Loading...

Improving Artificial Neural Network Predictive Performance Using Panel Data

Alirezaei, Hamid Reza | 2019

521 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 53095 (01)
  4. University: Sharif University of Technology
  5. Department: Industrial Engineering
  6. Advisor(s): Khedmati, Majid; Rafiee, Majid
  7. Abstract:
  8. The purpose of the present study is to develop neural network estimation method for hybrid or panel data which have a combination of two cross-sectional and time series structures and because of the features of both structures, their use in different sciences offers many advantages; and the analytical methods for this data structure are also different from other one-dimensional structures, so different and specific regression models are presented for this data structure. However, in the artificial neural network method, modeling the development for this data structure is neglected, so in the present study, using the concepts of panel regression methods and their application to the development of neural networks, the ability of this tool to analyze these data is improved. In order to accomplish the above objective, after collecting panel data and analyzing these data using Chow test to identify the model required for estimation, panel regression method, conventional neural network method and proposed hybrid method were applied to the data and results of applying these concepts for the neural network, the performance of all models is improved. Furthermore, among these methods, the performance of the hybrid least squares dummy variable method was better than other hybrid ones
  9. Keywords:
  10. Artificial Neural Network ; Panel Data ; Multi-Layer Perceptron (MLP) ; Panel Regression ; Panel Data Estimation ; Hybrid Data

 Digital Object List

 Bookmark

No TOC