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.

For any unemployed person in Sweden that is looking for a job, the most common place they can turn to is the Swedish Public Employment Service, also known as Arbetsförmedlingen, where they can register to get help with the job search process. Occasionally, in order to land an employment, the person might require extra guidance and education, Arbetsförmedlingen outsource this education to external companies called providers where each person gets assigned a coach that can assist them in achieving an employment quicker. Given the current labour market data, can the data be used to help optimize and speed up the job search process? To try and help optimize the process, the labour market data was inserted into a graph database, using the database, a recommendation system was built which uses different methods to perform each recommendation. The recommendations can be used by a provider to assist them in assigning coaches to newly registered participants as well as recommending activities. The performance of each recommendation method was evaluated using a statistic measure. While the user-created methods had acceptable performance, the overall best performing recommendation method was collaborative filtering. However, there are definitely some potential for the user-created method, and given some additional testing and tuning, the methods can surely outperform the collaborative filtering method. In addition, expanding the database by adding more data would positively affect the recommendations as well.

No description available.

No description available.

Recommendation systems have significantly influenced user experiences across various industries, yet their application in the insurance sector remains relatively unexplored. This thesis focuses on developing a car insurance recommendation system that implements a `consumers like you' feature. The study initially employs a clustering-based recommendation system due to missing labels in an offline environment. However, challenges emerge, such as determining the optimal number of clusters and managing complex data. Additionally, the inability to effectively update based on feedback and lower predictive performance compared to supervised methods necessitated exploring supervised alternatives. In response, this thesis proposes a methodology where the unsupervised approach simulates consumer behavior in an offline environment. Supervised alternatives are pre-trained on the clustering-based system to replicate it and come with the ability to be fine-tuned based on live traffic. Three supervised alternatives — KNN, XGBoost, and a neural network — are developed and compared. Given the supervised recommendation system adaptability based on feedback, supervised methods can provide more accurate, personalized recommendations in the insurance domain. The XGBoost and neural network-based recommendation systems were able to replicate the unsupervised approach, and their expressive power makes them valid candidate models to further evaluate on live traffic. The thesis concludes with the potential to both improve and adapt these recommendation systems to other insurance types, marking a significant step toward more personalized, user-friendly insurance services.

No description available.

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.

No description available.

Some classes of Internet users have specific information needs and specialized information-seeking behaviors. For example, educators who are designing a course might create a syllabus, recommend books, create lecture slides, and use tools as lecture aid. All of these resources are available online, but are scattered across a large number of websites. Collecting, linking, and presenting the disparate items related to a given course topic within a digital library will help educators in finding quality educational material. Content quality is important for users. The results of popular search engines typically fail to reflect community input regarding quality of the content. To disseminate information related to the quality of available resources, users need a common place to meet and share their experiences. Online communities can support knowledge-sharing practices (e.g., reviews, ratings). We focus on finding the information needs of educators and helping users to identify potentially useful resources within an educational digital library. This research builds upon the existing 5S digital library (DL) framework. We extend core DL services (e.g., index, search, browse) to include information from latent user groups. We propose a formal definition for the next generation of educational digital libraries. We extend one aspect of this definition to study methods that incorporate collective knowledge within the DL framework. We introduce the concept of deduced social network (DSN) - a network that uses navigation history to deduce connections that are prevalent in an educational digital library. Knowledge gained from the DSN can be used to tailor DL services so as to guide users through the vast information space of educational digital libraries. As our testing ground, we use the AlgoViz and Ensemble portals, both of which have large collections of educational resources and seek to support online communities. We developed two applications, ranking of search results and recommendation, that use the information derived from DSNs. The revised ranking system incorporates social trends into the system, whereas the recommendation system assigns users to a specific group for content recommendation. Both applications show enhanced performance when DSN-derived information is incorporated. / Ph. D.