Sökning: "DeepHit"

Hittade 2 uppsatser innehållade ordet DeepHit.

1. 1. Deep Learning Approach for Time- to-Event Modeling of Credit Risk

   Master-uppsats, KTH/Matematisk statistik

   Författare :Mehnaz Kazi; Natalija Stanojlovic; [2022]
   Nyckelord :Survival Analysis; Credit Risk; Credit Scoring; Time-To-Event; Default Probability; Överlevnadsanalys; Kreditrisk; Kreditprövning; Tid-till-utfall; Sannolikhet för fallissemang;

   Sammanfattning : This thesis explores how survival analysis models performs for default risk prediction of small-to-medium sized enterprises (SME) and investigates when survival analysis models are preferable to use. This is examined by comparing the performance of three deep learning models in a survival analysis setting, a traditional survival analysis model Cox Proportional Hazards, and a traditional credit risk model logistic regression. LÄS MER

3. 2. Survival Comparison of Open and Endovascular Repair Using Machine Learning

   Master-uppsats, KTH/Matematik (Avd.)

   Författare :Aston Brunnberg; Gustaf Holte; [2021]
   Nyckelord :Master Thesis; Degree Project; Machine Learning; Survival Analysis; Abdominal Aortic Aneurysm; AAA; Kaplan-Meier; Survival Tree; Random Survival Forest; Neural Multi-Task Logistic Regression; DeepHit; Examensarbete; Masteruppsats; Maskininlärning; Överlevnadsanalys; Abdominellt Aortaaneurysm; AAA; Kaplan-Meier; Survival Tree; Random Survival Forest; Neural Multi-Task Logistic Regression; DeepHit;

   Sammanfattning : 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. LÄS MER