen är , tillsammans med barn eller inte. Datarengöring används för att hantera dubbletter och ofullständiga data. Därefter tar en normaliserings metod bort bruset i data. Efter olika balanserings behandlingar är SMOTE-metoden mest lämplig för att korrigera klassobalans flyg data. Baserat på våra befintliga data väljer jag klassificerings modell och sekventiell ranknings algoritm. Använd pris, direktflyg eller inte, restid etc. som funktioner, och klicka eller inte som etikett. Klassificerings algoritmerna som jag använde inkluderar Logistic Regression, Gradient Boost, KNN, Decision Tree, Random Forest, Gaussian Process Classifier, Gaussian NB Bayesian and Quadratic Discriminant Analysis. Dessutom antog vi också Sequential ranking algoritm. Resultaten visar att Random Forest-SMOTE presterar bäst med AUC för ROC = 0.94, noggrannhet = 0.8998.