Can I read Kernel-based Copula Processes for Time-Series Analysis on EtoBox?
Kernel-based Copula Processes for Time-Series Analysis by Sapto Indratno is a document available to read on EtoBox.
What is Kernel-based Copula Processes for Time-Series Analysis about?
This thesis introduces Kernel-based Copula Processes (KCPs), a novel framework for analyzing non-Gaussian and non-stationary time-series data by combining copula theory with machine learning techniques. KCPs effectively separate marginal behaviors from serial dependencies, allowing for flexible modeling of complex relationships and superior predictive capabilities across various applications such as finance and meteorology. The framework also extends to classification problems, demonstrating its versatility
- Author
- Sapto Indratno
- Language
- EN