Studien har som mål att undersöka utfall efter stroke med hjälp av två statistiska modeller. Mer specifikt är det av intresse att prediktera risken att avlida eller få en nedsatt funktionsförmåga efter en stroke samt även jämföra prediktionsförmågan för de två modellerna. För att undersöka detta har en Ordinal regression och Random Forest modell applicerats på ett datamaterial från det svenska strokeregistret Riksstroke. Båda modellerna producerar bra prediktioner som hade ett testfel på cirka 25 procent. Resultaten visar att det inte finns några större skillnader mellan modellerna i avseende på  prediktionsförmåga. Då resultaten är liknande vägs även andra aspekter in i jämförelsen. Ordinal regression har en hög tolkningsbarhet på modellkoefficienterna medan Random Forest är mer svårtolkad. Även modelleringsprocessen tas i beräkning där Ordinal regression kräver mer manuell hantering än Random Forest.

No description available.

No description available.

Over the past few years there has been an exponentially increasing attention in financetowards socially responsible investments which creates a need to determine whether acompany is socially responsible or not. The ESG ratings often used to do this are based onEnvironmental, Social and Governance related data about the companies and have manyflaws. This thesis proposes to instead model them by their controversies discussed in themedia. It tries to answer the question if it is possible to predict future controversies of acompany by its controversies and ESG indicators in the past and to isolate predictors whichinfluence these. This has not been done before and offers a new way of rating companieswithout falling for the biases of conventional ESG ratings. The chosen method to approachthis issue is the Zero Inflated Poisson Regression with Random Intercepts. A selectionof variables was determined by Lasso and projection predictive variable selection. Thismethod discovered new connections in the data between ESG indicators and the numberof controversies but also made it apparent that it is difficult to make predictions for futureyears. Nether the less the coefficients of the selected indicators can give a valuable insightinto the potential risk of an investment.

Kungliga biblioteket (National Library of Sweden, KB) uses Optical Character Recognition (OCR) engines to extract and segment texts from their archive of daily newspaper articles. These systems are good at extracting and segmenting text on the paragraph level and lower (i.e., sentences, words, and characters), but less on the article level, resulting in the segmentation of articles into text blocks not attached to their articles. In this thesis, BERT, a natural language processing (NLP) model, is fine-tuned on newspaper articles and used to reconstruct these articles by predicting if a text block is the next or not.  A small data set of 127 text blocks from 21 articles is used.  The best performing BERT achieved an accuracy of 94% on text block pair prediction when the blocks are ordered. It resulted in 13 reconstructed articles. The performance was reduced when selecting from all possible, unordered text pairs. It was also found that BERT performs well on clustering text blocks from the same articles.

The aim of this thesis is to investigate what in the ad insertion affects how fast a car is sold on Blocket, a Swedish marketplace for second-hand goods. The method, through which the issue was investigated, is the machine learning algorithm random forest. Three models have been created and optimized, each with different datasets. Despite the models’ differences, the results were similar for the three models – their R2 and MAE values indicate that the variables for ad insertion explain little about how long it takes until a car is sold on Blocket. Of the variables in the models, the most important in all three models had to do with the pricing of the car. The results also show that the length of the description, is the second most important variable that the seller can impact herself, of those variables included in this investigation.

No description available.

In this thesis, we analyse and evaluate classification models for panel credit risk data. Variables are selected based on results from recursive feature elimination as well as economic reasoning where the probability of default is estimated. We employ several machine learning and statistical techniques and assess the performance of each model based on AUC, Brier score as well as the absolute mean difference between the predicted and the actual outcome, carried out with cross validation of four folds and extensive hyperparameter optimization. The LightGBM model had the best performance and many machine learning models showed a superior performance compared to traditional models like logistic regression. Hence, the results of this thesis show that machine learning models like gradient boosting models, neural networks and voting models have the capacity to challenge traditional statistical methods such as logistic regression within credit risk modelling.

No description available.

The LLL algorithm is recognized as one of the most important achievements of twentieth century with applications across many fields in mathematics. Yet, the subject is explained only on an advanced level in the current literature. We systematically present background and key concepts needed to understand the underlying problematic and afterwards give detailed proofs of all ideas needed to understand the algorithm. The paper focuses on application to lattice problems and proving results pre-sented in the original paper of A. K. Lenstra et al. published in 1982.