Sökning: "Gradient boosting decision trees"

Visar resultat 1 - 5 av 11 uppsatser innehållade orden Gradient boosting decision trees.

1. 1. Prediction of Stock Returns Using Accounting Data with a Machine Learning Approach

   Master-uppsats, Göteborgs universitet/Graduate School

   Författare :Ludvig Ekmark; Tobias Frisell; [2022-06-30]
   Nyckelord :Stock price prediction; Accounting data; Machine learning; Gradient boosting decision trees; CatBoost classifier; Logistic regression; Feature importance;

   Sammanfattning : The relationship between accounting data and stock price prediction has been a hot topic for over half a century. Researchers have been trying to identify the relationship and investigate how it may be useful when trying to improve prediction accuracy. LÄS MER

3. 2. Anticipating bankruptcies among companies with abnormal credit risk behaviour : Acase study adopting a GBDT model for small Swedish companies

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

   Författare :Simon Heinke; [2022]
   Nyckelord :Bankruptcy prediction; Credit risk analysis; Abnormal credit risk behaviour; Gradient boosted decision trees; SHAP-values.; Konkurs förutsägelse; Kredit riskanalys; Abnomralt kreditbeteende; Gradient baserat beslutsträd; SHAP-värden.;

   Sammanfattning : The field of bankruptcy prediction has experienced a notable increase of interest in recent years. Machine Learning (ML) models have been an essential component of developing more sophisticated models. Previous studies within bankruptcy prediction have not evaluated how well ML techniques adopt for data sets of companies with higher credit risks. LÄS MER

4. 3. Risk Evaluation in a ML-Approximated Portfolio Environment

   Master-uppsats, KTH/Matematik (Avd.)

   Författare :Filip Franzén; Karl Axel Nord; [2022]
   Nyckelord :Financial risk management; forecasting; machine learning; FMCG; Finansiell riskhantering; prognostisering; maskininlärning; konsumtionsvaror;

   Sammanfattning : This thesis explores and evaluates the forecasting application of the machine learning method Gradient Boosting Decision Trees. This method is used to forecast the demand of the online grocery market with a 7-day time horizon. The thesis was conducted in collaboration with the online grocery company Mathem. LÄS MER

5. 4. Prediction of Short-term Default Probability of Credit Card Invoices Using Behavioural Data

   Master-uppsats, KTH/Matematisk statistik

   Författare :Billy Lu; [2022]
   Nyckelord :Probability of Default; Credit Risk; Short-term Default Prediction; Machine Learning; Gradient Boosting; Thresholding; Sannolikheten för Fallissemang; Kreditrisk; Kortsiktig Fallissemang Prediktion; Maskininlärning; Gradientförstärkning; Tröskling;

   Sammanfattning : Probability of Default (PD) is a standard metric to model and monitor credit risk, a major risk facing financial institutions. Traditional PD models are used to forecast risk levels in the long-term, while short-term PD predictions are rarer, but they can support management decisions on an operational level. LÄS MER

7. 5. Friends character classification personality quiz

   Kandidat-uppsats, Uppsala universitet/Avdelningen för systemteknik

   Författare :Ruben Hedström; Leon Lovén; Simon Mojtahedi; Fredrik Malmström; [2021]
   Nyckelord :Quiz; Friends; Machine learning; Information technology;

   Sammanfattning : The purpose of this project was to create a personality quiz based on the scientifical method and machine learning that determine which character in the TV-series Friends that the person taking the quiz is the most similar to. The manuscripts from all the episodes were used to extract features and create a split training/test dataset. LÄS MER