Le cancer de la prostate est le cancer le plus fréquemment diagnostiqué chez les hommes canadiens. Aucun facteur de risque modifiable n’a été identifié, mais l’alimentation pourrait être impliquée. Les profils alimentaires, décrivant l’ensemble de l’apport alimentaire, constituent une approche de recherche prometteuse. L’objectif général de cette thèse était d’évaluer le rôle des profils alimentaires et du niveau de transformation des aliments sur le risque de cancer de la prostate. Les données colligées dans une vaste étude cas-témoins populationnelle menée chez les résidents montréalais ont été utilisées. Les 1919 cas incidents histologiquement confirmés étaient âgés de 75 ans ou moins et avaient été diagnostiqués entre 2005 et 2009. Les 1991 témoins ont été sélectionnés aléatoirement à partir de la liste électorale, puis appariés aux cas selon l’âge (± 5 ans). Les informations concernant l’alimentation ont été recueillies avec un questionnaire de fréquence alimentaire documentant la consommation deux ans avant le diagnostic ou l’entrevue. Le premier objectif visait à identifier des profils alimentaires parmi les témoins francophones ainsi que les caractéristiques associées à ces profils. Une analyse en composantes principales a permis d’identifier les profils alimentaires Santé, Occidental modifié - Salé et Occidental modifié - Sucré. Le profil Santé a été associé à des niveaux plus élevés de revenu et d’éducation, à un niveau modéré d’activité physique et à un faible niveau de tabagisme. Le profil Occidental modifié - Salé a été associé avec des ethnicités française, européenne (autre que française) ou latine, avec le fait d’être marié ou en union libre, et était inversement associé avec l’âge. Le profil Occidental modifié - Sucré était plus commun chez les hommes d’origine française et chez les consommateurs de suppléments de vitamines et minéraux. Le deuxième objectif visait à évaluer les associations entre les profils alimentaires et le cancer de la prostate. Les rapports de cotes (RC) et intervalles de confiance (IC) à 95% ont été obtenus par régression logistique non conditionnelle ajustée pour les facteurs de confusion. Le profil Santé était inversement associé au risque de cancer de la prostate (RC= 0,76 [IC 95% = 0,61-0,93], en comparant le quartile supérieur au quartile inférieur). Le profil Occidental - Sucré et Boissons était associé à une augmentation du risque de cancer de la prostate (RC= 1,35 [IC 95% =1,10-1,66], quartile supérieur vs inférieur). Ces résultats sont novateurs. Aucune association n’a été observée avec le profil Occidental - Salé et Alcool. Le troisième objectif visait à évaluer l’association entre le niveau de transformation des aliments et le cancer de la prostate. Les aliments transformés étaient associés à une augmentation du risque (RC= 1,32 [IC 95% =1,07-1,62], quartile supérieur vs inférieur) et l’association était légèrement plus prononcée pour les cancers agressifs. En conclusion, ces résultats suggèrent que les profils alimentaires et le niveau de transformation des aliments jouent un rôle dans le développement du cancer de la prostate. Il s’agit d’informations importantes pour soutenir la promotion de saines habitudes de vie et la prévention du cancer de la prostate. / Prostate cancer is the most commonly diagnosed cancer among men in Canada. No modifiable risk factor has been identified, but diet is suspected to play a role. Dietary patterns, which describe the overall dietary intake rather than the consumption of specific foods or nutrients, represent a promising research approach. The general objective of this thesis was to assess the role of dietary patterns and the level of food processing on the risk of prostate cancer. Data collected in a large population-based case-control study conducted among Montreal residents were used. The 1919 histologically confirmed incident cases were 75 years of age or younger and had been diagnosed between 2005 and 2009. Concurrently, the 1991 controls were randomly selected from the electoral list and frequency-matched to cases by age (± 5 years). Food consumption was assessed using a food frequency questionnaire focusing on the period two years before diagnosis or interview. The first objective was to identify dietary patterns among the French-speaking controlsas well as the characteristics associated with these patterns. Principal component analysis led to the identification of three dietary patterns: Healthy, Western modified - Salty and Western modified - Sweet. The Healthy pattern was associated with higher income, education, moderate levels of recreational physical activity and lower levels of smoking. The Western modified – Salty pattern was positively associated with French, other European (other than French), and Latino ancestries, and with married and common-law relationships, whereas it was inversely associated with age. Finally, the Modified Western – Sweet pattern was more common among men of French ancestry and users of vitamin/mineral supplements. The second objective was to assess associations between the different dietary patterns and prostate cancer. Odds ratios (OR) and 95% confidence interval (95% CI) were obtained by unconditional logistic regression adjusting for confounders. The Healthy dietary pattern was inversely associated with prostate cancer (OR = 0,76 [95% CI = 0,61-0,93], highest vs lowest quartile), whereas the Western - Sweet and beverages pattern increased the risk of this cancer (OR = 1,35 [95% CI = 1,10-1,66], highest vs lowest quartile). Both results are novel. The Western - Salty and alcohol pattern was not associated with prostate cancer risk. The third objective was to assess the association between the level of food processing and prostate cancer. The level of food processing in the diet was assigned using the NOVA food classification. Processed foods were associated with an increased risk (OR = 1,32 [95% CI] = 1,07-1,62], highest vs lowest quartile) of prostate cancer, and the association was slightly more pronounced for high-grade prostate cancers. In conclusion, these results suggest that dietary patterns and the level of food processing play a role on the risk of developing prostate cancer. This information is important for promoting a healthy lifestyle and for prostate cancer prevention.

No description available.

No description available.

No description available.

No description available.

This thesis focuses on predicting trends in Commodity Trading Advisors (CTAs), also known as trend-following hedge funds. The paper applies a Hidden Markov Model (HMM) for classifying trends. Additionally, by incorporating additional features, a regularized logistic regression model is used to enhance prediction capability. The model demonstrates success in identifying positive trends in CTA funds, with particular emphasis on precision and risk-adjusted return metrics. In the context of regularized regression models, techniques for statistical inference such as bootstrap resampling and Markov Chain Monte Carlo are applied to estimate the distribution of parameters. The findings suggest the model's effectiveness in predicting favorable CTA performance and mitigating equity market drawdowns. For future research, it is recommended to explore alternative classification models and extend the methodology to different markets and datasets.

Although studies examining juvenile recidivism have focused primarily on violent recidivism, the factors that predict recidivism likely differ by offense type. To examine general, property, and violent recidivism, this study combined individual-level data (i.e., offender and case characteristics) from the Mississippi Youth Court Information Data System (MYCIDS) for the years 2009-2011 and contextual-level data (i.e., county characteristics) from the 2010 U.S. Census and the 2010 Uniform Crime Reports (UCR). Results showed that offender characteristics predicted only general and property recidivism, but case characteristics mattered for all three types (i.e., general, violent, and property recidivism). Contextual characteristics (i.e., the percentage of the population that is male aged 15 to 24) also mattered, but only for property recidivism. These findings have implications for policies and programs related to the treatment of juvenile offenders.

Set-pieces such as free-kicks and corners have been thoroughly examined in studies related to football analytics in recent years. However, little focus has been put on the most frequently occurring set-piece: the throw-in. This project aims to investigate how football teams can optimize their throw-in tactics in order to improve the chance of taking a successful throw-in. Two different definitions of what constitutes a successful throw-in are considered, firstly if the ball is kept in possession and secondly if a goal chance is created after the throw-in. The analysis is conducted using logistic regression, as this model comes with high interpretability, making it easier for players and coaches to gain direct insights from the results. A substantial focus is put on the investigation of the logistic regression assumptions, with the greatest emphasis being put on the linearity assumption. The results suggest that long throws directed towards the opposition’s goal are the most effective for creating goal-scoring opportunities from throw-ins taken in the attacking third of the pitch. However, if the throw-in is taken in the middle or defensive regions of the pitch, the results interestingly indicate that throwing the ball backwards leads to increased chance of scoring. When it comes to retaining the ball possession, the results suggest that throwing the ball backwards is an effective strategy regardless of the pitch position. Moreover, the project outlines how feature transformations can be used to improve the fitting of the logistic regression model. However, it turns out that the most significant improvement in accuracy of logistic regression occurs when incorporating additional relevant features into the model. In such case, the logistic regression model achieves a predictive power comparable to more advanced machine learning methods. / Fasta situationer såsom frisparkar och hörnor har varit välstuderade i studier rörande fotbollsanalys de senaste åren. Lite fokus har emellertid lagts på den vanligast förekommande fasta situationen: inkastet. Detta projekt syftar till att undersöka hur fotbollslag kan optimera sin inkasttaktik för att förbättra möjligheterna till att genomföra ett lyckat inkast. Två olika definitioner av vad som utgör ett lyckat inkast beaktas, dels om bollinnehavet behålls och dels om en målchans skapas efter inkastet. Analysen görs med logistisk regression eftersom denna modell har hög tolkningsbarhet, vilket gör det lättare för spelare och tränare att få direkta insikter från resultaten. Stort fokus läggs på undersökning av de logistiska regressionsantagandena, där störst vikt läggs på antagandet gällande linjäritet. Resultaten tyder på att långa inkast riktade mot motståndarnas mål är de mest gynnsamma för att skapa en målchans från inkast tagna i den offensiva tredjedelen av planen. Om inkastet istället tas från de mellersta eller defensiva delarna av planen tyder resultaten intressant nog på att inkast riktade bakåt leder till ökad chans till att göra mål. När det kommer till att behålla bollinnehavet visar resultaten att kast bakåt är en gynnsam strategi, oavsett var på planen inkasten tas ifrån. Vidare visar projektet hur variabeltransformationer kan användas för att förbättra modellanpassningen för logistisk regression. Det visar sig dock att den tydligaste förbättringen fås då fler relevanta variabler läggs till i modellen. I sådant fall, får logistisk regression en prediktiv förmåga som är jämförbar med mer avancerade maskininlärningsmetoder.

Eftersom samhället blir allt mer datadrivet revolutionerar användningen av AI och maskininlärning sättet företag fungerar och utvecklas på. Denna studie utforskar användningen av AI, Big Data och Natural Language Processing (NLP) för att förbättra affärsverksamhet och intelligens i företag. Huvudsyftet med denna avhandling är att undersöka om den nuvarande klassificeringsprocessen hos värdorganisationen kan upprätthållas med minskade driftskostnader, särskilt lägre moln-GPU-kostnader. Detta har potential att förbättra klassificeringsmetoden, förbättra produkten som företaget erbjuder sina kunder på grund av ökad klassificeringsnoggrannhet och stärka deras värdeerbjudande. Vidare utvärderas tre tillvägagångssätt mot varandra och implementationerna visar utvecklingen inom området. Modellerna som jämförs i denna studie inkluderar traditionella maskininlärningsmetoder som Support Vector Machine (SVM) och Logistisk Regression, tillsammans med state-of-the-art transformermodeller som BERT, både Pre-Trained och Fine-Tuned. Artikeln visar att det finns en avvägning mellan prestanda och kostnad vilket illustrerar problemet som många företag, som Valu8, står inför när de utvärderar vilket tillvägagångssätt de ska implementera. Denna avvägning diskuteras och analyseras sedan mer detaljerat för att utforska möjliga kompromisser från varje perspektiv i ett försök att hitta en balanserad lösning som kombinerar prestandaeffektivitet och kostnadseffektivitet. / As society is becoming more data-driven, Artificial Intelligence (AI) and Machine Learning are revolutionizing how companies operate and evolve. This study explores the use of AI, Big Data, and Natural Language Processing (NLP) in improving business operations and intelligence in enterprises. The primary objective of this thesis is to examine if the current classification process at the host company can be maintained with reduced operating costs, specifically lower cloud GPU costs. This can improve the classification method, enhance the product the company offers its customers due to increased classification accuracy, and strengthen its value proposition. Furthermore, three approaches are evaluated against each other, and the implementations showcase the evolution within the field. The models compared in this study include traditional machine learning methods such as Support Vector Machine (SVM) and Logistic Regression, alongside state-of-the-art transformer models like BERT, both Pre-Trained and Fine-Tuned. The paper shows a trade-off between performance and cost, showcasing the problem many companies like Valu8 stand before when evaluating which approach to implement. This trade-off is discussed and analyzed in further detail to explore possible compromises from each perspective to strike a balanced solution that combines performance efficiency and cost-effectiveness.

Today it is important for investors to identify which stocks that will result in positive returns in order for the right decision to be made when trading on the stock market. For decades it has been an area of interest for academics, and it is still challenging due to many difficulties and problems. A large number of studies has been carried out in machine learning and stock trading,where many of the studies has resulted in promising results despite these challenges. The aim of this study was to develop and evaluate predictive models for identifying stocks that outperform the Swedish market index OMXSPI. The research utilized a dataset of historical stock data and applied three various machine learning algorithms, Support Vector Machine, Logistic Regression and Decision Trees to predict if excess performance was met. With the help of ten-fold cross-validation and hyperparameter tuning the results were an IT-artefact that produced satisfying results. The results showed that hyperparameter tuning techniques marginally improved the metrics focused-on, namely accuracy and precision. The support vector machine model achieved an accuracy of 58,52% and a precision of 57,51%. The logistic regression model achieved an accuracy of 55,75% and a precision of 54,81%. Finally, the decision tree model which was the best performer, achieved an accuracy of 64,84% and a precision of 65,00%.