信用評等制度在美國已有百年以上歷史，而我國自民國80幾年開始發展評等制度，截至目前，僅有中華信用評等公司與台灣經濟新報社兩家公司提供評等服務，而台灣經濟新報社更將金融保險業排除於評等對象之外。站在穩定市場競爭、保障消費者權益、配合監理需求，以及輔助專案投標等方面來看，市場上的確需要一套能反映產險業行業特性之評等模式。 本文以美國接受A.M.Best評等之產險公司為研究對象，運用三種統計方法：多元區別分析(Multiple Discriminant Analysis，MDA)、羅吉斯迴歸(Unordered Logistic Regression，ULR)、順序性羅吉斯迴歸(Ordered Logistic Regression，OLR)，來建構產險公司之信用評等模式。樣本選擇方面：估計樣本，選取美國1993年到1996年接受A.M.Best評等之產險公司327家；保留樣本，為1997年78筆資料。 而本文預定達成目標如下： 一、建立等級預測模型：參考Ederington(1985)所作債券等級預測模型，以獲利能力、槓桿、流動性、投資風險、準備金適足性五類指標共38個財務比率，透過三種統計模型，建構等級預測模型。 二、藉由等級預測之建立，尋找能有效區別產險公司評等等級之財務指標，並分析其影響程度。 三、力求模型公信力：無論變數選擇或權數決定，皆由統計軟體按照樣本特性選取產生，減少人為主觀判斷。 在決定研究對象之初，因考慮到國內產險公司接受評等之家數不多，且年數又太短，資料數量無法據以建立評等模式，因而決定以美國的產險公司為對象，再以台灣樣本作為保留樣本，預測之等級結果僅供參考之用。 / Three possible models of the P-L Insurers rating process are estimated and compared：1. Muitiple Discriminant Model, 2. Unordered Logistic Model, 3. Ordered Logistic Model. Each model is estimated for a sample of 327 American P-L insurance companies using the same 38 independent variables. The three estimated models are then employed to predict ratings for a holdout sample of 78 companies. The study analyzes 1993 through 1997 data for a sample of P-L insurers that acquired A.M.Best Financial strength ratings between December 31,1993, and December 31, 1997. Empirical evidence suggests that even when models with the same basic structure were compared, differences in estimation procedures resulted in quite different coefficient estimates and classifications. The muitiple discriminant model clearly outperformed the regression model, while the unordered logistic model was clearly superior to the ordered logistic model.

The astronomical increase in the number of wireless devices such as smart phones in 21th century has revolutionized the way people communicate with one another and share information. The new wireless technologies have also enabled researchers to collect real data about how people move and meet one another in different social settings. Understanding human mobility has many applications in different areas such as traffic planning in cities and public health studies of epidemic diseases. In this thesis, we study the fundamental properties of human contact graphs in order to characterize how people meet one another in different social environments. Understanding human contact patterns in return allows us to propose a cost-effective routing algorithm for spreading information in Delay Tolerant Networks. Furthermore, we propose several contact predictors to predict the unobserved parts of contact graphs when only partial observations are available. Our results show that we are able to infer hidden contacts of real contact traces by exploiting the underlying properties of contact graphs. In the last few years, we have also witnessed an explosion in the number of people who use social media to share information with their friends. In the last part of this thesis, we study the running times of several information spreading algorithms in social networks in order to find the fastest strategy. Fast information spreading has an obvious application in advertising a product to a large number of people in a short amount of time. We prove that a fast information spreading algorithm should efficiently identify communication bottlenecks in order to speed up the running time. Finally, we show that sparsifying large social graphs by exploiting the edge-betweenness centrality measure can also speed up the information spreading rate. / Graduate

This report explores whether machine learning methods such as regression and classification can be used with the goal of estimating the resolution time of trouble tickets in a telecommunications network. Historical trouble ticket data from Telenor were used to train different machine learning models. Three different machine learning classifiers were built: a support vector classifier, a logistic regression classifier and a deep neural network classifier. Three different machine learning regressors were also built: a support vector regressor, a gradient boosted trees regressor and a deep neural network regressor. The results from the different models were compared to determine what machine learning models were suitable for the problem. The most important features for estimating the trouble ticket resolution time were also investigated. Two different prediction scenarios were investigated in this report. The first scenario uses the information available at the time of ticket creation to make a prediction. The second scenario uses the information available after it has been decided whether a technician will be sent to the affected site or not. The conclusion of the work is that it is easier to make a better resolution time estimation in the second scenario compared to the first scenario. The differences in results between the different machine learning models were small. Future work can include more information and data about the underlying root cause of the trouble tickets, more weather data and power outage information in order to make better predictions. A standardised way of recording and logging ticket data is proposed to make a future trouble ticket time estimation easier and reduce the problem of missing data. / Den här rapporten undersöker om maskininlärningsmetoder som regression och klassificering kan användas för att uppskatta hur lång tid det tar att lösa en felanmälan i ett telenät. Data från tidigare felanmälningar användes för att träna olika maskininlärningsmodeller. Tre olika klassificerare byggdes: en support vector-klassificerare, en logistic regression-klassificerare och ett neuralt nätverk-klassificerare. Tre olika regressionsmodeller byggdes också: en support vector-regressor, en gradient boosted trees-regressor och ett neuralt nätverk-regressor. Resultaten från de olika modellerna jämfördes för att se vilken modell som är lämpligast för problemet. En undersökning om vilken information och vilka datavariabler som är viktigast för att uppskatta tiden det tar att lösa felanmälan utfördes också. Två olika scenarion för att uppskatta tiden har undersökts i rapporten. Det första scenariot använder informationen som är tillgänglig när en felanmälan skapas. Det andra scenariot använder informationen som finns tillgänglig efter det har bestämts om en tekniker ska skickas till den påverkade platsen. Slutsatsen av arbetet är att det är lättare att göra en bra tidsuppskattning i det andra scenariot jämfört med det första scenariot. Skillnaden i resultat mellan de olika maskininlärningsmodellerna var små. Framtida arbete inom ämnet kan använda information och data om de bakomliggande orsakerna till felanmälningarna, mer väderdata och information om elavbrott. En standardiserad metod för att samla in och logga data för varje felanmälan föreslås också för att göra framtida tidsuppskattningar bättre och undvika problemet med datapunkter som saknas.

Today there exists two types of preventive surgical treatment procedures for Abdominal Aortic Aneurysm. In order to make an informed choice of treatment, the clinician needs to have a clear picture of how the choice will affect the patients chances of survival. In this master thesis, machine learning techniques are used to predict survival probabilities after respective treatment procedure and the performance is compared to the more conventional Kaplan-Meier estimator.  Using Danish patient data, different machine learning models for survival predictions were trained and evaluated by their performance. Administrative Brier Score was used as performance metric as the data was administratively censored. An Ensemble model consisting of one Random Survival Forest and one Neural Multi Task Logistic Regression model was shown to achieve the best performance and significantly outperformed the conventional Kaplan-Meier model. Furthermore, an approach to investigate the predicted effects of choice of treatment was introduced. It showed that on average the Ensemble model predicted the choice of treatment to have less effect on the long term survival than what the corresponding prediction using the Kaplan-Meier estimator suggested. This applies to the full patient group as well as for patients of age between 70 and 79 years. In the latter case this prediction was also shown to be more accurate. / Idag finns det två typer av förebyggande kirurgiska behandlingsmetoder för abdominal aortaaneurysm. För att göra ett välgrundat val av behandlingsmetod måste läkaren ha en tydlig bild av hur valet kommer att påverka patienternas överlevadschanser. I detta examensarbete används maskininlärningstekniker för att förutsäga överlevnadssannolikheten efter respektive behandlingsmetod och prestandan jämförs mot den mer konventionella Kaplan-Meier-estimatorn. Med hjälp av dansk patientdata tränades olika maskininlärningsmodeller avsedda för överlevnadanalys och utvärderades utifrån deras prestanda. Administrativt Brier Score användes som mätvärde då censureringen i datan skett administrativt. En Ensemble-modell bestående av en Random Survival Forest- och en Neural Multi-Task Logistic Regression-modell visade sig uppnå bäst prestanda och överträffade signifikant den konventionella Kaplan-Meier-estimatorn.  Dessutom introducerades ett tillvägagångssätt för att undersöka de predikterade effekterna av valet av behandling. Resultaten visade att Ensemble-modellen i genomsnitt förutspådde valet av behandling att ha mindre effekt på den långsiktiga överlevnaden än vad motsvarande förutsägelse med Kaplan-Meier-estimatorn föreslog. Detta både för alla patienter såväl som för patienter i åldern mellan 70 och 79 år. I det senare fallet visade sig denna förutsägelse också vara mer träffsäker.

In the manufacturing industry, predictive maintenance (PdM) stands out by leveraging data analytics and IoT technologies to predict machine failures, offering a significant advancement over traditional reactive and scheduled maintenance practices. The aim of this thesis was to examine how anomaly detection algorithms could be utilized to anticipate potential breakdowns in manufacturing operations, while also investigating the feasibility and potential benefits of integrating PdM strategies into a production line. The methodology of this projectconsisted of a literature review, application of machine learning (ML) algorithms, and conducting interviews. Firstly, the literature review provided a foundational basis to explore the benefits of PdM and its impact on production line productivity, thereby shaping the development of interview questions. Secondly, ML algorithms were employed to analyze data and predict equipment failures. The algorithms used in this project were: Isolation Forest (IF), Local Outlier Factor (LOF), Logistic Regression (LR), One-Class Support Vector Machine(OC-SVM) and Random Forest (RF). Lastly, interviews with production line personnel provided qualitative insights into the current maintenance practices and perceptions of PdM. The findings from this project underscore the efficacy of the IF model in identifying potential equipment failures, emphasizing its key role in improving future PdM strategies to enhance maintenance schedules and boost operational efficiency. Insights gained from both literature and interviews underscore the transformative potential of PdM in refining maintenance strategies, enhancing operational efficiency, and minimizing unplanned downtime. More broadly, the successful implementation of these technologies is expected to revolutionize manufacturing processes, driving towards more sustainable and efficient industrial operations. / I tillverkningsindustrin utmärker sig prediktivt underhåll (PdM) genom att använda dataanalys och IoT-teknologier för att förutse maskinfel, vilket erbjuder ett betydande framsteg jämfört med traditionella reaktiva och schemalagda underhållsstrategier. Syftet med denna avhandling var att undersöka hur algoritmer för avvikelsedetektering kunde användas för att förutse potentiella haverier i tillverkningsoperationer, samtidigt som genomförbarheten och de potentiella fördelarna med att integrera PdM-strategier i en produktionslinje undersöktes. Metodologin för detta projekt bestod av en litteraturöversikt, tillämpning av maskininlärningsalgoritmer (ML) och genomförande av intervjuer. Först och främst gav litteraturöversikten en grundläggande bas för att utforska fördelarna med PdM och dess inverkan på produktionslinjens produktivitet, vilket därmed påverkade utformningen av intervjufrågorna. För det andra användes ML-algoritmer för att analysera data och förutsäga utrustningsfel. Algoritmerna som användes i detta projekt var: Isolation Forest (IF), Local Outlier Factor (LOF), Logistic Regression (LR), One-Class Support Vector Machine (OCSVM) och Random Forest (RF). Slutligen gav intervjuer med produktionslinjepersonal kvalitativa insikter i de nuvarande underhållsstrategierna och uppfattningarna om PdM.Resultaten från detta projekt understryker effektiviteten hos IF-modellen för att identifiera potentiella utrustningsfel, vilket betonar dess centrala roll i att förbättra framtida PdM-strategier för att förbättra underhållsscheman och öka den operativa effektiviteten. Insikter vunna från både litteratur och intervjuer understryker PdM:s transformativa potential att finslipa underhållsstrategier, öka operativ effektivitet och minimera oplanerade driftstopp. Mer generellt förväntas den framgångsrika implementeringen av dessa teknologier revolutionera tillverkningsprocesser och driva mot mer hållbara och effektiva industriella operationer.

過去都市的發展與道路規劃多以汽機車為主體，對於自行車的騎乘環境相對不夠友善，而隨著近年國內自行車使用率逐年攀升，據資料指出自行車發生事故的機率也有提高的趨勢，顯示自行車於道路上之安全性考量更需重視。故本研究將針對台北市自行車肇事資料進行深入探討，找出影響肇事嚴重度之因素，進而從規劃設計面研擬降低自行車事故之改善策略。 本研究係以民國98年至102年台北市自行車事故資料為分析對象，將肇事嚴重程度分為「死亡或頭部受傷」、「人員受傷」及「未受傷」三類，同時根據文獻回顧及實務上所能取得之資料，蒐集人、路、環境等24項研究變數。首先透過統計分析了解肇事資料之特性，而後再以多項式羅吉斯迴歸模型，分別針對整體事故以及不同空間及不同事故型態之自行車肇事資料，建構自行車肇事嚴重度模型，以釐清影響自行車事故之主要因素。 研究結果顯示，道路因素中事故位置為路口及路段對於自行車事故皆有顯著影響，其中路口造成死亡或受傷之機率更高；環境因素中，因彎道或建物造成視距不良對於增加自行車事故亦有顯著影響，而坡道則會降低事故發生之機率；在人的因素中，18歲以下和年齡越大、酒駕、直行或右轉，皆會增加因自行車事故致死或受傷之機率。最後依據實證之結果，謹從交通管理中的3E政策-交通工程（Engineering）、交通教育（Education）及交通執法（Enforcement）三面向之觀念及角度帶入都市設計層面，提出道路及環境改善措施，以提升都市街道之自行車騎乘環境，並透過教育宣導、推廣活動及相關法令規範等配套措施，藉以增加自行車之騎乘安全。

A study was conducted on 74 school first- and second-team rugby players from four Pretoria high schools, to investigate whether start-up A-team players differ significantly from other (B-team start-up and reserve) players on emotional intelligence. It was further investigated whether emotional intelligence is a predictor of rugby performance if measured as being included into the study’s ‘best team’ or being a start-up A-team school rugby player. Various other physical, psychological, social and spiritual predictors were also investigated singularly and in combination with the emotional intelligence predictor to indicate performance. Data were gathered through a self-reporting questionnaire developed by the researcher. The main methods for analysing data used included the Mann-Whitney Test and the Logistic Regression analysis. The study found certain spiritual and social predictor aspects to be significantly related to performance in rugby but not emotional intelligence. Certain underlying emotional aspects where more significant to the study’s B-team players’ performance. / Spiritual aspects / M.A. (Psychology)

Résumé : Objectif : Identifier les facteurs associés avec le succès d’une intervention multidisciplinaire de prise en charge et de prévention des maladies chroniques dans un contexte de soins de santé de première ligne. Devis : Étude corrélationnelle prédictive d’analyse secondaire des données du projet PR1MaC, un essai randomisé contrôlé analysant les effets d’une intervention intégrant un programme de prise en charge et de prévention Contexte : Huit cliniques de soins de première ligne de la région Saguenay-Lac-Saint-Jean. Participants : un échantillon de 160 patients (52,5% d’hommes) référés par des professionnels de première ligne. L’analyse a porté sur le groupe intervention seulement. Mesure de résultats primaire : Mesure d’amélioration significative dans les huit domaines du «Health Education Impact Questionnaire». Résultat : L’analyse de régression multivariée a démontré qu’être plus jeune, être célibataire et avoir un salaire plus bas a mené à plus d’amélioration au niveau du domaine « Bien-être émotionnel »; avoir de bonnes habitudes alimentaires et cibler moins de facteurs de risque durant l’intervention a mené à plus d’amélioration au niveau du domaine « Approches et attitudes constructives »; être plus jeune, avoir plus de temps de contact avec les professionnels et avoir une concertation des professionnels a mené à plus d’amélioration dans le domaine « Approches et attitudes constructives »; avoir plus de temps de contact avec les professionnels a aussi eu une influence sur l’amélioration du domaine « Engagement positif et actif dans la vie » et avoir un plus grand nombre de professionnels intervenant chez une même personne a démontré plus d’amélioration dans le domaine « Acquisition des techniques et habiletés ». Aucun facteur prédictif n’a pu être identifié pour les domaines « Comportements de santé », « Intégration sociale et soutien » et « Auto-surveillance et discernement ». Seulement les résultats statistiquement significatifs sont présentés (valeur p ≥ 0,05). La petite taille de l'échantillon ainsi que la possibilité d'une perte de signification des résultats après certains ajustements statistiques suggèrent que ces observations devraient faire l'objet d'une validation plus approfondie dans d'autres études. Conclusion : La tentative d’identification des facteurs prédictifs de résultats de cette recherche contribue à la compréhension des mécanismes complexes de l’efficacité et offre des pistes quant à l’optimisation des programmes de prévention et de gestion des maladies chroniques. // Abstract : Context : Research on the factors associated with the successes of chronic disease prevention and management (CDPM) interventions is scarce. Objectives : To identify the factors associated with the successes of an interprofessional CDPM intervention among adult patients in primary healthcare (PHC) settings. Design : Secondary analysis of data from the PR1MaC project; a pragmatic randomized controlled trial looking at the effects of an intervention involving the integration of CDPM services in PHC. Settings : Eight PHC practices in the Saguenay - Lac - Saint - Jean region of Quebec, Canada. Participants : A sample of 160 patients (84 males) referred by PHC providers constituted the sample (mean age 52.66 ± 11.5 years); 98.5% presented two or more chronic conditions analysis focused on the intervention arm sample only. Main and secondary outcome measures : Dichotomic substantive improvement in the eight domains of the Health Education Impact questionnaire (hei Q) measured at baseline and three months later. Results : Multivariate logistic regression analysis showed that being younger, being single and having a lower family income led to a better improvement in the emotional wellbeing domain; having healthy eating habits and less objectives during the intervention led to improvement in the constructive attitudes and approaches domain; being younger, a longer intervention and a consensus of professionals led to improvement in the health services navigation domain; a longer intervention led to improvement in the positive and active engagement in life domain and having more professionals involved led to improvement in the Skills and techniques acquisition domain. No predictive factors were identified for the Health - directed behaviour, Social interaction and support and S elf - monitoring and insight domains. Only significant results are presented here (p - value ≥ 0.05). The small sample and the lost of significance after statistical adjustments suggest that observations should be validated by other studies. Conclusion: In an attempt to make causal inferences in regards to improvement, this research contributes to the understanding of the complex mechanisms of efficiency and provides information about the optimisation of CDPM program delivery.

This study was conducted in the Nkangala district, in the province of Mpumalanga in South Africa. This province remains the largest forestry production region in South Africa. The majority of people living in Mpumalanga are farmers and they have contributed immensely to promote food security. The objective of the study was to determine the level of climate change awareness among small scale maize producers in Mpumalanga province. Random sampling techniques was used to select two hundred and fifty one (251) farmers to be interviewed. A pre-tested questionnaire was administered to maize farmers, focusing on matters relating to climate change awareness in maize production. Data was captured and analysed using software package for social science (SPSS version 20 of 2012). Descriptive statistics were applied to analyse and describe the data. Logistic regression analysis followed to demonstrate the significance of the independent variables on climate change awareness. The results of the analysis indicated that the information received and the size of the farm had an impact on climate change awareness in the area of study. It was therefore recommended that the majority of farmers in Mpumalanga needed to be made aware of climate change in order to assist them to build the adaptive capacity, increase resilience and reduce vulnerability. Information on climate change awareness should be disseminated well to ensure that it will attract the attention of the farmers / Agriculture and  Animal Health / M.Sc. (Agriculture)

The aim of this thesis was to investigate the use of effect sizes to report the results of statistical credit rating models in a more practical way. Rating systems in the form of statistical probability models like logistic regression models are used to forecast the behaviour of clients and guide business in rating clients as “high” or “low” risk borrowers. Therefore, model results were reported in terms of statistical significance as well as business language (practical significance), which business experts can understand and interpret. In this thesis, statistical results were expressed as effect sizes like Cohen‟s d that puts the results into standardised and measurable units, which can be reported practically. These effect sizes indicated strength of correlations between variables, contribution of variables to the odds of defaulting, the overall goodness-of-fit of the models and the models‟ discriminating ability between high and low risk customers. / Statistics / M. Sc. (Statistics)