Sökning: "Predictive Value"

Visar resultat 1 - 5 av 211 uppsatser innehållade orden Predictive Value.

1. 1. Predicting True Sepsis and Culture-positive Sepsis in Intensive Care Unit with Machine Learning Techniques

   Master-uppsats, Lunds universitet/Matematisk statistik

   Författare :Zeyuan Wu; [2024]
   Nyckelord :Machine Learning; Diagnosis of Sepsis; XGBoost; Logistic Regression; Mathematics and Statistics;

   Sammanfattning : Sepsis, a serious medical condition often leading to patients requiring intensive care, has prompted numerous scientists to employ mathematical techniques to aid in its diagnosis. This thesis uses logistic regression and a machine learning technique, XGBoost, to predict true sepsis (as opposed to sepsis mimics) and culture-positive sepsis (among true sepsis) in critical care using blood test results, physiological measurements and other patient characteristics. LÄS MER

3. 2. The Missing Ingredient: How to improve value investing in the information age

   D-uppsats, Handelshögskolan i Stockholm/Institutionen för redovisning och finansiering

   Författare :Robin Grawe; Kjell Thomsen; [2023]
   Nyckelord :Value investing; Fama-French; Intangible Assets; Accounting-based valuation;

   Sammanfattning : This thesis aims to inform a value investing strategy in specific niches of European firms by adjusting the book-to-market (B/M) ratio for intangible assets. An increase in intangible assets' importance for corporate value creation coupled with a lack of amendments to their accounting treatment has led to debates on the value relevance and accuracy of accounting information, including the B/M ratio used to derive value premiums. LÄS MER

4. 3. Assessment and evaluation of heterogeneity in data from immune infiltration spatial niches in lung cancer

   Kandidat-uppsats, Lunds universitet/Matematisk statistik

   Författare :Mahta Keivani Najafabadi; [2023]
   Nyckelord :Mathematics and Statistics;

   Sammanfattning : The protein biomarker expressions in three types of sampled immune INFILTration spatial niches in lung cancer tissue were measured using the new technology Digital Spatial Profiler (DSP). The three types of immune INFILTration that were observed in lung tumors were STROMA identified as immune cells separate from tumor cells, Tertiary lymphoid structures (TLS) identified as dense structures of organized immune cells and finally Infiltraterate where immune cells dispersed among and in direct contact with tumor cells (INFILT). LÄS MER

5. 4. Ferdinand, the Unpredictable Bull : Cash Flow Distribution Behavior During U.S. Recessions - An Event Time Analysis

   C-uppsats, Handelshögskolan i Stockholm/Institutionen för finansiell ekonomi

   Författare :Erik Gunnarsson; Tom Mueffelmann; [2023]
   Nyckelord :Business Cycles; Event Time Study; Predictability of the Price-Dividend Ratio; Aggregate Dividends; Net Repurchases;

   Sammanfattning : The paper employs an event study approach to investigate the behavior of aggregate cash flow distributions and stock prices in the U.S. stock market around recessions. Aggregate prices anticipate low aggregate dividend and economic growth until adjusting for the diverse time measurement methodologies. LÄS MER

7. 5. Predicting user churn using temporal information : Early detection of churning users with machine learning using log-level data from a MedTech application

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Love Marcus; [2023]
   Nyckelord :User churn; Customer attrition; Artificial neural networks; Log-level analysis; Random forests; Decision trees; Användarbortfall; Kundbortfall; Artificiella neurala nätverk; logganalys; Slumpskogar; Beslutsträd;

   Sammanfattning : User retention is a critical aspect of any business or service. Churn is the continuous loss of active users. A low churn rate enables companies to focus more resources on providing better services in contrast to recruiting new users. LÄS MER