Sökning: "Rekursiva neurala nätverk"

Visar resultat 1 - 5 av 6 uppsatser innehållade orden Rekursiva neurala nätverk.

1. 1. Modelling Proxy Credit Cruves Using Recurrent Neural Networks

   Master-uppsats, KTH/Matematisk statistik

   Författare :Lucas Fageräng; Hugo Thoursie; [2023]
   Nyckelord :Deep Neural Networks; Credit Risk; Financial Modelling; LSTM; Credit Default Swaps; Credit Valuation Adjustment; Djupa Neurala Nätverk; Kreditrisk; Finansiell Modellering; LSTM; Kreditswappar; Kreditvärderingsjustering;

   Sammanfattning : Since the global financial crisis of 2008, regulatory bodies worldwide have implementedincreasingly stringent requirements for measuring and pricing default risk in financialderivatives. Counterparty Credit Risk (CCR) serves as the measure for default risk infinancial derivatives, and Credit Valuation Adjustment (CVA) is the pricing method used toincorporate this default risk into derivatives prices. LÄS MER

3. 2. Automatic event detection oncontinuous glucose datausing neural networks

   Master-uppsats, KTH/Skolan för kemi, bioteknologi och hälsa (CBH)

   Författare :David Borghäll; [2023]
   Nyckelord :Automatic Event Detection; Continuous Glucose Monitor; Deep Learning; Diabetes Mellitus; Automatisk Eventdetektion; Kontinuerlig Glukosmätare; Djupinlärning; Diabetes;

   Sammanfattning : Automatically detecting events for people with diabetes mellitus using continuousglucose monitors is an important step in allowing insulin pumps to automaticallycorrect the blood glucose levels and for a more hands-off approach to thedisease. The automatic detection of events could also aid physicians whenassisting their patients when referring to their continuous glucose monitordata. LÄS MER

4. 3. Time Dependencies Between Equity Options Implied Volatility Surfaces and Stock Loans, A Forecast Analysis with Recurrent Neural Networks and Multivariate Time Series

   Master-uppsats, KTH/Matematik (Avd.)

   Författare :Simon Wahlberg; [2022]
   Nyckelord :RNN; LSTM; GRU; vector autoregression; implied volatility surface; stock loan; equity options; multivariate time-series analysis; financial mathematics.; Rekursiva neurala nätverk; LSTM; GRU; VAR; implicerade volatilitetsytor; aktielån; aktieoptioner; multidimensionell tidsserieanalys; finansiell matematik.;

   Sammanfattning : Synthetic short positions constructed by equity options and stock loan short sells are linked by arbitrage. This thesis analyses the link by considering the implied volatility surface (IVS) at 80%, 100%, and 120% moneyness, and stock loan variables such as benchmark rate (rt), utilization, short interest, and transaction trends to inspect time-dependent structures between the two assets. LÄS MER

5. 4. Scenario Reduction in Debt Simulations Using Recurrent Autoencoders : Finding Meaningful Patterns in Stochastic Processes

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

   Författare :Love Eklund; [2021]
   Nyckelord :;

   Sammanfattning : This thesis studies how improvements can be made to a simulation model used to analyse debt portfolios. Today, the simulation model needs to evaluate a portfolio over a large sample of scenarios to get accurate results. This can be time-consuming if the portfolios consist of many different and complex securities. LÄS MER

7. 5. Topological recursive fitting trees : A framework for interpretable regression extending decision trees

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

   Författare :Alexandre Tadros; [2020]
   Nyckelord :;

   Sammanfattning : Many real-world machine learning applications need interpretation of an algorithm output. The simplicity of some of the most fundamental machine learning algorithms for regression, such as linear regression or decision trees, facilitates interpretation. However, they fall short when facing complex (e.g. LÄS MER