Les systèmes de recommandation se sont révélés être des outils efficaces pour aider les utilisateurs à faire face à la surcharge informationnelle. D’importants progrès ont été réalisés dans le domaine durant les deux dernières décennies, menant en particulier à l’exploitation de l’information contextuelle pour modéliser l’aspect dynamique des utilisateurs et des articles. La définition traditionnelle du contexte, adoptée dans la plupart des systèmes de recommandation contextuels, ne répond pas à plusieurs contraintes rencontrées dans les applications du monde réel. Dans cette thèse, nous abordons les problèmes de recommandation en présence d’informations contextuelles partiellement observables et d’informations contextuelles non observables dans deux applications particulières, la recommandation d’hôtels et la recommandation en ligne, remettant en question plusieurs aspects de la définition traditionnelle du contexte, notamment l'accessibilité, la pertinence, l'acquisition et la modélisation.La première partie de la thèse étudie le problème de recommandation d’hôtels qui souffre du démarrage à froid continu, limitant la performance des approches classiques de recommandation. Le voyage n’est pas une activité fréquente et les utilisateurs ont tendance à adopter des comportements diversifiés en fonction de leurs situations spécifiques. Après une analyse du comportement des utilisateurs dans ce domaine, nous proposons de nouvelles approches de recommandation intégrant des informations contextuelles partiellement observables affectant les utilisateurs. Nous montrons comment cela contribue à améliorer la qualité des recommandations.La deuxième partie de la thèse aborde le problème de recommandation en ligne en présence de flux de données où les observations apparaissent continûment à haute fréquence. Nous considérons que les utilisateurs et les articles reposent sur des informations contextuelles non observables par le système et évoluent de façons différentes à des rythmes différents. Nous proposons alors d’effectuer de la détection active de changements et d’assurer la mise à jour des modèles en temps réel. Nous concevons de nouvelles méthodes qui s’adaptent aux changements qui apparaissent au niveau des préférences des utilisateurs et des perceptions et descriptions des articles, et montrons l’importance de la recommandation adaptative en ligne pour garantir de bonnes performances au cours du temps. / Recommender systems have proven to be valuable tools to help users overcome the information overload, and significant advances have been made in the field over the last two decades. In particular, contextual information has been leveraged to model the dynamics occurring within users and items. Context is a complex notion and its traditional definition, which is adopted in most recommender systems, fails to cope with several issues occurring in real-world applications. In this thesis, we address the problems of partially observable and unobservable contexts in two particular applications, hotel recommendation and online recommendation, challenging several aspects of the traditional definition of context, including accessibility, relevance, acquisition, and modeling.The first part of the thesis investigates the problem of hotel recommendation which suffers from the continuous cold-start issue, limiting the performance of classical approaches for recommendation. Traveling is not a frequent activity and users tend to have multifaceted behaviors depending on their specific situation. Following an analysis of the user behavior in this domain, we propose novel recommendation approaches integrating partially observable context affecting users and we show how it contributes in improving the recommendation quality.The second part of the thesis addresses the problem of online adaptive recommendation in streaming environments where data is continuously generated. Users and items may depend on some unobservable context and can evolve in different ways and at different rates. We propose to perform online recommendation by actively detecting drifts and updating models accordingly in real-time. We design novel methods adapting to changes occurring in user preferences, item perceptions, and item descriptions, and show the importance of online adaptive recommendation to ensure a good performance over time.

The purpose of this project is to create a website with a React-based prototype recommendation system of a large cultural collection. The aim of the website is to provide a function that allows a user to upload an image to which the system consequently recommends correlating artwork from the publicly available collection of the Metropolitan Museum of Modern Art (MET). The correlation coefficient between the uploaded image and the artworks from (MET) is acquired through Pearson Correlation. Furthermore the artwork with the highest correlation to the uploaded picture is shown first, then each subsequent artwork is shown in order of highest correlation. The main challenge for building this prototype was to combine the different components together with JavaScript and the REACT framework. The recommendation engine demands numerical representations of these artworks, and most effort was given to the automatic conversion of photos of artworks into a proper format for the recommendation engine.

This study analyzes the recommendation systems from a user’s perspective and identifies five areas of concern in developing and using a recommendation system. The study’s methods are focus group discussions with Data scientists and Full-stack developers working in the industry. An online survey was distributed to several Facebook groups of various universities. The study results indicate that users have a strong desire to have their moral sensitivities under their control. The study also enables the system developers to understand the recommendations of the system affect the conflicting interests of various entities. / Den här studien analyserar rekommendationssystemen ur ett användarperspektiv, och identifierar fem relevanta områden att ha i åtanke i utvecklingen och användandet av ett rekommendationssystem. Studiens metoder består av fokusgruppsdiskussioner med datavetare och s.k. “full-stack-utvecklare” som arbetar inom IT-branschen. En online-enkät delades ut till flera Facebook-grupper tillhörande olika universitet. Studiens resultat indikerar att användare har en tydlig preferens att ha kontroll över sina moraliska perspektiv. Vidare tillåter även studien systemutvecklare att förstå att systemets rekommendationer påverkar intressekonflikter mellan olika enheter och intressenter.

No description available.

In recent years, Recommendation Systems have revolutionized how social media and ecommerce are used. Fashion Recommendation Systems have made it easier for customers to do shopping, by recommending items to them based on various factors, such as their previous orders, and their similarities to other users. To apply a Fashion Recommendation System, there are four main approaches: Content-based filtering, where the system recommends similar items to the user. Collaborative filtering, in which the system recommends items from similar users. Hybrid filtering, which merges the features of the previous techniques, and Hyper-personalized filtering, which uses the profiling of customers to draw certain assumptions about users. The problem this research addresses is the lack of involving the intent of users when designing and applying a fashion recommendation system, as well as the cold start problem. The Research Questions are: 1. How to develop and implement a Fashion Recommendation System as an artifact that provides recommendations to customers, 2. How to implement intent as context in such Recommendation Systems to provide improved recommendations to the fashion customers, 3. How the inclusion of intent as context in a Fashion Recommendation System impacts customer satisfaction. The Research Methodology used in this study is design science research, with various research strategies and data collection methods used throughout, such as crowdsourcing, document analysis, testing, qualitative questionnaires, and thematic analysis. The Results of the study indicate the involvement of the intent results in better recommendations, a smoother and more accurate shopping experience, and an overall higher customer satisfaction.

One of the key tasks in the study of the recommendation system is to model the dynamics aspect of a person's preference, i.e. to give sequential recommendations. Markov Chain (MC), which is famous for its capability of learning a transition graph, is the most popular approach to address the task. In previous work, the recommendation system attempts to model the short-term dynamics of the personal preference based on the long-term dynamics, which implies the assumption that the personal preference over a set of items remains same over time. However, in the field of food science, the study of Sensory-Specific Satiety (SSS) shows that the personal preference on food changes along time and previous meals. However, whether such changes follow certain patterns remains unclear. In this paper, a recommendation system is built based on Variable Order Markov Chain (VOMC), which is capable of modeling various lengths of sequential patterns using the suffix tree (ST) search. This recommendation system aims to understand and model the short-term dynamics aspect of the personal preference on food. To evaluate the system, a Food Diary survey is carried to collect users’ meals data over seven days. The results show that this recommendation system can give meaningful recommendations. / En av huvuduppgifterna när det kommer till rekommenderingsplatformar är att modellera kortsidiga dynamiska egenskaper, dvs. användares sekventiella beteenden. Markov Chain (MC), som är mest känd för sin förmåga att lära sig övergångsgrafer, är den mest populära metoden för att ge sig på denna uppgift. I föregående arbeten så har rekommenderingsplatformar ofta tenderat att modellera kortsidig dynamik baserat på långsidig dynamik, t.ex. likheter mellan objekt eller användares relativa preferenser givet olika tillfällen. Att använda den här metoden brukar medföra att användares långsiktiga dynamik, i detta fall personliga smakpreferenser, är alltid densamma. Däremot, så har studien av Sensory-Specific Satiety visat att användares preferenser gällande mat varierar. I detta arbete så undersöks ett rekommenderingssystem som baseras på Variable Order Markov Chain (VOMC) som kan anpassa sig efter den observerade realiseringen genom att använda suffix tree (ST) för att extrahera sekventiella mönster. Detta rekommenderingssystem fokuserar på kortsidig dynamik istället för att kombinera kort- och långsidig dynamik. För att evaluera metoden, en undersökning av vilken mat som konsumeras, under loppet av sju dagar, ges ut för att samla data om vilken mat och i vilken ordning användare konsumerar. I resultaten så visas att det föreslagna rekommenderingsystemet kan ge meningsfulla rekommendationer.

Background: The demand for a sustainable lifestyle is increasing due to the need to tackle rapid climate change. One-third of carbon emissions come from the food industry; reducing emissions from this industry is crucial when fighting climate change. One of the ways to reduce carbon emissions from this industry is by helping consumers adopt sustainable eating habits by consuming eco-friendly food. To help consumers find eco-friendly recipes, we developed a sustainable recipe recommendation system that can recommend relevant and eco-friendly recipes to consumers using little information about their previous food consumption.  Objective: The main objective of this research is to identify (i) the appropriate recommendation algorithm suitable for a dataset that has few training and testing examples, and (ii) a technique to re-order the recommendation list such that a proper balance is maintained between relevance and carbon rating of the recipes. Method: We conducted an experiment to test the performance of a GPT embeddings-based recommendation system, Factorization Machines, and a version of a Graph Neural Network-based recommendation algorithm called PinSage for a different number of training examples and used ROC AUC value as our metric. After finding the best-performing model we experimented with different re-ordering techniques to find which technique provides the right balance between relevance and sustainability. Results: The results from the experiment show that the PinSage and Factorization Machines predict on average whether an item is relevant or not with 75% probability whereas GPT-embedding-based recommendation systems predict with only 55% probability. We also found the performance of PinSage and Factorization Machines improved as the training set size increased. For re-ordering, we found using a loga- rithmic combination of the relevance score and carbon rating of the recipe helped to reduce the average carbon rating of recommendations with a marginal reduction in the ROC AUC score.  Conclusion: The results show that the chosen state-of-the-art recommendation systems: PinSage and Factorization Machines outperform GPT-embedding-based recommendation systems by almost 1.4 times.

This thesis proposes a two-stage recommendation system for providing music recommendations based on seed playlists as inputs. The goal is to help businesses find relevant and brand-fit music to play in their venues. The problem of recommending music using machine learning has been investigated quite a bit in both academia and the industry, with collaborative filtering and content-based filtering being the major approaches used. One of the difficulties of creating a recommendation system is how to evaluate it. In this thesis, both a quantitative and a qualitative evaluation are made to determine how well the results correspond to the actual quality of recommendations. The application of recommending music to businesses also poses different problems than a service directed at end consumers, mostly related to how many track recommendations are needed. A two-stage approach was used with Stage 1 producing candidates and a Stage 2 model using a neural network comparing five tracks from the playlist with a candidate was used to rank said candidates. The results show that the Stage 2 model has substantially better results in both the qualitative and quantitative evaluation compared to Stage 1. The quality of the recommendations from the whole system is not completely satisfactory, and some possible reasons for this are discussed, including improving the Stage 1 candidate generator (which was not modified in the scope of this thesis). / Automatisk musikrekommendation med hjälp av maskininlärning har utforskats av både industrin och akademin genom åren, där två huvudsakliga metoder utkristalliserats: collaborative filtering samt content-based filtering. I det här arbetet har en content-based modell tagits fram, uppdelad i två stadier: Steg 1 som genererar kandidater som Steg 2 sedan ordnade om med hjälp av ett neuralt nätverk som jämförde 5 låtar i taget från en spellista med motsvarande kandidater genererade av Steg 1 En av svårigheterna med att skapa automatiska rekommendationer är utvärderingen av den. I det här arbetet har både en kvantitativ och kvalitativ studie utförts för att försäkra att resultaten motsvarar den faktiska kvaliten hos rekommendationerna. Slutmålet med att hjälpa företag med musikrekommendation ställer också unika problem att lösa i jämförelse med en tjänst för privatpersoner, framförallt relaterat till storleken på de returnerade rekommendationerna. Resultaten visade att Steg 2 lyckades rangordna rekommendationerna från Steg 1 på ett sätt som gav högre poäng i både den kvantitativa och kvalitativa utvärderingen av systemen. De slutgiltiga resultaten var inte helt tillfredsställande, och potentialla orsaker till detta diskuteras. Dessa inkluderar Steg 1 (som inte modifierades inom ramen för detta arbete). Utvärderingen visade dock att de kvantitativa utvärderingsramarna verkar motsvara den upplevda kvaliten hos rekommendationerna baserat på den kvalitativa utvärderingen.

No

People’s selection of leisure activities is a complex choice because of implicit human factors and explicit environmental factors. Satisfactory participation in leisure activities is an important task since keeping a regular active lifestyle can help to maintain and improve the wellbeing of people. Technology could help in selecting the most appropriate activities by designing and implementing activities, collecting people profiles and their preferences relations. In fact, recommendation systems, have been successfully used in the last years in similar tasks with different types of recommendation systems. This thesis aims at the design, implementation, and evaluation of recommendation systems that could help us to better understand the complex choice of selecting leisure activities. In this work, we first define an evaluation framework for different recommendations systems. Then we compare their performances using different evaluation metrics. Thus, we explore and try to better understand the user’s preferences over leisure activities. After, having a comprehensive analysis of modelling recommended items and leisure activities, we also design and implement a content-based leisure activity recommendation system to make use of a taxonomy of activities. Moreover, in the course of our research, we have collected and evaluated two datasets obtained one from the Meetup social network and the other from crowd-workers and made them available as open data sources for further evaluation in the recommendation system research community.