Description
This book aims to present an overview of grey system models for time series modelling and forecasting. It is about modelling and forecasting time series with ordinary differential equations, especially when the available samples are extremely limited. Grey system models (GSM) develop sequence operators to nonparametrically identify the underlying dynamics from the limited observations. This book concerns about two important modelling themes, small sample and poor information. The former focuses on the mechanism and methodology of GSMs for small-sample real-number time series, and the latter on the uncertainty quantification of grey number together with its small-sample modelling principles. In this book, a broad entry point to applied data science for students majoring in economic, management science, and engineering is applied, covering a wide range of topics from basic introductory material up to research-level techniques.
Table of Contents
1. Introduction.- 2. Architecture of grey forecasting models.- 3. Mechanism and reduction of grey forecasting models.- 4. Continuous-time grey endogenous forecasting models.- 5. Discrete-time grey endogenous forecasting models.- 6. Continuous-time grey exogenous forecasting models.- 7. Discrete-time grey exogenous forecasting models.- 8. Nonlinear grey forecasting models.- 9. Grey number-oriented forecasting models.- 10. Comments and future thinking.
